{"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/text-to-speech","name":"Text to Speech","slug":"text-to-speech","description_markdown":"import gTTS import os def text_to_speech_kurdish(text, output_file=\"output.mp3\"): # گۆڕینی نووسین بۆ دەنگ بە زمانی کوردی (هەڵبژاردنی زمانی \"ku\" بۆ کوردی) tts = gTTS(text=text, lang='ku', slow=False) tts.save(output_file) os.system(f\"start {output_file}\") # کردنەوەی فایلە دەنگییەکە (لە Windows) # نموونە: text_to_speech_kurdish(\"سڵاو، ئەمە دەنگی منە بە زمانی کوردی.\")","categories":[{"name":"Adversarial","url":"/area/adversarial"},{"name":"Audio","url":"/area/audio"},{"name":"Computer Code","url":"/area/computer-code"},{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Graphs","url":"/area/graphs"},{"name":"Knowledge Base","url":"/area/knowledge-base"},{"name":"Medical","url":"/area/medical"},{"name":"Miscellaneous","url":"/area/miscellaneous"},{"name":"Music","url":"/area/music"},{"name":"Playing Games","url":"/area/playing-games"},{"name":"Robots","url":"/area/robots"},{"name":"Speech","url":"/area/speech"},{"name":"Time Series","url":"/area/time-series"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":1419,"papers_with_code":399,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"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":3,"subtasks":0,"parent_tasks":2},"benchmarks":[{"leaderboard":"/sota/text-to-speech-on","slug":"text-to-speech-on","dataset":".","dataset_url":"/dataset/gun-detection-dataset","rows_in_archive":1,"metrics":["0-shot MRR"],"first_row_in_archive_order":{"model":"mio","paper_title":"StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models","paper_url":"/paper/styletts-2-towards-human-level-text-to-speech","paper_date":"2023-06-13","arxiv_id":"2306.07691","code_links":[{"title":"yl4579/StyleTTS2","url":"https://github.com/yl4579/StyleTTS2"}],"syntology":{"n":4,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 4 unverified","sample_list":"/paper/styletts-2-towards-human-level-text-to-speech#ran","syntology_url":"https://syntology.ai/paper/2306.07691","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.07691"}},"official":null}}},{"leaderboard":"/sota/text-to-speech-on-1","slug":"text-to-speech-on-1","dataset":"^(#$!@#$)(()))******","dataset_url":null,"rows_in_archive":1,"metrics":["0-shot MRR"],"first_row_in_archive_order":{"model":"Reply","paper_title":"Text + Sketch: Image Compression at Ultra Low Rates","paper_url":"/paper/text-sketch-image-compression-at-ultra-low","paper_date":"2023-07-04","arxiv_id":"2307.01944","code_links":[{"title":"leieric/text-sketch","url":"https://github.com/leieric/text-sketch"}],"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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) · 1 unverified","sample_list":"/paper/text-sketch-image-compression-at-ultra-low#ran","syntology_url":"https://syntology.ai/paper/2307.01944","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.01944"}},"official":{"repos":["leieric/text-sketch"],"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"]}}}}],"datasets":[{"url":"/dataset/gun-detection-dataset","name":"Gun Detection Dataset","full_name":"","num_papers_in_archive":9},{"url":"/dataset/openslr","name":"OpenSLR","full_name":"Open Speech and Language Resources","num_papers_in_archive":2},{"url":"/dataset/arvoice","name":"ArVoice","full_name":"ArVoice: A Multi-Speaker Dataset for Arabic Speech Synthesis","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/10-shot-image-generation","name":"10-shot image generation"},{"url":"/task/audio-visual-speech-recognition","name":"Audio-Visual 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":15,"rows_per_page":100,"shown":100,"of":1419,"of_with_code":399,"tagged_in_all":1419,"counts":{"archive_papers_tagged":1419,"with_a_code_link":399,"where_syntology_ran_a_sample":108,"not_listed_spam_title":0,"listed":1419,"listed_where_code_ran":108,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":94,"every_run_a_failure_of_syntologys_instrument":14,"listed_with_a_run_with_no_instrument_failure":94,"listed_every_run_a_failure_of_syntologys_instrument":14,"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/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/efficiently-trainable-text-to-speech-system","slug":"efficiently-trainable-text-to-speech-system","title":"Efficiently Trainable Text-to-Speech System Based on Deep Convolutional Networks with Guided Attention","date":"2017-10-24","arxiv_id":"1710.08969","repositories_listed":22,"syntology":{"n":28,"n_ran":16,"n_constructed":0,"n_ran_checked":15,"n_instrument":1,"n_unverified":12,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":1,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 