{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/speech-synthesis","name":"Speech Synthesis","slug":"speech-synthesis","description_markdown":"Speech synthesis is the task of generating speech from some other modality like text, lip movements etc. \r\n\r\nPlease note that the leaderboards here are not really comparable between studies - as they use mean opinion score as a metric and collect different samples from Amazon Mechnical Turk.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [WaveNet: A generative model for raw audio](https://deepmind.com/blog/article/wavenet-generative-model-raw-audio) )</span>","categories":[{"name":"Audio","url":"/area/audio"},{"name":"Speech","url":"/area/speech"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":1249,"papers_with_code":366,"benchmarks":5,"benchmark_tables_in_archive":5,"benchmark_tables_shown":5,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":22,"subtasks":15,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/speech-synthesis-on-libritts","slug":"speech-synthesis-on-libritts","dataset":"LibriTTS","dataset_url":"/dataset/libritts","rows_in_archive":15,"metrics":["PESQ","M-STFT","MCD","Periodicity","V/UV F1"],"first_row_in_archive_order":{"model":"PeriodWave-Turbo-L","paper_title":"Accelerating High-Fidelity Waveform Generation via Adversarial Flow Matching Optimization","paper_url":"/paper/accelerating-high-fidelity-waveform","paper_date":"2024-08-15","arxiv_id":"2408.08019","code_links":[{"title":"sh-lee-prml/periodwave","url":"https://github.com/sh-lee-prml/periodwave"}],"syntology":null}},{"leaderboard":"/sota/speech-synthesis-on-north-american-english","slug":"speech-synthesis-on-north-american-english","dataset":"North American English","dataset_url":null,"rows_in_archive":7,"metrics":["Mean Opinion Score"],"first_row_in_archive_order":{"model":"Tacotron 2","paper_title":"Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions","paper_url":"/paper/natural-tts-synthesis-by-conditioning-wavenet","paper_date":"2017-12-16","arxiv_id":"1712.05884","code_links":[{"title":"coqui-ai/TTS","url":"https://github.com/coqui-ai/TTS"},{"title":"PaddlePaddle/PaddleSpeech","url":"https://github.com/PaddlePaddle/PaddleSpeech"},{"title":"NVIDIA/tacotron2","url":"https://github.com/NVIDIA/tacotron2"},{"title":"TensorSpeech/TensorflowTTS","url":"https://github.com/TensorSpeech/TensorflowTTS"},{"title":"Rayhane-mamah/Tacotron-2","url":"https://github.com/Rayhane-mamah/Tacotron-2"},{"title":"xcmyz/FastSpeech","url":"https://github.com/xcmyz/FastSpeech"},{"title":"Jeevesh8/Cross-Lingual-Voice-Cloning","url":"https://github.com/Jeevesh8/Cross-Lingual-Voice-Cloning"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/research/audio/tacotron2"},{"title":"BogiHsu/Tacotron2-PyTorch","url":"https://github.com/BogiHsu/Tacotron2-PyTorch"},{"title":"dipjyoti92/SC-WaveRNN","url":"https://github.com/dipjyoti92/SC-WaveRNN"},{"title":"bfs18/tacotron2","url":"https://github.com/bfs18/tacotron2"},{"title":"keonlee9420/Comprehensive-Tacotron2","url":"https://github.com/keonlee9420/Comprehensive-Tacotron2"},{"title":"codetendolkar/tacotron-2-explained","url":"https://github.com/codetendolkar/tacotron-2-explained"},{"title":"thuhcsi/tacotron","url":"https://github.com/thuhcsi/tacotron"},{"title":"kaiidams/voice100","url":"https://github.com/kaiidams/voice100"},{"title":"kaiidams/voice100-tts","url":"https://github.com/kaiidams/voice100-tts"},{"title":"dipjyoti92/TTS-Style-Transfer","url":"https://github.com/dipjyoti92/TTS-Style-Transfer"},{"title":"dathudeptrai/TensorflowTTS","url":"https://github.com/dathudeptrai/TensorflowTTS"},{"title":"creotiv/RussianTTS-Tacotron2","url":"https://github.com/creotiv/RussianTTS-Tacotron2"},{"title":"rosinality/melgan-pytorch","url":"https://github.com/rosinality/melgan-pytorch"},{"title":"xinshengwang/Tacotron-pytorch","url":"https://github.com/xinshengwang/Tacotron-pytorch"},{"title":"izzajalandoni/tts_models","url":"https://github.com/izzajalandoni/tts_models"},{"title":"choiHkk/Transformer-TTS","url":"https://github.com/choiHkk/Transformer-TTS"},{"title":"anandaswarup/rnn-tts","url":"https://github.com/anandaswarup/rnn-tts"},{"title":"anandaswarup/TTS","url":"https://github.com/anandaswarup/TTS"},{"title":"jiean001/models_m","url":"https://github.com/jiean001/models_m/tree/main/tacotron2"},{"title":"OlaWod/my-tacotron2","url":"https://github.com/OlaWod/my-tacotron2"},{"title":"thepowerfuldeez/tacotron2","url":"https://github.com/thepowerfuldeez/tacotron2"},{"title":"alpharol/Taco_Collection","url":"https://github.com/alpharol/Taco_Collection"},{"title":"s3nh/pytorch-tacotron2","url":"https://github.com/s3nh/pytorch-tacotron2"},{"title":"martinlenglet/avtacotron2","url":"https://github.com/martinlenglet/avtacotron2"},{"title":"MindSpore-paper-code-2/code400","url":"https://github.com/MindSpore-paper-code-2/code400/tree/main/Tacotron2"},{"title":"vincenzo-scotti/tacotron2","url":"https://github.com/vincenzo-scotti/tacotron2"}],"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/natural-tts-synthesis-by-conditioning-wavenet#ran","syntology_url":"https://syntology.ai/paper/1712.05884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1712.05884"}},"official":null}}},{"leaderboard":"/sota/speech-synthesis-on-ljspeech","slug":"speech-synthesis-on-ljspeech","dataset":"LJSpeech","dataset_url":"/dataset/ljspeech","rows_in_archive":4,"metrics":["Mean Opinion Score"],"first_row_in_archive_order":{"model":"BDDM vocoder","paper_title":"BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis","paper_url":"/paper/bddm-bilateral-denoising-diffusion-models-for-1","paper_date":"2022-03-25","arxiv_id":"2203.13508","code_links":[{"title":"tencent-ailab/bddm","url":"https://github.com/tencent-ailab/bddm"}],"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/bddm-bilateral-denoising-diffusion-models-for-1#ran","syntology_url":"https://syntology.ai/paper/2203.13508","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.13508"}},"official":{"repos":["tencent-ailab/bddm"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/speech-synthesis-on-mandarin-chinese","slug":"speech-synthesis-on-mandarin-chinese","dataset":"Mandarin Chinese","dataset_url":null,"rows_in_archive":3,"metrics":["Mean Opinion Score"],"first_row_in_archive_order":{"model":"WaveNet (L+F)","paper_title":"WaveNet: A Generative Model for Raw Audio","paper_url":"/paper/wavenet-a-generative-model-for-raw-audio","paper_date":"2016-09-12","arxiv_id":"1609.03499","code_links":[{"title":"ibab/tensorflow-wavenet","url":"https://github.com/ibab/tensorflow-wavenet"},{"title":"awslabs/gluon-ts","url":"https://github.com/awslabs/gluon-ts"},{"title":"karpathy/makemore","url":"https://github.com/karpathy/makemore"},{"title":"basveeling/wavenet","url":"https://github.com/basveeling/wavenet"},{"title":"vincentherrmann/pytorch-wavenet","url":"https://github.com/vincentherrmann/pytorch-wavenet"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/research/audio/wavenet"},{"title":"swasun/VQ-VAE-Speech","url":"https://github.com/swasun/VQ-VAE-Speech"},{"title":"WLM1ke/poptimizer","url":"https://github.com/WLM1ke/poptimizer"},{"title":"Baichenjia/Tensorflow-TCN","url":"https://github.com/Baichenjia/Tensorflow-TCN"},{"title":"MSRDL/Deep4Cast","url":"https://github.com/MSRDL/Deep4Cast"},{"title":"albarji/neurowriter","url":"https://github.com/albarji/neurowriter"},{"title":"randomrandom/deep-atrous-cnn-sentiment","url":"https://github.com/randomrandom/deep-atrous-cnn-sentiment"},{"title":"ashishpatel26/tcn-keras-Examples","url":"https://github.com/ashishpatel26/tcn-keras-Examples"},{"title":"HaiFengZeng/clari_wavenet_vocoder","url":"https://github.com/HaiFengZeng/clari_wavenet_vocoder"},{"title":"rampage644/wavenet","url":"https://github.com/rampage644/wavenet"},{"title":"ZhouYuxuanYX/Wavenet-in-Keras-for-Kaggle-Competition-Web-Traffic-Time-Series-Forecasting","url":"https://github.com/ZhouYuxuanYX/Wavenet-in-Keras-for-Kaggle-Competition-Web-Traffic-Time-Series-Forecasting"},{"title":"PeihaoChen/regnet","url":"https://github.com/PeihaoChen/regnet"},{"title":"ShichengChen/WaveNetSeparateAudio","url":"https://github.com/ShichengChen/WaveNetSeparateAudio"},{"title":"scpark20