{"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-synthesis","name":"Text-To-Speech Synthesis","slug":"text-to-speech-synthesis","description_markdown":"**Text-To-Speech Synthesis** is a machine learning task that involves converting written text into spoken words. The goal is to generate synthetic speech that sounds natural and resembles human speech as closely as possible.","categories":[{"name":"Audio","url":"/area/audio"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"},{"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":332,"papers_with_code":104,"benchmarks":6,"benchmark_tables_in_archive":6,"benchmark_tables_shown":6,"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":18,"subtasks":2,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/text-to-speech-synthesis-on-ljspeech","slug":"text-to-speech-synthesis-on-ljspeech","dataset":"LJSpeech","dataset_url":"/dataset/ljspeech","rows_in_archive":16,"metrics":["Audio Quality MOS","Pleasantness MOS","Word Error Rate (WER)","MOS","WER (%)"],"first_row_in_archive_order":{"model":"NaturalSpeech","paper_title":"NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality","paper_url":"/paper/naturalspeech-end-to-end-text-to-speech","paper_date":"2022-05-09","arxiv_id":"2205.04421","code_links":[{"title":"microsoft/NeuralSpeech","url":"https://github.com/microsoft/NeuralSpeech"},{"title":"daniilrobnikov/vits2","url":"https://github.com/daniilrobnikov/vits2"},{"title":"heatz123/naturalspeech","url":"https://github.com/heatz123/naturalspeech"}],"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"]}}}},{"leaderboard":"/sota/text-to-speech-synthesis-on-20000-utterances","slug":"text-to-speech-synthesis-on-20000-utterances","dataset":"20000 utterances","dataset_url":"/dataset/20000-utterances","rows_in_archive":1,"metrics":["10-keyword Speech Commands dataset"],"first_row_in_archive_order":{"model":"Mia","paper_title":"MIA-Prognosis: A Deep Learning Framework to Predict Therapy Response","paper_url":"/paper/mia-prognosis-a-deep-learning-framework-to","paper_date":"2020-10-08","arxiv_id":"2010.04062","code_links":[{"title":"M3DV/SimTA","url":"https://github.com/M3DV/SimTA"}],"syntology":null}},{"leaderboard":"/sota/text-to-speech-synthesis-on-cmudict-07b","slug":"text-to-speech-synthesis-on-cmudict-07b","dataset":"CMUDict 0.7b","dataset_url":null,"rows_in_archive":1,"metrics":["Phoneme Error Rate","Word Error Rate (WER)"],"first_row_in_archive_order":{"model":"Token-Level Ensemble Distillation","paper_title":"Token-Level Ensemble Distillation for Grapheme-to-Phoneme Conversion","paper_url":"/paper/token-level-ensemble-distillation-for","paper_date":"2019-04-06","arxiv_id":"1904.03446","code_links":[],"syntology":null}},{"leaderboard":"/sota/text-to-speech-synthesis-on-hui","slug":"text-to-speech-synthesis-on-hui","dataset":"HUI speech corpus","dataset_url":"/dataset/hui","rows_in_archive":1,"metrics":["Mean Opinion Score"],"first_row_in_archive_order":{"model":"Tacotron 2","paper_title":"Neural Speech Synthesis in German","paper_url":"/paper/neural-speech-synthesis-in-german","paper_date":"2021-10-03","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/text-to-speech-synthesis-on-thorsten-voice-21","slug":"text-to-speech-synthesis-on-thorsten-voice-21","dataset":"Thorsten voice 21.02 neutral","dataset_url":"/dataset/thorsten-voice-21-02-neutral","rows_in_archive":1,"metrics":["Mean Opinion Score"],"first_row_in_archive_order":{"model":"Tacotron 2","paper_title":"Neural Speech Synthesis in German","paper_url":"/paper/neural-speech-synthesis-in-german","paper_date":"2021-10-03","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/text-to-speech-synthesis-on-trinity-speech","slug":"text-to-speech-synthesis-on-trinity-speech","dataset":"Trinity Speech-Gesture Dataset","dataset_url":"/dataset/https-trinityspeechgesture-scss-tcd-ie","rows_in_archive":1,"metrics":["MOS"],"first_row_in_archive_order":{"model":"Match-TTSG","paper_title":"Unified speech and gesture synthesis using flow matching","paper_url":"/paper/unified-speech-and-gesture-synthesis-using","paper_date":"2023-10-08","arxiv_id":"2310.05181","code_links":[],"syntology":null}}],"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/aishell-3","name":"AISHELL-3","full_name":"","num_papers_in_archive":38},{"url":"/dataset/cvss","name":"CVSS","full_name":"","num_papers_in_archive":26},{"url":"/dataset/20000-utterances","name":"20000 