1 where Syntology's instrument failed) · 12 unverified","sample_list":"/paper/efficiently-trainable-text-to-speech-system#ran","syntology_url":"https://syntology.ai/paper/1710.08969","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.08969"}},"official":null}},{"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/fastspeech-fastrobustand-controllable-text-to","slug":"fastspeech-fastrobustand-controllable-text-to","title":"FastSpeech: Fast,Robustand Controllable Text-to-Speech","date":"2019-05-22","arxiv_id":null,"repositories_listed":11,"syntology":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/diffsinger-diffusion-acoustic-model-for","slug":"diffsinger-diffusion-acoustic-model-for","title":"DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism","date":"2021-05-06","arxiv_id":"2105.02446","repositories_listed":10,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":3,"n_pointer_only":4,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/diffsinger-diffusion-acoustic-model-for#ran","syntology_url":"https://syntology.ai/paper/2105.02446","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.02446"}},"official":{"repos":["MoonInTheRiver/DiffSinger"],"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/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/robust-universal-neural-vocoding","slug":"robust-universal-neural-vocoding","title":"Robust universal neural vocoding","date":"2018-11-15","arxiv_id":"1811.06292","repositories_listed":8,"syntology":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/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/sequence-transduction-with-recurrent-neural","slug":"sequence-transduction-with-recurrent-neural","title":"Sequence Transduction with Recurrent Neural Networks","date":"2012-11-14","arxiv_id":"1211.3711","repositories_listed":7,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/sequence-transduction-with-recurrent-neural#ran","syntology_url":"https://syntology.ai/paper/1211.3711","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1211.3711"}},"official":null}},{"url":"/paper/soundstream-an-end-to-end-neural-audio-codec","slug":"soundstream-an-end-to-end-neural-audio-codec","title":"SoundStream: An End-to-End Neural Audio Codec","date":"2021-07-07","arxiv_id":"2107.03312","repositories_listed":6,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":3,"n_no_contract":0,"n_pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/soundstream-an-end-to-end-neural-audio-codec#ran","syntology_url":"https://syntology.ai/paper/2107.03312","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.03312"}},"official":null}},{"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/non-attentive-tacotron-robust-and-1","slug":"non-attentive-tacotron-robust-and-1","title":"Non-Attentive Tacotron: Robust and Controllable Neural TTS Synthesis Including Unsupervised Duration Modeling","date":"2020-10-08","arxiv_id":"2010.04301","repositories_listed":6,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/non-attentive-tacotron-robust-and-1#ran","syntology_url":"https://syntology.ai/paper/2010.04301","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.04301"}},"official":null}},{"url":"/paper/fastpitch-parallel-text-to-speech-with-pitch","slug":"fastpitch-parallel-text-to-speech-with-pitch","title":"FastPitch: Parallel Text-to-speech with Pitch Prediction","date":"2020-06-11","arxiv_id":"2006.06873","repositories_listed":6,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":1,"n_honours":3,"n_violates":0,"n_no_contract":4,"n_pointer_only":3,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/fastpitch-parallel-text-to-speech-with-pitch#ran","syntology_url":"https://syntology.ai/paper/2006.06873","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.06873"}},"official":{"repos":["NVIDIA/DeepLearningExamples"],"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","named_in_paper"]}}},{"url":"/paper/defense-for-black-box-attacks-on-anti","slug":"defense-for-black-box-attacks-on-anti","title":"Defense for Black-box Attacks on Anti-spoofing Models by Self-Supervised Learning","date":"2020-06-05","arxiv_id":"2006.03214","repositories_listed":6,"syntology":null},{"url":"/paper/glow-tts-a-generative-flow-for-text-to-speech","slug":"glow-tts-a-generative-flow-for-text-to-speech","title":"Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search","date":"2020-05-22","arxiv_id":"2005.11129","repositories_listed":6,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":10,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":2,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/glow-tts-a-generative-flow-for-text-to-speech#ran","syntology_url":"https://syntology.ai/paper/2005.11129","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.11129"}},"official":{"repos":["jaywalnut310/glow-tts"],"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/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/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/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/seamlessm4t-massively-multilingual-multimodal","slug":"seamlessm4t-massively-multilingual-multimodal","title":"SeamlessM4T: Massively Multilingual & Multimodal Machine Translation","date":"2023-08-22","arxiv_id":"2308.11596","repositories_listed":4,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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) · 0 unverified","sample_list":"/paper/seamlessm4t-massively-multilingual-multimodal#ran","syntology_url":"https://syntology.ai/paper/2308.11596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.11596"}},"official":{"repos":["facebookresearch/seamless_communication"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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/portaspeech-portable-and-high-quality","slug":"portaspeech-portable-and-high-quality","title":"PortaSpeech: Portable and High-Quality Generative Text-to-Speech","date":"2021-09-30","arxiv_id":"2109.15166","repositories_listed":4,"syntology":{"n":12,"n_ran":12,"n_constructed":1,"n_ran_checked":9,"n_instrument":3,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":6,"n_pointer_only":6,"phrase":"12 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/portaspeech-portable-and-high-quality#ran","syntology_url":"https://syntology.ai/paper/2109.15166","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.15166"}},"official":{"repos":["natspeech/natspeech"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}},{"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/lightspeech-lightweight-and-fast-text-to","slug":"lightspeech-lightweight-and-fast-text-to","title":"LightSpeech: Lightweight and Fast Text to Speech with Neural Architecture Search","date":"2021-02-08","arxiv_id":"2102.04040","repositories_listed":4,"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/lightspeech-lightweight-and-fast-text-to#ran","syntology_url":"https://syntology.ai/paper/2102.04040","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.04040"}},"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/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/audio-super-resolution-using-neural-networks","slug":"audio-super-resolution-using-neural-networks","title":"Audio Super Resolution using Neural Networks","date":"2017-08-02","arxiv_id":"1708.00853","repositories_listed":4,"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":3,"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/audio-super-resolution-using-neural-networks#ran","syntology_url":"https://syntology.ai/paper/1708.00853","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.00853"}},"official":null}},{"url":"/paper/moshi-a-speech-text-foundation-model-for-real","slug":"moshi-a-speech-text-foundation-model-for-real","title":"Moshi: a speech-text foundation model for real-time dialogue","date":"2024-09-17","arxiv_id":"2410.00037","repositories_listed":3,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"7 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/moshi-a-speech-text-foundation-model-for-real#ran","syntology_url":"https://syntology.ai/paper/2410.00037","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.00037"}},"official":{"repos":["kyutai-labs/moshi"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/natural-language-guidance-of-high-fidelity","slug":"natural-language-guidance-of-high-fidelity","title":"Natural language guidance of high-fidelity text-to-speech with synthetic annotations","date":"2024-02-02","arxiv_id":"2402.01912","repositories_listed":3,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"5 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/natural-language-guidance-of-high-fidelity#ran","syntology_url":"https://syntology.ai/paper/2402.01912","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01912"}},"official":null}},{"url":"/paper/speechtokenizer-unified-speech-tokenizer-for","slug":"speechtokenizer-unified-speech-tokenizer-for","title":"SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models","date":"2023-08-31","arxiv_id":"2308.16692","repositories_listed":3,"syntology":{"n":26,"n_ran":24,"n_constructed":0,"n_ran_checked":16,"n_instrument":8,"n_unverified":2,"n_honours":1,"n_violates":5,"n_no_contract":10,"n_pointer_only":10,"phrase":"24 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 5 violated, 10 