/universal-music-translation","url":"https://github.com/scpark20/universal-music-translation"},{"title":"peustr/wavenet","url":"https://github.com/peustr/wavenet"},{"title":"stdereka/liverpool-ion-switching","url":"https://github.com/stdereka/liverpool-ion-switching"},{"title":"Chasm4359/ProTS","url":"https://github.com/Chasm4359/ProTS"},{"title":"PhilippeNguyen/keras_wavenet","url":"https://github.com/PhilippeNguyen/keras_wavenet"},{"title":"TanUkkii007/wavenet","url":"https://github.com/TanUkkii007/wavenet"},{"title":"thorwhalen/slang","url":"https://github.com/thorwhalen/slang"},{"title":"otosense/slang","url":"https://github.com/otosense/slang"},{"title":"thorwhalen/sla","url":"https://github.com/thorwhalen/sla"},{"title":"zhong110020/keras-tcn","url":"https://github.com/zhong110020/keras-tcn"},{"title":"LucaHermes/lightweight-motion-forecasting","url":"https://github.com/LucaHermes/lightweight-motion-forecasting"},{"title":"kingstarcraft/speech-to-text-wavenet2","url":"https://github.com/kingstarcraft/speech-to-text-wavenet2"},{"title":"AI-Huang/WaveNet","url":"https://github.com/AI-Huang/WaveNet"},{"title":"coreyoconnor/tensorderp","url":"https://github.com/coreyoconnor/tensorderp"},{"title":"Talk2Levi/DJL","url":"https://github.com/Talk2Levi/DJL"},{"title":"r9y9/wavenet","url":"https://github.com/r9y9/wavenet"},{"title":"ShuSQ/CCI_AP_PoseLoops","url":"https://github.com/ShuSQ/CCI_AP_PoseLoops"},{"title":"yebiny/DepthOfAnaesthesia_eeg","url":"https://github.com/yebiny/DepthOfAnaesthesia_eeg"},{"title":"ShotDownDiane/tcn-master","url":"https://github.com/ShotDownDiane/tcn-master"},{"title":"isadrtdinov/wavenet","url":"https://github.com/isadrtdinov/wavenet"},{"title":"imdatsolak/wavenet","url":"https://github.com/imdatsolak/wavenet"},{"title":"DevonFulcher/CryptoPricePredictor","url":"https://github.com/DevonFulcher/CryptoPricePredictor"},{"title":"anandharaju/Basic_TCN","url":"https://github.com/anandharaju/Basic_TCN"},{"title":"ucsd-dsc-arts/dsc160-final-dsc160-final-group19","url":"https://github.com/ucsd-dsc-arts/dsc160-final-dsc160-final-group19"},{"title":"Salazar-99/Gravitational-WaveNet","url":"https://github.com/Salazar-99/Gravitational-WaveNet"},{"title":"sriharireddypusapati/speech-to-text-wavenet2","url":"https://github.com/sriharireddypusapati/speech-to-text-wavenet2"},{"title":"benmoseley/simple-wavenet","url":"https://github.com/benmoseley/simple-wavenet"},{"title":"pascalbakker/WaveNet-Implementation","url":"https://github.com/pascalbakker/WaveNet-Implementation"},{"title":"ZTianle/keras-tcn-solar","url":"https://github.com/ZTianle/keras-tcn-solar"},{"title":"Gal1eo/DT2119","url":"https://github.com/Gal1eo/DT2119"},{"title":"zhong110020/Tensorflow-TCN","url":"https://github.com/zhong110020/Tensorflow-TCN"},{"title":"adityaagrawal7/speech-to-text-wavenet","url":"https://github.com/adityaagrawal7/speech-to-text-wavenet"},{"title":"Vikas-Sony/speech-to-text","url":"https://github.com/Vikas-Sony/speech-to-text"},{"title":"outofculture/talk-like-me","url":"https://github.com/outofculture/talk-like-me"},{"title":"vicky-hnk/time-flex","url":"https://github.com/vicky-hnk/time-flex"},{"title":"HsiehKang/wavenet","url":"https://github.com/HsiehKang/wavenet/blob/main/wavenet.ipynb"},{"title":"2023-MindSpore-1/ms-code-15","url":"https://github.com/2023-MindSpore-1/ms-code-15/tree/main/wavenet"},{"title":"RamsteinWR/wavenet-master","url":"https://github.com/RamsteinWR/wavenet-master"},{"title":"freedombenLiu/speech-to-text-wavenet","url":"https://github.com/freedombenLiu/speech-to-text-wavenet"},{"title":"liguigui/speech-to-text-wavenet","url":"https://github.com/liguigui/speech-to-text-wavenet"},{"title":"glakshay/Generating-audio-DL","url":"https://github.com/glakshay/Generating-audio-DL"},{"title":"Shivendra-psc/speechbot","url":"https://github.com/Shivendra-psc/speechbot"},{"title":"pbrandl/aNN_Audio","url":"https://github.com/pbrandl/aNN_Audio"},{"title":"zll1996/TCN","url":"https://github.com/zll1996/TCN"}],"syntology":{"n":103,"n_ran":65,"n_constructed":23,"n_ran_checked":52,"n_instrument":13,"n_unverified":38,"n_honours":2,"n_violates":1,"n_no_contract":49,"n_pointer_only":25,"phrase":"65 ran (of which 23 constructed an object rather than computing a result; 52 with no instrument failure: 2 honoured, 1 violated, 49 with no contract checked; 13 where Syntology's instrument failed) · 38 unverified","sample_list":"/paper/wavenet-a-generative-model-for-raw-audio#ran","syntology_url":"https://syntology.ai/paper/1609.03499","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1609.03499"}},"official":null}}},{"leaderboard":"/sota/speech-synthesis-on-blizzard-challenge-2013","slug":"speech-synthesis-on-blizzard-challenge-2013","dataset":"Blizzard Challenge 2013","dataset_url":"/dataset/blizzard-challenge-2013","rows_in_archive":2,"metrics":["NLL"],"first_row_in_archive_order":{"model":"SampleRNN (3-tier)","paper_title":"SampleRNN: An Unconditional End-to-End Neural Audio Generation Model","paper_url":"/paper/samplernn-an-unconditional-end-to-end-neural","paper_date":"2016-12-22","arxiv_id":"1612.07837","code_links":[{"title":"soroushmehr/sampleRNN_ICLR2017","url":"https://github.com/soroushmehr/sampleRNN_ICLR2017"},{"title":"deepsound-project/samplernn-pytorch","url":"https://github.com/deepsound-project/samplernn-pytorch"},{"title":"dada-bots/dadabots_sampleRNN","url":"https://github.com/dada-bots/dadabots_sampleRNN"},{"title":"cchinchristopherj/Concert-of-Whales","url":"https://github.com/cchinchristopherj/Concert-of-Whales"}],"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/samplernn-an-unconditional-end-to-end-neural#ran","syntology_url":"https://syntology.ai/paper/1612.07837","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.07837"}},"official":{"repos":["soroushmehr/sampleRNN_ICLR2017"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}}}],"datasets":[{"url":"/dataset/ljspeech","name":"LJSpeech","full_name":"The LJ Speech Dataset","num_papers_in_archive":323},{"url":"/dataset/libritts","name":"LibriTTS","full_name":"LibriTTS","num_papers_in_archive":257},{"url":"/dataset/thchs-30","name":"THCHS-30","full_name":"","num_papers_in_archive":34},{"url":"/dataset/css10","name":"CSS10","full_name":"","num_papers_in_archive":22},{"url":"/dataset/promptspeech","name":"PromptSpeech","full_name":"","num_papers_in_archive":14},{"url":"/dataset/somos","name":"SOMOS","full_name":"The Samsung Open MOS Dataset for the Evaluation of Neural Text-to-Speech Synthesis","num_papers_in_archive":11},{"url":"/dataset/jsut-corpus","name":"JSUT Corpus","full_name":"","num_papers_in_archive":8},{"url":"/dataset/gumar-corpus","name":"Gumar Corpus","full_name":"","num_papers_in_archive":7},{"url":"/dataset/blizzard-challenge-2013","name":"Blizzard Challenge 2013","full_name":"Blizzard Challenge 2013 - English language tasks","num_papers_in_archive":5},{"url":"/dataset/hui","name":"HUI speech corpus","full_name":"Hof University iisys speech dataset","num_papers_in_archive":3},{"url":"/dataset/tal-corpus","name":"TaL Corpus","full_name":"The Tongue and Lips Corpus","num_papers_in_archive":3},{"url":"/dataset/jit-dataset","name":"JIT Dataset","full_name":"Jejueo Interview Transcripts","num_papers_in_archive":2},{"url":"/dataset/jvs-music","name":"JVS-MuSiC","full_name":"","num_papers_in_archive":2},{"url":"/dataset/ruslan","name":"RUSLAN","full_name":"","num_papers_in_archive":2},{"url":"/dataset/tilde-model-corpus","name":"Tilde MODEL Corpus","full_name":"Tilde Multilingual Open Data for European Languages","num_papers_in_archive":2},{"url":"/dataset/tts-portuguese-corpus","name":"TTS-Portuguese Corpus","full_name":"","num_papers_in_archive":2},{"url":"/dataset/vocbench","name":"VocBench","full_name":"","num_papers_in_archive":2},{"url":"/dataset/gneutralspeech-male","name":"GneutralSpeech Male","full_name":"","num_papers_in_archive":1},{"url":"/dataset/jss-dataset","name":"JSS Dataset","full_name":"Jejueo Single Speaker Speech","num_papers_in_archive":1},{"url":"/dataset/silent-speech-emg","name":"Silent Speech EMG","full_name":"","num_papers_in_archive":1},{"url":"/dataset/ttsds-synthetic-speech","name":"TTSDS Synthetic