utterances","full_name":"20000 utterances","num_papers_in_archive":15},{"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/gumar-corpus","name":"Gumar Corpus","full_name":"","num_papers_in_archive":7},{"url":"/dataset/kazakhtts","name":"KazakhTTS","full_name":"","num_papers_in_archive":4},{"url":"/dataset/speechinstruct","name":"SpeechInstruct","full_name":"","num_papers_in_archive":4},{"url":"/dataset/emovie","name":"EMOVIE","full_name":"","num_papers_in_archive":3},{"url":"/dataset/hui","name":"HUI speech corpus","full_name":"Hof University iisys speech dataset","num_papers_in_archive":3},{"url":"/dataset/openslr","name":"OpenSLR","full_name":"Open Speech and Language Resources","num_papers_in_archive":2},{"url":"/dataset/ryanspeech","name":"RyanSpeech","full_name":"","num_papers_in_archive":2},{"url":"/dataset/https-trinityspeechgesture-scss-tcd-ie","name":"Trinity Speech-Gesture Dataset","full_name":"","num_papers_in_archive":2},{"url":"/dataset/gneutralspeech-female","name":"GneutralSpeech Female","full_name":"","num_papers_in_archive":1},{"url":"/dataset/gneutralspeech-male","name":"GneutralSpeech Male","full_name":"","num_papers_in_archive":1},{"url":"/dataset/imasc","name":"IMaSC","full_name":"ICFOSS Malayalam Speech Corpus","num_papers_in_archive":1},{"url":"/dataset/thorsten-voice-21-02-neutral","name":"Thorsten voice 21.02 neutral","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/prosody-prediction","name":"Prosody Prediction"},{"url":"/task/zero-shot-multi-speaker-tts","name":"Zero-Shot Multi-Speaker TTS"}],"parent_tasks":[],"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":4,"rows_per_page":100,"shown":100,"of":332,"of_with_code":104,"tagged_in_all":332,"counts":{"archive_papers_tagged":332,"with_a_code_link":104,"where_syntology_ran_a_sample":37,"not_listed_spam_title":0,"listed":332,"listed_where_code_ran":37,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":34,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":34,"listed_every_run_a_failure_of_syntologys_instrument":3,"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/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/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/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/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/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/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/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/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/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/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/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/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/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/back-transcription-as-a-method-for-evaluating","slug":"back-transcription-as-a-method-for-evaluating","title":"Back Transcription as a Method for Evaluating Robustness of Natural Language Understanding Models to Speech Recognition Errors","date":"2023-10-25","arxiv_id":"2310.16609","repositories_listed":2,"syntology":null},{"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/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/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/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/multi-singer-fast-multi-singer-singing-voice-1","slug":"multi-singer-fast-multi-singer-singing-voice-1","title":"Multi-Singer: Fast Multi-Singer Singing Voice Vocoder With A Large-Scale