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/speechtokenizer-unified-speech-tokenizer-for#ran","syntology_url":"https://syntology.ai/paper/2308.16692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.16692"}},"official":{"repos":["0nutation/uslm","zhangxinfd/speechtokenizer","0nutation/slmtokbench"],"state":"official (archive's flag): 21 ran","n_ran":21,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":2,"ran_from_kinds":["community","official","unlocated"]}}},{"url":"/paper/vits2-improving-quality-and-efficiency-of","slug":"vits2-improving-quality-and-efficiency-of","title":"VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design","date":"2023-07-31","arxiv_id":"2307.16430","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/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/editspeech-a-text-based-speech-editing-system","slug":"editspeech-a-text-based-speech-editing-system","title":"EditSpeech: A Text Based Speech Editing System Using Partial Inference and Bidirectional Fusion","date":"2021-07-04","arxiv_id":"2107.01554","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/sc-glowtts-an-efficient-zero-shot-multi","slug":"sc-glowtts-an-efficient-zero-shot-multi","title":"SC-GlowTTS: an Efficient Zero-Shot Multi-Speaker Text-To-Speech Model","date":"2021-04-02","arxiv_id":"2104.05557","repositories_listed":3,"syntology":null},{"url":"/paper/one-class-learning-towards-generalized-voice-1","slug":"one-class-learning-towards-generalized-voice-1","title":"One-class learning towards generalized voice spoofing detection","date":"2020-10-27","arxiv_id":"2010.13995","repositories_listed":3,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 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) · 0 unverified","sample_list":"/paper/one-class-learning-towards-generalized-voice-1#ran","syntology_url":"https://syntology.ai/paper/2010.13995","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.13995"}},"official":{"repos":["yzyouzhang/AIR-ASVspoof"],"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/the-sequence-to-sequence-baseline-for-the","slug":"the-sequence-to-sequence-baseline-for-the","title":"The Sequence-to-Sequence Baseline for the Voice Conversion Challenge 2020: Cascading ASR and TTS","date":"2020-10-06","arxiv_id":"2010.02434","repositories_listed":3,"syntology":null},{"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/espnet-tts-unified-reproducible-and","slug":"espnet-tts-unified-reproducible-and","title":"ESPnet-TTS: Unified, Reproducible, and Integratable Open Source End-to-End Text-to-Speech Toolkit","date":"2019-10-24","arxiv_id":"1910.10909","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/espnet-tts-unified-reproducible-and#ran","syntology_url":"https://syntology.ai/paper/1910.10909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.10909"}},"official":{"repos":["r9y9/wavenet_vocoder","espnet/espnet"],"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","unlocated"]}}},{"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/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/unitts-an-end-to-end-tts-system-without","slug":"unitts-an-end-to-end-tts-system-without","title":"UniTTS: An end-to-end TTS system without decoupling of acoustic and semantic information","date":"2025-05-23","arxiv_id":"2505.17426","repositories_listed":2,"syntology":null},{"url":"/paper/audio-deepfake-detection-with-self-supervised-1","slug":"audio-deepfake-detection-with-self-supervised-1","title":"Audio Deepfake Detection with Self-Supervised XLS-R and SLS Classifier","date":"2024-10-28","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/recent-advances-in-speech-language-models-a","slug":"recent-advances-in-speech-language-models-a","title":"Recent Advances in Speech Language Models: A Survey","date":"2024-10-01","arxiv_id":"2410.03751","repositories_listed":2,"syntology":null},{"url":"/paper/seed-tts-a-family-of-high-quality-versatile","slug":"seed-tts-a-family-of-high-quality-versatile","title":"Seed-TTS: A Family of High-Quality Versatile Speech Generation Models","date":"2024-06-04","arxiv_id":"2406.02430","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/audioldm-2-learning-holistic-audio-generation","slug":"audioldm-2-learning-holistic-audio-generation","title":"AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining","date":"2023-08-10","arxiv_id":"2308.05734","repositories_listed":2,"syntology":{"n":27,"n_ran":16,"n_constructed":0,"n_ran_checked":13,"n_instrument":3,"n_unverified":11,"n_honours":4,"n_violates":4,"n_no_contract":5,"n_pointer_only":19,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 4 honoured, 4 