Speech","full_name":"","num_papers_in_archive":1},{"url":"/dataset/united-syn-med","name":"United-Syn-Med","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/emotional-speech-synthesis","name":"Emotional Speech Synthesis"},{"url":"/task/expressive-speech-synthesis","name":"Expressive Speech Synthesis"},{"url":"/task/speech-synthesis-assamese","name":"Speech Synthesis - Assamese"},{"url":"/task/speech-synthesis-bengali","name":"Speech Synthesis - Bengali"},{"url":"/task/speech-synthesis-bodo","name":"Speech Synthesis - Bodo"},{"url":"/task/speech-synthesis-gujarati","name":"Speech Synthesis - Gujarati"},{"url":"/task/speech-synthesis-hindi","name":"Speech Synthesis - Hindi"},{"url":"/task/speech-synthesis-kannada","name":"Speech Synthesis - Kannada"},{"url":"/task/speech-synthesis-malayalam","name":"Speech Synthesis - Malayalam"},{"url":"/task/speech-synthesis-manipuri","name":"Speech Synthesis - Manipuri"},{"url":"/task/speech-synthesis-marathi","name":"Speech Synthesis - Marathi"},{"url":"/task/speech-synthesis-rajasthani","name":"Speech Synthesis - Rajasthani"},{"url":"/task/speech-synthesis-tamil","name":"Speech Synthesis - Tamil"},{"url":"/task/speech-synthesis-telugu","name":"Speech Synthesis - Telugu"},{"url":"/task/text-to-speech-translation","name":"text-to-speech translation"}],"parent_tasks":[{"url":"/task/accented-speech-recognition","name":"Accented Speech Recognition"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":13,"rows_per_page":100,"shown":100,"of":1249,"of_with_code":366,"tagged_in_all":1249,"counts":{"archive_papers_tagged":1249,"with_a_code_link":366,"where_syntology_ran_a_sample":101,"not_listed_spam_title":0,"listed":1249,"listed_where_code_ran":101,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":84,"every_run_a_failure_of_syntologys_instrument":17,"listed_with_a_run_with_no_instrument_failure":84,"listed_every_run_a_failure_of_syntologys_instrument":17,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/wavenet-a-generative-model-for-raw-audio","slug":"wavenet-a-generative-model-for-raw-audio","title":"WaveNet: A Generative Model for Raw Audio","date":"2016-09-12","arxiv_id":"1609.03499","repositories_listed":62,"syntology":{"n":103,"n_ran":65,"n_constructed":23,"n_ran_checked":52,"n_instrument":13,"n_unverified":38,"n_honours":2,"n_violates":1,"n_no_contract":49,"n_pointer_only":25,"phrase":"65 ran (of which 23 constructed an object rather than computing a result; 52 with no instrument failure: 2 honoured, 1 violated, 49 with no contract checked; 13 where Syntology's instrument failed) · 38 unverified","sample_list":"/paper/wavenet-a-generative-model-for-raw-audio#ran","syntology_url":"https://syntology.ai/paper/1609.03499","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1609.03499"}},"official":null}},{"url":"/paper/fastspeech-2-fast-and-high-quality-end-to-end","slug":"fastspeech-2-fast-and-high-quality-end-to-end","title":"FastSpeech 2: Fast and High-Quality End-to-End Text to Speech","date":"2020-06-08","arxiv_id":"2006.04558","repositories_listed":37,"syntology":{"n":119,"n_ran":83,"n_constructed":27,"n_ran_checked":70,"n_instrument":13,"n_unverified":36,"n_honours":9,"n_violates":1,"n_no_contract":60,"n_pointer_only":40,"phrase":"83 ran (of which 27 constructed an object rather than computing a result; 70 with no instrument failure: 9 honoured, 1 violated, 60 with no contract checked; 13 where Syntology's instrument failed) · 36 unverified","sample_list":"/paper/fastspeech-2-fast-and-high-quality-end-to-end#ran","syntology_url":"https://syntology.ai/paper/2006.04558","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.04558"}},"official":null}},{"url":"/paper/natural-tts-synthesis-by-conditioning-wavenet","slug":"natural-tts-synthesis-by-conditioning-wavenet","title":"Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions","date":"2017-12-16","arxiv_id":"1712.05884","repositories_listed":33,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/natural-tts-synthesis-by-conditioning-wavenet#ran","syntology_url":"https://syntology.ai/paper/1712.05884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1712.05884"}},"official":null}},{"url":"/paper/tacotron-towards-end-to-end-speech-synthesis","slug":"tacotron-towards-end-to-end-speech-synthesis","title":"Tacotron: Towards End-to-End Speech Synthesis","date":"2017-03-29","arxiv_id":"1703.10135","repositories_listed":30,"syntology":{"n":25,"n_ran":16,"n_constructed":0,"n_ran_checked":13,"n_instrument":3,"n_unverified":9,"n_honours":3,"n_violates":1,"n_no_contract":9,"n_pointer_only":6,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 3 honoured, 1 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/tacotron-towards-end-to-end-speech-synthesis#ran","syntology_url":"https://syntology.ai/paper/1703.10135","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.10135"}},"official":null}},{"url":"/paper/fastspeech-fast-robust-and-controllable-text","slug":"fastspeech-fast-robust-and-controllable-text","title":"FastSpeech: Fast, Robust and Controllable Text to Speech","date":"2019-05-22","arxiv_id":"1905.09263","repositories_listed":22,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/fastspeech-fast-robust-and-controllable-text#ran","syntology_url":"https://syntology.ai/paper/1905.09263","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.09263"}},"official":null}},{"url":"/paper/melgan-generative-adversarial-networks-for","slug":"melgan-generative-adversarial-networks-for","title":"MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis","date":"2019-10-08","arxiv_id":"1910.06711","repositories_listed":21,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/melgan-generative-adversarial-networks-for#ran","syntology_url":"https://syntology.ai/paper/1910.06711","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.06711"}},"official":{"repos":["descriptinc/melgan-neurips"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/efficient-neural-audio-synthesis","slug":"efficient-neural-audio-synthesis","title":"Efficient Neural Audio Synthesis","date":"2018-02-23","arxiv_id":"1802.08435","repositories_listed":16,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/efficient-neural-audio-synthesis#ran","syntology_url":"https://syntology.ai/paper/1802.08435","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.08435"}},"official":null}},{"url":"/paper/parallel-wavegan-a-fast-waveform-generation","slug":"parallel-wavegan-a-fast-waveform-generation","title":"Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram","date":"2019-10-25","arxiv_id":"1910.11480","repositories_listed":12,"syntology":{"n":20,"n_ran":17,"n_constructed":0,"n_ran_checked":17,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":17,"n_pointer_only":1,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/parallel-wavegan-a-fast-waveform-generation#ran","syntology_url":"https://syntology.ai/paper/1910.11480","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.11480"}},"official":null}},{"url":"/paper/hifi-gan-generative-adversarial-networks-for","slug":"hifi-gan-generative-adversarial-networks-for","title":"HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","date":"2020-10-12","arxiv_id":"2010.05646","repositories_listed":11,"syntology":{"n":25,"n_ran":17,"n_constructed":11,"n_ran_checked":14,"n_instrument":3,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":3,"phrase":"17 ran (of which 11 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/hifi-gan-generative-adversarial-networks-for#ran","syntology_url":"https://syntology.ai/paper/2010.05646","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.05646"}},"official":{"repos":["jik876/hifi-gan"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/diffwave-a-versatile-diffusion-model-for","slug":"diffwave-a-versatile-diffusion-model-for","title":"DiffWave: A Versatile Diffusion Model for Audio Synthesis","date":"2020-09-21","arxiv_id":"2009.09761","repositories_listed":11,"syntology":{"n":33,"n_ran":20,"n_constructed":11,"n_ran_checked":13,"n_instrument":7,"n_unverified":13,"n_honours":1,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"20 ran (of which 11 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 7 