Corpus","date":"2021-12-20","arxiv_id":"2112.10358","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/multi-singer-fast-multi-singer-singing-voice-1#ran","syntology_url":"https://syntology.ai/paper/2112.10358","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.10358"}},"official":{"repos":["Rongjiehuang/Multi-Singer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"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/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/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/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/zipvoice-fast-and-high-quality-zero-shot-text","slug":"zipvoice-fast-and-high-quality-zero-shot-text","title":"ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching","date":"2025-06-16","arxiv_id":"2506.13053","repositories_listed":1,"syntology":null},{"url":"/paper/audio-jailbreak-an-open-comprehensive","slug":"audio-jailbreak-an-open-comprehensive","title":"Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models","date":"2025-05-21","arxiv_id":"2505.15406","repositories_listed":1,"syntology":null},{"url":"/paper/mooncast-high-quality-zero-shot-podcast","slug":"mooncast-high-quality-zero-shot-podcast","title":"MoonCast: High-Quality Zero-Shot Podcast Generation","date":"2025-03-18","arxiv_id":"2503.14345","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-latent-language-modeling-with-next","slug":"multimodal-latent-language-modeling-with-next","title":"Multimodal Latent Language Modeling with Next-Token Diffusion","date":"2024-12-11","arxiv_id":"2412.08635","repositories_listed":1,"syntology":null},{"url":"/paper/lina-speech-gated-linear-attention-is-a-fast","slug":"lina-speech-gated-linear-attention-is-a-fast","title":"Lina-Speech: Gated Linear Attention is a Fast and Parameter-Efficient Learner for text-to-speech synthesis","date":"2024-10-30","arxiv_id":"2410.23320","repositories_listed":1,"syntology":null},{"url":"/paper/ssr-speech-towards-stable-safe-and-robust","slug":"ssr-speech-towards-stable-safe-and-robust","title":"SSR-Speech: Towards Stable, Safe and Robust Zero-shot Text-based Speech Editing and Synthesis","date":"2024-09-11","arxiv_id":"2409.07556","repositories_listed":1,"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":0,"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/ssr-speech-towards-stable-safe-and-robust#ran","syntology_url":"https://syntology.ai/paper/2409.07556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.07556"}},"official":{"repos":["WangHelin1997/SSR-Speech"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sample-efficient-diffusion-for-text-to-speech","slug":"sample-efficient-diffusion-for-text-to-speech","title":"Sample-Efficient Diffusion for Text-To-Speech Synthesis","date":"2024-09-01","arxiv_id":"2409.03717","repositories_listed":1,"syntology":null},{"url":"/paper/emosphere-tts-emotional-style-and-intensity","slug":"emosphere-tts-emotional-style-and-intensity","title":"EmoSphere-TTS: Emotional Style and Intensity Modeling via Spherical Emotion Vector for Controllable Emotional Text-to-Speech","date":"2024-06-12","arxiv_id":"2406.07803","repositories_listed":1,"syntology":null},{"url":"/paper/meta-learning-text-to-speech-synthesis-in","slug":"meta-learning-text-to-speech-synthesis-in","title":"Meta Learning Text-to-Speech Synthesis in over 7000 Languages","date":"2024-06-10","arxiv_id":"2406.06403","repositories_listed":1,"syntology":null},{"url":"/paper/streamspeech-simultaneous-speech-to-speech","slug":"streamspeech-simultaneous-speech-to-speech","title":"StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning","date":"2024-06-05","arxiv_id":"2406.03049","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/streamspeech-simultaneous-speech-to-speech#ran","syntology_url":"https://syntology.ai/paper/2406.03049","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03049"}},"official":{"repos":["ictnlp/streamspeech"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mm-tts-a-unified-framework-for-multimodal","slug":"mm-tts-a-unified-framework-for-multimodal","title":"UMETTS: A Unified Framework for Emotional Text-to-Speech Synthesis with Multimodal Prompts","date":"2024-04-29","arxiv_id":"2404.18398","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mm-tts-a-unified-framework-for-multimodal#ran","syntology_url":"https://syntology.ai/paper/2404.18398","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.18398"}},"official":{"repos":["kttrcdl/umetts"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/kazemotts-a-dataset-for-kazakh-emotional-text","slug":"kazemotts-a-dataset-for-kazakh-emotional-text","title":"KazEmoTTS: A Dataset for Kazakh Emotional Text-to-Speech