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/audioldm-2-learning-holistic-audio-generation#ran","syntology_url":"https://syntology.ai/paper/2308.05734","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.05734"}},"official":{"repos":["haoheliu/AudioLDM2"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/latent-optimal-paths-by-gumbel-propagation","slug":"latent-optimal-paths-by-gumbel-propagation","title":"Latent Optimal Paths by Gumbel Propagation for Variational Bayesian Dynamic Programming","date":"2023-06-05","arxiv_id":"2306.02568","repositories_listed":2,"syntology":null},{"url":"/paper/xphonebert-a-pre-trained-multilingual-model","slug":"xphonebert-a-pre-trained-multilingual-model","title":"XPhoneBERT: A Pre-trained Multilingual Model for Phoneme Representations for Text-to-Speech","date":"2023-05-31","arxiv_id":"2305.19709","repositories_listed":2,"syntology":{"n":18,"n_ran":14,"n_constructed":0,"n_ran_checked":12,"n_instrument":2,"n_unverified":4,"n_honours":2,"n_violates":0,"n_no_contract":10,"n_pointer_only":10,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/xphonebert-a-pre-trained-multilingual-model#ran","syntology_url":"https://syntology.ai/paper/2305.19709","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.19709"}},"official":{"repos":["vinairesearch/xphonebert"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}},{"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/an-investigation-of-speaker-independent","slug":"an-investigation-of-speaker-independent","title":"An investigation of phrase break prediction in an End-to-End TTS system","date":"2023-04-09","arxiv_id":"2304.04157","repositories_listed":2,"syntology":null},{"url":"/paper/pits-variational-pitch-inference-without","slug":"pits-variational-pitch-inference-without","title":"PITS: Variational Pitch Inference without Fundamental Frequency for End-to-End Pitch-controllable TTS","date":"2023-02-24","arxiv_id":"2302.12391","repositories_listed":2,"syntology":null},{"url":"/paper/unsupervised-data-selection-for-tts-using","slug":"unsupervised-data-selection-for-tts-using","title":"Unsupervised Data Selection for TTS: Using Arabic Broadcast News as a Case Study","date":"2023-01-22","arxiv_id":"2301.09099","repositories_listed":2,"syntology":null},{"url":"/paper/phoneme-level-bert-for-enhanced-prosody-of","slug":"phoneme-level-bert-for-enhanced-prosody-of","title":"Phoneme-Level BERT for Enhanced Prosody of Text-to-Speech with Grapheme Predictions","date":"2023-01-20","arxiv_id":"2301.08810","repositories_listed":2,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/phoneme-level-bert-for-enhanced-prosody-of#ran","syntology_url":"https://syntology.ai/paper/2301.08810","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.08810"}},"official":null}},{"url":"/paper/speechlmscore-evaluating-speech-generation","slug":"speechlmscore-evaluating-speech-generation","title":"SpeechLMScore: Evaluating speech generation using speech language model","date":"2022-12-08","arxiv_id":"2212.04559","repositories_listed":2,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/speechlmscore-evaluating-speech-generation#ran","syntology_url":"https://syntology.ai/paper/2212.04559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.04559"}},"official":{"repos":["espnet/espnet"],"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/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/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/prosody-cloning-in-zero-shot-multispeaker","slug":"prosody-cloning-in-zero-shot-multispeaker","title":"Exact Prosody Cloning in Zero-Shot Multispeaker Text-to-Speech","date":"2022-06-24","arxiv_id":"2206.12229","repositories_listed":2,"syntology":null},{"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/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/jets-jointly-training-fastspeech2-and-hifi","slug":"jets-jointly-training-fastspeech2-and-hifi","title":"JETS: Jointly Training FastSpeech2 and HiFi-GAN for End to End Text to Speech","date":"2022-03-31","arxiv_id":"2203.16852","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/jets-jointly-training-fastspeech2-and-hifi#ran","syntology_url":"https://syntology.ai/paper/2203.16852","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.16852"}},"official":{"repos":["imdanboy/jets"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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/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/espnet-slu-advancing-spoken-language","slug":"espnet-slu-advancing-spoken-language","title":"ESPnet-SLU: Advancing Spoken Language Understanding through