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/diffwave-a-versatile-diffusion-model-for#ran","syntology_url":"https://syntology.ai/paper/2009.09761","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.09761"}},"official":null}},{"url":"/paper/transfer-learning-from-speaker-verification","slug":"transfer-learning-from-speaker-verification","title":"Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis","date":"2018-06-12","arxiv_id":"1806.04558","repositories_listed":11,"syntology":null},{"url":"/paper/style-tokens-unsupervised-style-modeling","slug":"style-tokens-unsupervised-style-modeling","title":"Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis","date":"2018-03-23","arxiv_id":"1803.09017","repositories_listed":11,"syntology":{"n":21,"n_ran":19,"n_constructed":0,"n_ran_checked":13,"n_instrument":6,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":9,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/style-tokens-unsupervised-style-modeling#ran","syntology_url":"https://syntology.ai/paper/1803.09017","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.09017"}},"official":null}},{"url":"/paper/univnet-a-neural-vocoder-with-multi","slug":"univnet-a-neural-vocoder-with-multi","title":"UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation","date":"2021-06-15","arxiv_id":"2106.07889","repositories_listed":9,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":5,"n_instrument":6,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":7,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/univnet-a-neural-vocoder-with-multi#ran","syntology_url":"https://syntology.ai/paper/2106.07889","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.07889"}},"official":null}},{"url":"/paper/neural-codec-language-models-are-zero-shot","slug":"neural-codec-language-models-are-zero-shot","title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","date":"2023-01-05","arxiv_id":"2301.02111","repositories_listed":7,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/neural-codec-language-models-are-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2301.02111","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.02111"}},"official":{"repos":["microsoft/unilm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/wavegrad-estimating-gradients-for-waveform","slug":"wavegrad-estimating-gradients-for-waveform","title":"WaveGrad: Estimating Gradients for Waveform Generation","date":"2020-09-02","arxiv_id":"2009.00713","repositories_listed":7,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/wavegrad-estimating-gradients-for-waveform#ran","syntology_url":"https://syntology.ai/paper/2009.00713","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.00713"}},"official":null}},{"url":"/paper/deep-voice-3-scaling-text-to-speech-with","slug":"deep-voice-3-scaling-text-to-speech-with","title":"Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning","date":"2017-10-20","arxiv_id":"1710.07654","repositories_listed":7,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/deep-voice-3-scaling-text-to-speech-with#ran","syntology_url":"https://syntology.ai/paper/1710.07654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.07654"}},"official":null}},{"url":"/paper/speecht5-unified-modal-encoder-decoder-pre","slug":"speecht5-unified-modal-encoder-decoder-pre","title":"SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing","date":"2021-10-14","arxiv_id":"2110.07205","repositories_listed":6,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/speecht5-unified-modal-encoder-decoder-pre#ran","syntology_url":"https://syntology.ai/paper/2110.07205","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.07205"}},"official":{"repos":["microsoft/speecht5"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/grad-tts-a-diffusion-probabilistic-model-for","slug":"grad-tts-a-diffusion-probabilistic-model-for","title":"Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech","date":"2021-05-13","arxiv_id":"2105.06337","repositories_listed":6,"syntology":{"n":18,"n_ran":15,"n_constructed":0,"n_ran_checked":9,"n_instrument":6,"n_unverified":3,"n_honours":1,"n_violates":2,"n_no_contract":6,"n_pointer_only":3,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 2 violated, 6 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/grad-tts-a-diffusion-probabilistic-model-for#ran","syntology_url":"https://syntology.ai/paper/2105.06337","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.06337"}},"official":{"repos":["huawei-noah/Speech-Backbones"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/durian-duration-informed-attention-network","slug":"durian-duration-informed-attention-network","title":"DurIAN: Duration Informed Attention Network For Multimodal Synthesis","date":"2019-09-04","arxiv_id":"1909.01700","repositories_listed":6,"syntology":null},{"url":"/paper/neural-speech-synthesis-with-transformer","slug":"neural-speech-synthesis-with-transformer","title":"Neural Speech Synthesis with Transformer Network","date":"2018-09-19","arxiv_id":"1809.08895","repositories_listed":6,"syntology":null},{"url":"/paper/neural-autoregressive-flows","slug":"neural-autoregressive-flows","title":"Neural Autoregressive Flows","date":"2018-04-03","arxiv_id":"1804.00779","repositories_listed":6,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/neural-autoregressive-flows#ran","syntology_url":"https://syntology.ai/paper/1804.00779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.00779"}},"official":{"repos":["CW-Huang/NAF"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/bigvgan-a-universal-neural-vocoder-with-large","slug":"bigvgan-a-universal-neural-vocoder-with-large","title":"BigVGAN: A Universal Neural Vocoder with Large-Scale Training","date":"2022-06-09","arxiv_id":"2206.04658","repositories_listed":5,"syntology":{"n":17,"n_ran":15,"n_constructed":2,"n_ran_checked":12,"n_instrument":3,"n_unverified":2,"n_honours":3,"n_violates":0,"n_no_contract":9,"n_pointer_only":9,"phrase":"15 ran (of which 2 constructed an object rather than computing a result; 12 with no instrument failure: 3 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/bigvgan-a-universal-neural-vocoder-with-large#ran","syntology_url":"https://syntology.ai/paper/2206.04658","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.04658"}},"official":{"repos":["nvidia/bigvgan"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community","listed"]}}},{"url":"/paper/melnet-a-generative-model-for-audio-in-the","slug":"melnet-a-generative-model-for-audio-in-the","title":"MelNet: A Generative Model for Audio in the Frequency Domain","date":"2019-06-04","arxiv_id":"1906.01083","repositories_listed":5,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/melnet-a-generative-model-for-audio-in-the#ran","syntology_url":"https://syntology.ai/paper/1906.01083","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.01083"}},"official":null}},{"url":"/paper/exploring-transfer-learning-for-low-resource","slug":"exploring-transfer-learning-for-low-resource","title":"Exploring Transfer Learning for Low Resource Emotional TTS","date":"2019-01-14","arxiv_id":"1901.04276","repositories_listed":5,"syntology":null},{"url":"/paper/clarinet-parallel-wave-generation-in-end-to","slug":"clarinet-parallel-wave-generation-in-end-to","title":"ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech","date":"2018-07-19","arxiv_id":"1807.07281","repositories_listed":5,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/clarinet-parallel-wave-generation-in-end-to#ran","syntology_url":"https://syntology.ai/paper/1807.07281","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.07281"}},"official":null}},{"url":"/paper/statistical-parametric-speech-synthesis-1","slug":"statistical-parametric-speech-synthesis-1","title":"Statistical Parametric Speech Synthesis Incorporating Generative Adversarial Networks","date":"2017-09-23","arxiv_id":"1709.08041","repositories_listed":5,"syntology":null},{"url":"/paper/speech-slytherin-examining-the-performance","slug":"speech-slytherin-examining-the-performance","title":"Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech Separation, Recognition, and