Synthesis","date":"2024-04-01","arxiv_id":"2404.01033","repositories_listed":1,"syntology":null},{"url":"/paper/cm-tts-enhancing-real-time-text-to-speech","slug":"cm-tts-enhancing-real-time-text-to-speech","title":"CM-TTS: Enhancing Real Time Text-to-Speech Synthesis Efficiency through Weighted Samplers and Consistency Models","date":"2024-03-31","arxiv_id":"2404.00569","repositories_listed":1,"syntology":null},{"url":"/paper/bayesian-parameter-efficient-fine-tuning-for","slug":"bayesian-parameter-efficient-fine-tuning-for","title":"Bayesian Parameter-Efficient Fine-Tuning for Overcoming Catastrophic Forgetting","date":"2024-02-19","arxiv_id":"2402.12220","repositories_listed":1,"syntology":null},{"url":"/paper/learning-arousal-valence-representation-from","slug":"learning-arousal-valence-representation-from","title":"Learning Arousal-Valence Representation from Categorical Emotion Labels of Speech","date":"2023-11-24","arxiv_id":"2311.14816","repositories_listed":1,"syntology":null},{"url":"/paper/improved-child-text-to-speech-synthesis","slug":"improved-child-text-to-speech-synthesis","title":"Improved Child Text-to-Speech Synthesis through Fastpitch-based Transfer Learning","date":"2023-11-07","arxiv_id":"2311.04313","repositories_listed":1,"syntology":null},{"url":"/paper/artst-arabic-text-and-speech-transformer","slug":"artst-arabic-text-and-speech-transformer","title":"ArTST: Arabic Text and Speech Transformer","date":"2023-10-25","arxiv_id":"2310.16621","repositories_listed":1,"syntology":null},{"url":"/paper/attentive-multi-layer-perceptron-for-non","slug":"attentive-multi-layer-perceptron-for-non","title":"Attentive Multi-Layer Perceptron for Non-autoregressive Generation","date":"2023-10-14","arxiv_id":"2310.09512","repositories_listed":1,"syntology":null},{"url":"/paper/generative-adversarial-training-for-text-to","slug":"generative-adversarial-training-for-text-to","title":"Generative Adversarial Training for Text-to-Speech Synthesis Based on Raw Phonetic Input and Explicit Prosody Modelling","date":"2023-10-14","arxiv_id":"2310.09636","repositories_listed":1,"syntology":null},{"url":"/paper/funcodec-a-fundamental-reproducible-and","slug":"funcodec-a-fundamental-reproducible-and","title":"FunCodec: A Fundamental, Reproducible and Integrable Open-source Toolkit for Neural Speech Codec","date":"2023-09-14","arxiv_id":"2309.07405","repositories_listed":1,"syntology":null},{"url":"/paper/matcha-tts-a-fast-tts-architecture-with","slug":"matcha-tts-a-fast-tts-architecture-with","title":"Matcha-TTS: A fast TTS architecture with conditional flow matching","date":"2023-09-06","arxiv_id":"2309.03199","repositories_listed":1,"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":0,"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/matcha-tts-a-fast-tts-architecture-with#ran","syntology_url":"https://syntology.ai/paper/2309.03199","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.03199"}},"official":{"repos":["shivammehta25/Matcha-TTS"],"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/qs-tts-towards-semi-supervised-text-to-speech","slug":"qs-tts-towards-semi-supervised-text-to-speech","title":"QS-TTS: Towards Semi-Supervised Text-to-Speech Synthesis via Vector-Quantized Self-Supervised Speech Representation Learning","date":"2023-08-31","arxiv_id":"2309.00126","repositories_listed":1,"syntology":null},{"url":"/paper/many-to-many-spoken-language-translation-via","slug":"many-to-many-spoken-language-translation-via","title":"Textless Unit-to-Unit training for Many-to-Many Multilingual Speech-to-Speech Translation","date":"2023-08-03","arxiv_id":"2308.01831","repositories_listed":1,"syntology":null},{"url":"/paper/voicebox-text-guided-multilingual-universal","slug":"voicebox-text-guided-multilingual-universal","title":"Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale","date":"2023-06-23","arxiv_id":"2306.15687","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":0,"n_honours":3,"n_violates":3,"n_no_contract":2,"n_pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 3 honoured, 3 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/voicebox-text-guided-multilingual-universal#ran","syntology_url":"https://syntology.ai/paper/2306.15687","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.15687"}},"official":null}},{"url":"/paper/multilingual-text-to-speech-synthesis-for","slug":"multilingual-text-to-speech-synthesis-for","title":"Multilingual