ESPnet","date":"2021-11-29","arxiv_id":"2111.14706","repositories_listed":2,"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/espnet-slu-advancing-spoken-language#ran","syntology_url":"https://syntology.ai/paper/2111.14706","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.14706"}},"official":{"repos":["espnet/espnet"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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/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/ur-channel-robust-synthetic-speech-detection","slug":"ur-channel-robust-synthetic-speech-detection","title":"UR Channel-Robust Synthetic Speech Detection System for ASVspoof 2021","date":"2021-07-26","arxiv_id":"2107.12018","repositories_listed":2,"syntology":null},{"url":"/paper/starganv2-vc-a-diverse-unsupervised-non","slug":"starganv2-vc-a-diverse-unsupervised-non","title":"StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion","date":"2021-07-21","arxiv_id":"2107.10394","repositories_listed":2,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/starganv2-vc-a-diverse-unsupervised-non#ran","syntology_url":"https://syntology.ai/paper/2107.10394","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.10394"}},"official":{"repos":["yl4579/StarGANv2-VC"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"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/meta-stylespeech-multi-speaker-adaptive-text","slug":"meta-stylespeech-multi-speaker-adaptive-text","title":"Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation","date":"2021-06-06","arxiv_id":"2106.03153","repositories_listed":2,"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":2,"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/meta-stylespeech-multi-speaker-adaptive-text#ran","syntology_url":"https://syntology.ai/paper/2106.03153","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.03153"}},"official":{"repos":["KevinMIN95/StyleSpeech"],"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":["listed","official"]}}},{"url":"/paper/limited-data-emotional-voice-conversion","slug":"limited-data-emotional-voice-conversion","title":"Limited Data Emotional Voice Conversion Leveraging Text-to-Speech: Two-stage Sequence-to-Sequence Training","date":"2021-03-31","arxiv_id":"2103.16809","repositories_listed":2,"syntology":null},{"url":"/paper/adaspeech-adaptive-text-to-speech-for-custom-1","slug":"adaspeech-adaptive-text-to-speech-for-custom-1","title":"AdaSpeech: Adaptive Text to Speech for Custom Voice","date":"2021-03-01","arxiv_id":"2103.00993","repositories_listed":2,"syntology":{"n":14,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":14,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/adaspeech-adaptive-text-to-speech-for-custom-1#ran","syntology_url":"https://syntology.ai/paper/2103.00993","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.00993"}},"official":null}},{"url":"/paper/universal-melgan-a-robust-neural-vocoder-for","slug":"universal-melgan-a-robust-neural-vocoder-for","title":"Universal MelGAN: A Robust Neural Vocoder for High-Fidelity Waveform Generation in Multiple Domains","date":"2020-11-19","arxiv_id":"2011.09631","repositories_listed":2,"syntology":null},{"url":"/paper/stylemelgan-an-efficient-high-fidelity","slug":"stylemelgan-an-efficient-high-fidelity","title":"StyleMelGAN: An Efficient High-Fidelity Adversarial Vocoder with Temporal Adaptive Normalization","date":"2020-11-03","arxiv_id":"2011.01557","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/stylemelgan-an-efficient-high-fidelity#ran","syntology_url":"https://syntology.ai/paper/2011.01557","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.01557"}},"official":null}},{"url":"/paper/pretraining-techniques-for-sequence-to","slug":"pretraining-techniques-for-sequence-to","title":"Pretraining Techniques for Sequence-to-Sequence Voice Conversion","date":"2020-08-07","arxiv_id":"2008.03088","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/aligntts-efficient-feed-forward-text-to","slug":"aligntts-efficient-feed-forward-text-to","title":"AlignTTS: Efficient Feed-Forward Text-to-Speech System without Explicit Alignment","date":"2020-03-04","arxiv_id":"2003.01950","repositories_listed":2,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"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) · 3 unverified","sample_list":"/paper/aligntts-efficient-feed-forward-text-to#ran","syntology_url":"https://syntology.ai/paper/2003.01950","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.01950"}},"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/semi-supervised-neural-architecture-search","slug":"semi-supervised-neural-architecture-search","title":"Semi-Supervised Neural Architecture