Synthesis","date":"2024-07-13","arxiv_id":"2407.09732","repositories_listed":4,"syntology":null},{"url":"/paper/vocos-closing-the-gap-between-time-domain-and","slug":"vocos-closing-the-gap-between-time-domain-and","title":"Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis","date":"2023-06-01","arxiv_id":"2306.00814","repositories_listed":4,"syntology":{"n":16,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/vocos-closing-the-gap-between-time-domain-and#ran","syntology_url":"https://syntology.ai/paper/2306.00814","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00814"}},"official":{"repos":["gemelo-ai/vocos"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/scaling-speech-technology-to-1000-languages-1","slug":"scaling-speech-technology-to-1000-languages-1","title":"Scaling Speech Technology to 1,000+ Languages","date":"2023-05-22","arxiv_id":"2305.13516","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/scaling-speech-technology-to-1000-languages-1#ran","syntology_url":"https://syntology.ai/paper/2305.13516","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13516"}},"official":{"repos":["facebookresearch/fairseq","pytorch/fairseq"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/prodiff-progressive-fast-diffusion-model-for","slug":"prodiff-progressive-fast-diffusion-model-for","title":"ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speech","date":"2022-07-13","arxiv_id":"2207.06389","repositories_listed":4,"syntology":{"n":6,"n_ran":6,"n_constructed":3,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/prodiff-progressive-fast-diffusion-model-for#ran","syntology_url":"https://syntology.ai/paper/2207.06389","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.06389"}},"official":{"repos":["Rongjiehuang/ProDiff"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/diffusion-based-voice-conversion-with-fast","slug":"diffusion-based-voice-conversion-with-fast","title":"Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme","date":"2021-09-28","arxiv_id":"2109.13821","repositories_listed":4,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/diffusion-based-voice-conversion-with-fast#ran","syntology_url":"https://syntology.ai/paper/2109.13821","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.13821"}},"official":{"repos":["huawei-noah/Speech-Backbones"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/fairseq-s-2-a-scalable-and-integrable-speech","slug":"fairseq-s-2-a-scalable-and-integrable-speech","title":"fairseq S^2: A Scalable and Integrable Speech Synthesis Toolkit","date":"2021-09-14","arxiv_id":"2109.06912","repositories_listed":4,"syntology":null},{"url":"/paper/waveflow-a-compact-flow-based-model-for-raw-1","slug":"waveflow-a-compact-flow-based-model-for-raw-1","title":"WaveFlow: A Compact Flow-based Model for Raw Audio","date":"2019-12-03","arxiv_id":"1912.01219","repositories_listed":4,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/waveflow-a-compact-flow-based-model-for-raw-1#ran","syntology_url":"https://syntology.ai/paper/1912.01219","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.01219"}},"official":{"repos":["PaddlePaddle/Parakeet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/location-relative-attention-mechanisms-for","slug":"location-relative-attention-mechanisms-for","title":"Location-Relative Attention Mechanisms For Robust Long-Form Speech Synthesis","date":"2019-10-23","arxiv_id":"1910.10288","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/location-relative-attention-mechanisms-for#ran","syntology_url":"https://syntology.ai/paper/1910.10288","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.10288"}},"official":null}},{"url":"/paper/learning-to-speak-fluently-in-a-foreign","slug":"learning-to-speak-fluently-in-a-foreign","title":"Learning to Speak Fluently in a Foreign Language: Multilingual Speech Synthesis and Cross-Language Voice Cloning","date":"2019-07-09","arxiv_id":"1907.04448","repositories_listed":4,"syntology":{"n":9,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/learning-to-speak-fluently-in-a-foreign#ran","syntology_url":"https://syntology.ai/paper/1907.04448","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.04448"}},"official":null}},{"url":"/paper/tools-and-resources-for-romanian-text-to","slug":"tools-and-resources-for-romanian-text-to","title":"Tools and resources for Romanian text-to-speech and speech-to-text applications","date":"2018-02-15","arxiv_id":"1802.05583","repositories_listed":4,"syntology":null},{"url":"/paper/samplernn-an-unconditional-end-to-end-neural","slug":"samplernn-an-unconditional-end-to-end-neural","title":"SampleRNN: An Unconditional End-to-End Neural Audio Generation Model","date":"2016-12-22","arxiv_id":"1612.07837","repositories_listed":4,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/samplernn-an-unconditional-end-to-end-neural#ran","syntology_url":"https://syntology.ai/paper/1612.07837","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.07837"}},"official":{"repos":["soroushmehr/sampleRNN_ICLR2017"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/bigvsan-enhancing-gan-based-neural-vocoders-1","slug":"bigvsan-enhancing-gan-based-neural-vocoders-1","title":"BigVSAN: Enhancing GAN-based Neural Vocoders with Slicing Adversarial Network","date":"2023-09-06","arxiv_id":"2309.02836","repositories_listed":3,"syntology":null},{"url":"/paper/enhancing-suno-s-bark-text-to-speech-model","slug":"enhancing-suno-s-bark-text-to-speech-model","title":"Enhancing Suno's Bark Text-to-Speech Model: Addressing Limitations Through Meta's Encodec and Pre-Trained Hubert","date":"2023-04-18","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/lip-to-speech-synthesis-in-the-wild-with","slug":"lip-to-speech-synthesis-in-the-wild-with","title":"Lip-to-Speech Synthesis in the Wild with Multi-task Learning","date":"2023-02-17","arxiv_id":"2302.08841","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lip-to-speech-synthesis-in-the-wild-with#ran","syntology_url":"https://syntology.ai/paper/2302.08841","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.08841"}},"official":{"repos":["ms-dot-k/Lip-to-Speech-Synthesis-in-the-Wild"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/preparing-an-endangered-language-for-the","slug":"preparing-an-endangered-language-for-the","title":"Preparing an Endangered Language for the Digital Age: The Case of Judeo-Spanish","date":"2022-05-31","arxiv_id":"2205.15599","repositories_listed":3,"syntology":null},{"url":"/paper/naturalspeech-end-to-end-text-to-speech","slug":"naturalspeech-end-to-end-text-to-speech","title":"NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality","date":"2022-05-09","arxiv_id":"2205.04421","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/naturalspeech-end-to-end-text-to-speech#ran","syntology_url":"https://syntology.ai/paper/2205.04421","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.04421"}},"official":{"repos":["microsoft/NeuralSpeech"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/yourtts-towards-zero-shot-multi-speaker-tts","slug":"yourtts-towards-zero-shot-multi-speaker-tts","title":"YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone","date":"2021-12-04","arxiv_id":"2112.02418","repositories_listed":3,"syntology":null},{"url":"/paper/one-tts-alignment-to-rule-them-all","slug":"one-tts-alignment-to-rule-them-all","title":"One TTS Alignment To Rule Them All","date":"2021-08-23","arxiv_id":"2108.10447","repositories_listed":3,"syntology":null},{"url":"/paper/wavegrad-2-iterative-refinement-for-text-to","slug":"wavegrad-2-iterative-refinement-for-text-to","title":"WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis","date":"2021-06-17","arxiv_id":"2106.09660","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/wavegrad-2-iterative-refinement-for-text-to#ran","syntology_url":"https://syntology.ai/paper/2106.09660","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09660"}},"official":null}},{"url":"/paper/ryanspeech-a-corpus-for-conversational-text","slug":"ryanspeech-a-corpus-for-conversational-text","title":"RyanSpeech: A Corpus for Conversational Text-to-Speech Synthesis","date":"2021-06-15","arxiv_id":"2106.08468","repositories_listed":3,"syntology":null},{"url":"/paper/speedyspeech-efficient-neural-speech","slug":"speedyspeech-efficient-neural-speech","title":"SpeedySpeech: Efficient Neural Speech Synthesis","date":"2020-08-09","arxiv_id":"2008.03802","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/speedyspeech-efficient-neural-speech#ran","syntology_url":"https://syntology.ai/paper/2008.03802","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.03802"}},"official":{"repos":["janvainer/speedyspeech"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/flowtron-an-autoregressive-flow-based","slug":"flowtron-an-autoregressive-flow-based","title":"Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis","date":"2020-05-12","arxiv_id":"2005.05957","repositories_listed":3,"syntology":{"n":19,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":8,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/flowtron-an-autoregressive-flow-based#ran","syntology_url":"https://syntology.ai/paper/2005.05957","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.05957"}},"official":{"repos":["NVIDIA/flowtron"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":8,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/using-speech-synthesis-to-train-end-to-end","slug":"using-speech-synthesis-to-train-end-to-end","title":"Using Speech Synthesis to Train End-to-End Spoken Language Understanding Models","date":"2019-10-21","arxiv_id":"1910.09463","repositories_listed":3,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/using-speech-synthesis-to-train-end-to-end#ran","syntology_url":"https://syntology.ai/paper/1910.09463","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.09463"}},"official":{"repos":["lorenlugosch/end-to-end-SLU"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/high-fidelity-speech-synthesis-with-1","slug":"high-fidelity-speech-synthesis-with-1","title":"High Fidelity Speech Synthesis with Adversarial Networks","date":"2019-09-25","arxiv_id":"1909.11646","repositories_listed":3,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/high-fidelity-speech-synthesis-with-1#ran","syntology_url":"https://syntology.ai/paper/1909.11646","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11646"}},"official":{"repos":["mbinkowski/DeepSpeechDistances"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/mixed-precision-training-for-nlp-and-speech","slug":"mixed-precision-training-for-nlp-and-speech","title":"Mixed-Precision Training for NLP and Speech Recognition with OpenSeq2Seq","date":"2018-05-25","arxiv_id":"1805.10387","repositories_listed":3,"syntology":null},{"url":"/paper/towards-end-to-end-prosody-transfer-for","slug":"towards-end-to-end-prosody-transfer-for","title":"Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron","date":"2018-03-24","arxiv_id":"1803.09047","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-end-to-end-prosody-transfer-for#ran","syntology_url":"https://syntology.ai/paper/1803.09047","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.09047"}},"official":null}},{"url":"/paper/deep-voice-real-time-neural-text-to-speech","slug":"deep-voice-real-time-neural-text-to-speech","title":"Deep Voice: Real-time Neural Text-to-Speech","date":"2017-02-25","arxiv_id":"1702.07825","repositories_listed":3,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/deep-voice-real-time-neural-text-to-speech#ran","syntology_url":"https://syntology.ai/paper/1702.07825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1702.07825"}},"official":null}},{"url":"/paper/a-critical-review-of-recurrent-neural","slug":"a-critical-review-of-recurrent-neural","title":"A Critical Review of Recurrent Neural Networks for Sequence Learning","date":"2015-05-29","arxiv_id":"1506.00019","repositories_listed":3,"syntology":null},{"url":"/paper/cosyvoice-3-towards-in-the-wild-speech","slug":"cosyvoice-3-towards-in-the-wild-speech","title":"CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training","date":"2025-05-23","arxiv_id":"2505.17589","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/cosyvoice-3-towards-in-the-wild-speech#ran","syntology_url":"https://syntology.ai/paper/2505.17589","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.17589"}},"official":{"repos":["funaudiollm/cosyvoice"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/llama-omni2-llm-based-real-time-spoken","slug":"llama-omni2-llm-based-real-time-spoken","title":"LLaMA-Omni2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis","date":"2025-05-05","arxiv_id":"2505.02625","repositories_listed":2,"syntology":{"n":11,"n_ran":9,"n_constructed":3,"n_ran_checked":4,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":10,"phrase":"9 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/llama-omni2-llm-based-real-time-spoken#ran","syntology_url":"https://syntology.ai/paper/2505.02625","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.02625"}},"official":{"repos":["ictnlp/llama-omni2"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text","listed"]}}},{"url":"/paper/wavlm-model-ensemble-for-audio-deepfake","slug":"wavlm-model-ensemble-for-audio-deepfake","title":"WavLM model ensemble for audio deepfake detection","date":"2024-08-14","arxiv_id":"2408.07414","repositories_listed":2,"syntology":null},{"url":"/paper/very-low-complexity-speech-synthesis-using","slug":"very-low-complexity-speech-synthesis-using","title":"Very Low Complexity Speech Synthesis Using Framewise Autoregressive GAN (FARGAN) with Pitch Prediction","date":"2024-05-31","arxiv_id":"2405.21069","repositories_listed":2,"syntology":null},{"url":"/paper/hierspeech-bridging-the-gap-between-semantic","slug":"hierspeech-bridging-the-gap-between-semantic","title":"HierSpeech++: Bridging the Gap between Semantic and Acoustic Representation of Speech by Hierarchical Variational Inference for Zero-shot Speech Synthesis","date":"2023-11-21","arxiv_id":"2311.12454","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/hierspeech-bridging-the-gap-between-semantic#ran","syntology_url":"https://syntology.ai/paper/2311.12454","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.12454"}},"official":{"repos":["sh-lee-prml/hierspeechpp"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/lauragpt-listen-attend-understand-and","slug":"lauragpt-listen-attend-understand-and","title":"LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT","date":"2023-10-07","arxiv_id":"2310.04673","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lauragpt-listen-attend-understand-and#ran","syntology_url":"https://syntology.ai/paper/2310.04673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04673"}},"official":null}},{"url":"/paper/diffv2s-diffusion-based-video-to-speech","slug":"diffv2s-diffusion-based-video-to-speech","title":"DiffV2S: Diffusion-based Video-to-Speech Synthesis with Vision-guided Speaker Embedding","date":"2023-08-15","arxiv_id":"2308.07787","repositories_listed":2,"syntology":null},{"url":"/paper/intelligible-lip-to-speech-synthesis-with","slug":"intelligible-lip-to-speech-synthesis-with","title":"Intelligible Lip-to-Speech Synthesis with Speech Units","date":"2023-05-31","arxiv_id":"2305.19603","repositories_listed":2,"syntology":null},{"url":"/paper/naturalspeech-2-latent-diffusion-models-are","slug":"naturalspeech-2-latent-diffusion-models-are","title":"NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers","date":"2023-04-18","arxiv_id":"2304.09116","repositories_listed":2,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":5,"n_no_contract":5,"n_pointer_only":2,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 5 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/naturalspeech-2-latent-diffusion-models-are#ran","syntology_url":"https://syntology.ai/paper/2304.09116","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.09116"}},"official":null}},{"url":"/paper/towards-building-text-to-speech-systems-for","slug":"towards-building-text-to-speech-systems-for","title":"Towards Building Text-To-Speech Systems for the Next Billion Users","date":"2022-11-17","arxiv_id":"2211.09536","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-building-text-to-speech-systems-for#ran","syntology_url":"https://syntology.ai/paper/2211.09536","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09536"}},"official":{"repos":["gokulkarthik/text2speech"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/overflow-putting-flows-on-top-of-neural","slug":"overflow-putting-flows-on-top-of-neural","title":"OverFlow: Putting flows on top of neural transducers for better TTS","date":"2022-11-13","arxiv_id":"2211.06892","repositories_listed":2,"syntology":null},{"url":"/paper/phaseaug-a-differentiable-augmentation-for","slug":"phaseaug-a-differentiable-augmentation-for","title":"PhaseAug: A Differentiable Augmentation for Speech Synthesis to Simulate One-to-Many Mapping","date":"2022-11-08","arxiv_id":"2211.04610","repositories_listed":2,"syntology":null},{"url":"/paper/ernie-sat-speech-and-text-joint-pretraining-1","slug":"ernie-sat-speech-and-text-joint-pretraining-1","title":"ERNIE-SAT: Speech and Text Joint Pretraining for Cross-Lingual Multi-Speaker Text-to-Speech","date":"2022-11-07","arxiv_id":"2211.03545","repositories_listed":2,"syntology":null},{"url":"/paper/samo-speaker-attractor-multi-center-one-class","slug":"samo-speaker-attractor-multi-center-one-class","title":"SAMO: Speaker Attractor Multi-Center One-Class Learning for Voice Anti-Spoofing","date":"2022-11-04","arxiv_id":"2211.02718","repositories_listed":2,"syntology":null},{"url":"/paper/convnext-based-neural-network-for-anti","slug":"convnext-based-neural-network-for-anti","title":"ConvNeXt Based Neural Network for Audio Anti-Spoofing","date":"2022-09-14","arxiv_id":"2209.06434","repositories_listed":2,"syntology":null},{"url":"/paper/rf-next-efficient-receptive-field-search-for","slug":"rf-next-efficient-receptive-field-search-for","title":"RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks","date":"2022-06-14","arxiv_id":"2206.06637","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/rf-next-efficient-receptive-field-search-for#ran","syntology_url":"https://syntology.ai/paper/2206.06637","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.06637"}},"official":{"repos":["ShangHua-Gao/RFNext"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/paddlespeech-an-easy-to-use-all-in-one-speech-1","slug":"paddlespeech-an-easy-to-use-all-in-one-speech-1","title":"PaddleSpeech: An Easy-to-Use All-in-One Speech Toolkit","date":"2022-05-20","arxiv_id":"2205.12007","repositories_listed":2,"syntology":null},{"url":"/paper/generspeech-towards-style-transfer-for","slug":"generspeech-towards-style-transfer-for","title":"GenerSpeech: Towards Style Transfer for Generalizable Out-Of-Domain Text-to-Speech","date":"2022-05-15","arxiv_id":"2205.07211","repositories_listed":2,"syntology":{"n":9,"n_ran":8,"n_constructed":3,"n_ran_checked":7,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"8 ran (of which 3 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/generspeech-towards-style-transfer-for#ran","syntology_url":"https://syntology.ai/paper/2205.07211","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.07211"}},"official":{"repos":["Rongjiehuang/GenerSpeech"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":3,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/svts-scalable-video-to-speech-synthesis","slug":"svts-scalable-video-to-speech-synthesis","title":"SVTS: Scalable Video-to-Speech Synthesis","date":"2022-05-04","arxiv_id":"2205.02058","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/svts-scalable-video-to-speech-synthesis#ran","syntology_url":"https://syntology.ai/paper/2205.02058","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.02058"}},"official":null}},{"url":"/paper/fastdiff-a-fast-conditional-diffusion-model","slug":"fastdiff-a-fast-conditional-diffusion-model","title":"FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis","date":"2022-04-21","arxiv_id":"2204.09934","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/fastdiff-a-fast-conditional-diffusion-model#ran","syntology_url":"https://syntology.ai/paper/2204.09934","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.09934"}},"official":{"repos":["Rongjiehuang/FastDiff"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/a-3-t-alignment-aware-acoustic-and-text","slug":"a-3-t-alignment-aware-acoustic-and-text","title":"A$^3$T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing","date":"2022-03-18","arxiv_id":"2203.09690","repositories_listed":2,"syntology":{"n":7,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/a-3-t-alignment-aware-acoustic-and-text#ran","syntology_url":"https://syntology.ai/paper/2203.09690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.09690"}},"official":null}},{"url":"/paper/istftnet-fast-and-lightweight-mel-spectrogram","slug":"istftnet-fast-and-lightweight-mel-spectrogram","title":"iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform","date":"2022-03-04","arxiv_id":"2203.02395","repositories_listed":2,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":5,"n_instrument":6,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/istftnet-fast-and-lightweight-mel-spectrogram#ran","syntology_url":"https://syntology.ai/paper/2203.02395","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.02395"}},"official":null}},{"url":"/paper/neural-speech-synthesis-on-a-shoestring","slug":"neural-speech-synthesis-on-a-shoestring","title":"Neural Speech Synthesis on a Shoestring: Improving the Efficiency of LPCNet","date":"2022-02-22","arxiv_id":"2202.11169","repositories_listed":2,"syntology":null},{"url":"/paper/conditional-diffusion-probabilistic-model-for","slug":"conditional-diffusion-probabilistic-model-for","title":"Conditional Diffusion Probabilistic Model for Speech Enhancement","date":"2022-02-10","arxiv_id":"2202.05256","repositories_listed":2,"syntology":null},{"url":"/paper/diffgan-tts-high-fidelity-and-efficient-text","slug":"diffgan-tts-high-fidelity-and-efficient-text","title":"DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANs","date":"2022-01-28","arxiv_id":"2201.11972","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":2,"n_ran_checked":4,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":2,"n_no_contract":1,"n_pointer_only":2,"phrase":"6 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/diffgan-tts-high-fidelity-and-efficient-text#ran","syntology_url":"https://syntology.ai/paper/2201.11972","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.11972"}},"official":null}},{"url":"/paper/delightfultts-the-microsoft-speech-synthesis","slug":"delightfultts-the-microsoft-speech-synthesis","title":"DelightfulTTS: The Microsoft Speech Synthesis System for Blizzard Challenge 2021","date":"2021-10-25","arxiv_id":"2110.12612","repositories_listed":2,"syntology":null},{"url":"/paper/caloflow-ii-even-faster-and-still-accurate","slug":"caloflow-ii-even-faster-and-still-accurate","title":"CaloFlow II: Even Faster and Still Accurate Generation of Calorimeter Showers with Normalizing Flows","date":"2021-10-21","arxiv_id":"2110.11377","repositories_listed":2,"syntology":null},{"url":"/paper/systematic-inequalities-in-language","slug":"systematic-inequalities-in-language","title":"Systematic Inequalities in Language Technology Performance across the World's Languages","date":"2021-10-13","arxiv_id":"2110.06733","repositories_listed":2,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/systematic-inequalities-in-language#ran","syntology_url":"https://syntology.ai/paper/2110.06733","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.06733"}},"official":{"repos":["neubig/globalutility"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/neural-hmms-are-all-you-need-for-high-quality","slug":"neural-hmms-are-all-you-need-for-high-quality","title":"Neural HMMs are all you need (for high-quality attention-free TTS)","date":"2021-08-30","arxiv_id":"2108.13320","repositories_listed":2,"syntology":null},{"url":"/paper/spoken-style-learning-with-multi-modal","slug":"spoken-style-learning-with-multi-modal","title":"Enhancing Speaking Styles in Conversational Text-to-Speech Synthesis with Graph-based Multi-modal Context Modeling","date":"2021-06-11","arxiv_id":"2106.06233","repositories_listed":2,"syntology":null},{"url":"/paper/multilingual-byte2speech-text-to-speech","slug":"multilingual-byte2speech-text-to-speech","title":"Multilingual Byte2Speech Models for Scalable Low-resource Speech