Text-to-Speech Synthesis for Turkic Languages Using Transliteration","date":"2023-05-25","arxiv_id":"2305.15749","repositories_listed":1,"syntology":null},{"url":"/paper/speak-foreign-languages-with-your-own-voice","slug":"speak-foreign-languages-with-your-own-voice","title":"Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling","date":"2023-03-07","arxiv_id":"2303.03926","repositories_listed":1,"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":0,"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/speak-foreign-languages-with-your-own-voice#ran","syntology_url":"https://syntology.ai/paper/2303.03926","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.03926"}},"official":null}},{"url":"/paper/imaginary-voice-face-styled-diffusion-model","slug":"imaginary-voice-face-styled-diffusion-model","title":"Imaginary Voice: Face-styled Diffusion Model for Text-to-Speech","date":"2023-02-27","arxiv_id":"2302.13700","repositories_listed":1,"syntology":null},{"url":"/paper/a-vector-quantized-approach-for-text-to","slug":"a-vector-quantized-approach-for-text-to","title":"A Vector Quantized Approach for Text to Speech Synthesis on Real-World Spontaneous Speech","date":"2023-02-08","arxiv_id":"2302.04215","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"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 2 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; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/a-vector-quantized-approach-for-text-to#ran","syntology_url":"https://syntology.ai/paper/2302.04215","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.04215"}},"official":{"repos":["b04901014/mqtts"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/rwen-tts-relation-aware-word-encoding-network","slug":"rwen-tts-relation-aware-word-encoding-network","title":"RWEN-TTS: Relation-aware Word Encoding Network for Natural Text-to-Speech Synthesis","date":"2022-12-15","arxiv_id":"2212.07939","repositories_listed":1,"syntology":null},{"url":"/paper/mntts2-an-open-source-multi-speaker-mongolian","slug":"mntts2-an-open-source-multi-speaker-mongolian","title":"MnTTS2: An Open-Source Multi-Speaker Mongolian Text-to-Speech Synthesis Dataset","date":"2022-12-11","arxiv_id":"2301.00657","repositories_listed":1,"syntology":null},{"url":"/paper/accented-text-to-speech-synthesis-with-a","slug":"accented-text-to-speech-synthesis-with-a","title":"Accented Text-to-Speech Synthesis with a Conditional Variational Autoencoder","date":"2022-11-07","arxiv_id":"2211.03316","repositories_listed":1,"syntology":null},{"url":"/paper/mntts-an-open-source-mongolian-text-to-speech","slug":"mntts-an-open-source-mongolian-text-to-speech","title":"MnTTS: An Open-Source Mongolian Text-to-Speech Synthesis Dataset and Accompanied Baseline","date":"2022-09-22","arxiv_id":"2209.10848","repositories_listed":1,"syntology":null},{"url":"/paper/mlphon-a-multifunctional-grapheme-phoneme","slug":"mlphon-a-multifunctional-grapheme-phoneme","title":"Mlphon: A Multifunctional Grapheme-Phoneme Conversion Tool Using Finite State Transducers","date":"2022-09-05","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/automatic-prosody-annotation-with-pre-trained","slug":"automatic-prosody-annotation-with-pre-trained","title":"Automatic Prosody Annotation with Pre-Trained Text-Speech Model","date":"2022-06-16","arxiv_id":"2206.07956","repositories_listed":1,"syntology":null},{"url":"/paper/styletts-a-style-based-generative-model-for","slug":"styletts-a-style-based-generative-model-for","title":"StyleTTS: A Style-Based Generative Model for Natural and Diverse Text-to-Speech Synthesis","date":"2022-05-30","arxiv_id":"2205.15439","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":5,"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) · 1 unverified","sample_list":"/paper/styletts-a-style-based-generative-model-for#ran","syntology_url":"https://syntology.ai/paper/2205.15439","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.15439"}},"official":{"repos":["yl4579/StyleTTS"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/systematic-inequalities-in-language-1","slug":"systematic-inequalities-in-language-1","title":"Systematic