Search","date":"2020-02-24","arxiv_id":"2002.10389","repositories_listed":2,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/semi-supervised-neural-architecture-search#ran","syntology_url":"https://syntology.ai/paper/2002.10389","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.10389"}},"official":{"repos":["renqianluo/SemiNAS"],"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":["listed","official"]}}},{"url":"/paper/voice-transformer-network-sequence-to","slug":"voice-transformer-network-sequence-to","title":"Voice Transformer Network: Sequence-to-Sequence Voice Conversion Using Transformer with Text-to-Speech Pretraining","date":"2019-12-14","arxiv_id":"1912.06813","repositories_listed":2,"syntology":null},{"url":"/paper/a-comparative-study-on-transformer-vs-rnn-in","slug":"a-comparative-study-on-transformer-vs-rnn-in","title":"A Comparative Study on Transformer vs RNN in Speech Applications","date":"2019-09-13","arxiv_id":"1909.06317","repositories_listed":2,"syntology":null},{"url":"/paper/parallel-neural-text-to-speech","slug":"parallel-neural-text-to-speech","title":"Non-Autoregressive Neural Text-to-Speech","date":"2019-05-21","arxiv_id":"1905.08459","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"6 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/parallel-neural-text-to-speech#ran","syntology_url":"https://syntology.ai/paper/1905.08459","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.08459"}},"official":null}},{"url":"/paper/end-to-end-lyrics-alignment-for-polyphonic","slug":"end-to-end-lyrics-alignment-for-polyphonic","title":"End-to-end Lyrics Alignment for Polyphonic Music Using an Audio-to-Character Recognition Model","date":"2019-02-18","arxiv_id":"1902.06797","repositories_listed":2,"syntology":null},{"url":"/paper/fpuas-fully-parallel-ufans-based-end-to-end","slug":"fpuas-fully-parallel-ufans-based-end-to-end","title":"FPETS : Fully Parallel End-to-End Text-to-Speech System","date":"2018-12-12","arxiv_id":"1812.05710","repositories_listed":2,"syntology":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/voiceloop-voice-fitting-and-synthesis-via-a","slug":"voiceloop-voice-fitting-and-synthesis-via-a","title":"VoiceLoop: Voice Fitting and Synthesis via a Phonological Loop","date":"2017-07-20","arxiv_id":"1707.06588","repositories_listed":2,"syntology":null}],"syntology_records":59,"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":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"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":[]},"papers_where_code_ran":108,"papers_where_code_ran_first_page":"/task/text-to-speech/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":15,"url":"/task/text-to-speech/papers/2","json":"/task/text-to-speech/papers/2.json","rows":100},{"order":"archive","page":3,"of":15,"url":"/task/text-to-speech/papers/3","json":"/task/text-to-speech/papers/3.json","rows":100},{"order":"archive","page":4,"of":15,"url":"/task/text-to-speech/papers/4","json":"/task/text-to-speech/papers/4.json","rows":100},{"order":"archive","page":5,"of":15,"url":"/task/text-to-speech/papers/5","json":"/task/text-to-speech/papers/5.json","rows":100},{"order":"archive","page":6,"of":15,"url":"/task/text-to-speech/papers/6","json":"/task/text-to-speech/papers/6.json","rows":100},{"order":"archive","page":7,"of":15,"url":"/task/text-to-speech/papers/7","json":"/task/text-to-speech/papers/7.json","rows":100},{"order":"archive","page":8,"of":15,"url":"/task/text-to-speech/papers/8","json":"/task/text-to-speech/papers/8.json","rows":100},{"order":"archive","page":9,"of":15,"url":"/task/text-to-speech/papers/9","json":"/task/text-to-speech/papers/9.json","rows":100},{"order":"archive","page":10,"of":15,"url":"/task/text-to-speech/papers/10","json":"/task/text-to-speech/papers/10.json","rows":100},{"order":"archive","page":11,"of":15,"url":"/task/text-to-speech/papers/11","json":"/task/text-to-speech/papers/11.json","rows":100},{"order":"archive","page":12,"of":15,"url":"/task/text-to-speech/papers/12","json":"/task/text-to-speech/papers/12.json","rows":100},{"order":"archive","page":13,"of":15,"url":"/task/text-to-speech/papers/13","json":"/task/text-to-speech/papers/13.json","rows":100},{"order":"archive","page":14,"of":15,"url":"/task/text-to-speech/papers/14","json":"/task/text-to-speech/papers/14.json","rows":100},{"order":"archive","page":15,"of":15,"url":"/task/text-to-speech/papers/15","json":"/task/text-to-speech/papers/15.json","rows":19},{"order":"ran","page":1,"of":2,"url":"/task/text-to-speech/papers/ran/1","json":"/task/text-to-speech/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":2,"url":"/task/text-to-speech/papers/ran/2","json":"/task/text-to-speech/papers/ran/2.json","rows":8}],"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":"b1dc31d1f448bae66d58f6ac6a057f16af46282a482aa03b6755335a3da4e24f","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}