Synthesis","date":"2021-03-05","arxiv_id":"2103.03541","repositories_listed":2,"syntology":null},{"url":"/paper/efficientnet-absolute-zero-for-continuous","slug":"efficientnet-absolute-zero-for-continuous","title":"EfficientNet-Absolute Zero for Continuous Speech Keyword Spotting","date":"2020-12-31","arxiv_id":"2012.15695","repositories_listed":2,"syntology":null},{"url":"/paper/a-spectral-energy-distance-for-parallel","slug":"a-spectral-energy-distance-for-parallel","title":"A Spectral Energy Distance for Parallel Speech Synthesis","date":"2020-08-03","arxiv_id":"2008.01160","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-spectral-energy-distance-for-parallel#ran","syntology_url":"https://syntology.ai/paper/2008.01160","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.01160"}},"official":{"repos":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/vocgan-a-high-fidelity-real-time-vocoder-with","slug":"vocgan-a-high-fidelity-real-time-vocoder-with","title":"VocGAN: A High-Fidelity Real-time Vocoder with a Hierarchically-nested Adversarial Network","date":"2020-07-30","arxiv_id":"2007.15256","repositories_listed":2,"syntology":null},{"url":"/paper/end-to-end-adversarial-text-to-speech","slug":"end-to-end-adversarial-text-to-speech","title":"End-to-End Adversarial Text-to-Speech","date":"2020-06-05","arxiv_id":"2006.03575","repositories_listed":2,"syntology":{"n":12,"n_ran":10,"n_constructed":7,"n_ran_checked":10,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":12,"phrase":"10 ran (of which 7 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/end-to-end-adversarial-text-to-speech#ran","syntology_url":"https://syntology.ai/paper/2006.03575","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.03575"}},"official":null}},{"url":"/paper/comparison-of-speech-representations-for","slug":"comparison-of-speech-representations-for","title":"Comparison of Speech Representations for Automatic Quality Estimation in Multi-Speaker Text-to-Speech Synthesis","date":"2020-02-28","arxiv_id":"2002.12645","repositories_listed":2,"syntology":null},{"url":"/paper/maximizing-mutual-information-for-tacotron","slug":"maximizing-mutual-information-for-tacotron","title":"Maximizing Mutual Information for Tacotron","date":"2019-08-30","arxiv_id":"1909.01145","repositories_listed":2,"syntology":null},{"url":"/paper/rawnet-fast-end-to-end-neural-vocoder","slug":"rawnet-fast-end-to-end-neural-vocoder","title":"RawNet: Fast End-to-End Neural Vocoder","date":"2019-04-10","arxiv_id":"1904.05351","repositories_listed":2,"syntology":null},{"url":"/paper/a-real-time-wideband-neural-vocoder-at-16-kbs","slug":"a-real-time-wideband-neural-vocoder-at-16-kbs","title":"A Real-Time Wideband Neural Vocoder at 1.6 kb/s Using LPCNet","date":"2019-03-28","arxiv_id":"1903.12087","repositories_listed":2,"syntology":{"n":14,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/a-real-time-wideband-neural-vocoder-at-16-kbs#ran","syntology_url":"https://syntology.ai/paper/1903.12087","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.12087"}},"official":{"repos":["mozilla/LPCNet"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":9,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-latent-representations-for-style","slug":"learning-latent-representations-for-style","title":"Learning latent representations for style control and transfer in end-to-end speech synthesis","date":"2018-12-11","arxiv_id":"1812.04342","repositories_listed":2,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":7,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/learning-latent-representations-for-style#ran","syntology_url":"https://syntology.ai/paper/1812.04342","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.04342"}},"official":null}},{"url":"/paper/learning-pronunciation-from-a-foreign","slug":"learning-pronunciation-from-a-foreign","title":"Learning pronunciation from a foreign language in speech synthesis networks","date":"2018-11-23","arxiv_id":"1811.09364","repositories_listed":2,"syntology":null},{"url":"/paper/waveglow-a-flow-based-generative-network-for","slug":"waveglow-a-flow-based-generative-network-for","title":"WaveGlow: A Flow-based Generative Network for Speech Synthesis","date":"2018-10-31","arxiv_id":"1811.00002","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/waveglow-a-flow-based-generative-network-for#ran","syntology_url":"https://syntology.ai/paper/1811.00002","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.00002"}},"official":null}},{"url":"/paper/lpcnet-improving-neural-speech-synthesis","slug":"lpcnet-improving-neural-speech-synthesis","title":"LPCNet: Improving Neural Speech Synthesis Through Linear Prediction","date":"2018-10-28","arxiv_id":"1810.11846","repositories_listed":2,"syntology":null},{"url":"/paper/hierarchical-generative-modeling-for","slug":"hierarchical-generative-modeling-for","title":"Hierarchical Generative Modeling for Controllable Speech Synthesis","date":"2018-10-16","arxiv_id":"1810.07217","repositories_listed":2,"syntology":null},{"url":"/paper/neural-voice-cloning-with-a-few-samples","slug":"neural-voice-cloning-with-a-few-samples","title":"Neural Voice Cloning with a Few Samples","date":"2018-02-14","arxiv_id":"1802.06006","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/neural-voice-cloning-with-a-few-samples#ran","syntology_url":"https://syntology.ai/paper/1802.06006","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.06006"}},"official":null}},{"url":"/paper/epoch-synchronous-overlap-add-esola-for-time","slug":"epoch-synchronous-overlap-add-esola-for-time","title":"Epoch-Synchronous Overlap-Add (ESOLA) for Time- and Pitch-Scale Modification of Speech Signals","date":"2018-01-19","arxiv_id":"1801.06492","repositories_listed":2,"syntology":null}],"syntology_records":58,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":2,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/speech-synthesis-on-libritts","since_archive":"/sota/speech-synthesis-on-libritts#since-judged","papers_judged":2,"placed":0}]},"papers_where_code_ran":101,"papers_where_code_ran_first_page":"/task/speech-synthesis/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":13,"url":"/task/speech-synthesis/papers/2","json":"/task/speech-synthesis/papers/2.json","rows":100},{"order":"archive","page":3,"of":13,"url":"/task/speech-synthesis/papers/3","json":"/task/speech-synthesis/papers/3.json","rows":100},{"order":"archive","page":4,"of":13,"url":"/task/speech-synthesis/papers/4","json":"/task/speech-synthesis/papers/4.json","rows":100},{"order":"archive","page":5,"of":13,"url":"/task/speech-synthesis/papers/5","json":"/task/speech-synthesis/papers/5.json","rows":100},{"order":"archive","page":6,"of":13,"url":"/task/speech-synthesis/papers/6","json":"/task/speech-synthesis/papers/6.json","rows":100},{"order":"archive","page":7,"of":13,"url":"/task/speech-synthesis/papers/7","json":"/task/speech-synthesis/papers/7.json","rows":100},{"order":"archive","page":8,"of":13,"url":"/task/speech-synthesis/papers/8","json":"/task/speech-synthesis/papers/8.json","rows":100},{"order":"archive","page":9,"of":13,"url":"/task/speech-synthesis/papers/9","json":"/task/speech-synthesis/papers/9.json","rows":100},{"order":"archive","page":10,"of":13,"url":"/task/speech-synthesis/papers/10","json":"/task/speech-synthesis/papers/10.json","rows":100},{"order":"archive","page":11,"of":13,"url":"/task/speech-synthesis/papers/11","json":"/task/speech-synthesis/papers/11.json","rows":100},{"order":"archive","page":12,"of":13,"url":"/task/speech-synthesis/papers/12","json":"/task/speech-synthesis/papers/12.json","rows":100},{"order":"archive","page":13,"of":13,"url":"/task/speech-synthesis/papers/13","json":"/task/speech-synthesis/papers/13.json","rows":49},{"order":"ran","page":1,"of":2,"url":"/task/speech-synthesis/papers/ran/1","json":"/task/speech-synthesis/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":2,"url":"/task/speech-synthesis/papers/ran/2","json":"/task/speech-synthesis/papers/ran/2.json","rows":1}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"790f0f48620541dd94023c26b40f768893b41bfa0f6c2af5a6df9b7900ff3330","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}