Inequalities in Language Technology Performance across the World’s Languages","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-text-to-speech-synthesis-by","slug":"unsupervised-text-to-speech-synthesis-by","title":"Unsupervised Text-to-Speech Synthesis by Unsupervised Automatic Speech Recognition","date":"2022-03-29","arxiv_id":"2203.15796","repositories_listed":1,"syntology":null},{"url":"/paper/ecapa-tdnn-for-multi-speaker-text-to-speech","slug":"ecapa-tdnn-for-multi-speaker-text-to-speech","title":"ECAPA-TDNN for Multi-speaker Text-to-speech Synthesis","date":"2022-03-20","arxiv_id":"2203.10473","repositories_listed":1,"syntology":null},{"url":"/paper/generative-modeling-for-low-dimensional","slug":"generative-modeling-for-low-dimensional","title":"Generative Modeling for Low Dimensional Speech Attributes with Neural Spline Flows","date":"2022-03-03","arxiv_id":"2203.01786","repositories_listed":1,"syntology":null},{"url":"/paper/fine-grained-style-control-in-transformer","slug":"fine-grained-style-control-in-transformer","title":"Fine-grained style control in Transformer-based Text-to-speech Synthesis","date":"2021-10-12","arxiv_id":"2110.06306","repositories_listed":1,"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/fine-grained-style-control-in-transformer#ran","syntology_url":"https://syntology.ai/paper/2110.06306","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.06306"}},"official":{"repos":["b04901014/FG-transformer-TTS"],"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/towards-lifelong-learning-of-multilingual","slug":"towards-lifelong-learning-of-multilingual","title":"Towards Lifelong Learning of Multilingual Text-To-Speech Synthesis","date":"2021-10-09","arxiv_id":"2110.04482","repositories_listed":1,"syntology":null},{"url":"/paper/editts-score-based-editing-for-controllable","slug":"editts-score-based-editing-for-controllable","title":"EdiTTS: Score-based Editing for Controllable Text-to-Speech","date":"2021-10-06","arxiv_id":"2110.02584","repositories_listed":1,"syntology":null},{"url":"/paper/extending-text-to-speech-synthesis-with","slug":"extending-text-to-speech-synthesis-with","title":"Extending Text-to-Speech Synthesis with Articulatory Movement Prediction using Ultrasound Tongue Imaging","date":"2021-07-12","arxiv_id":"2107.05550","repositories_listed":1,"syntology":null},{"url":"/paper/speech-synthesis-from-text-and-ultrasound","slug":"speech-synthesis-from-text-and-ultrasound","title":"Speech Synthesis from Text and Ultrasound Tongue Image-based Articulatory Input","date":"2021-07-05","arxiv_id":"2107.02003","repositories_listed":1,"syntology":null},{"url":"/paper/priorgrad-improving-conditional-denoising","slug":"priorgrad-improving-conditional-denoising","title":"PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Prior","date":"2021-06-11","arxiv_id":"2106.06406","repositories_listed":1,"syntology":null},{"url":"/paper/rad-tts-parallel-flow-based-tts-with-robust","slug":"rad-tts-parallel-flow-based-tts-with-robust","title":"RAD-TTS: Parallel Flow-Based TTS with Robust Alignment Learning and Diverse Synthesis","date":"2021-06-02","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/phrase-break-prediction-with-bidirectional","slug":"phrase-break-prediction-with-bidirectional","title":"Phrase break prediction with bidirectional encoder representations in Japanese text-to-speech synthesis","date":"2021-04-26","arxiv_id":"2104.12395","repositories_listed":1,"syntology":null},{"url":"/paper/kazakhtts-an-open-source-kazakh-text-to","slug":"kazakhtts-an-open-source-kazakh-text-to","title":"KazakhTTS: An Open-Source Kazakh Text-to-Speech Synthesis Dataset","date":"2021-04-17","arxiv_id":"2104.08459","repositories_listed":1,"syntology":null},{"url":"/paper/semi-supervised-url-segmentation-with-1","slug":"semi-supervised-url-segmentation-with-1","title":"Semi-supervised URL Segmentation with Recurrent Neural Networks Pre-trained on Knowledge Graph Entities","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/wave-tacotron-spectrogram-free-end-to-end","slug":"wave-tacotron-spectrogram-free-end-to-end","title":"Wave-Tacotron: Spectrogram-free end-to-end text-to-speech synthesis","date":"2020-11-06","arxiv_id":"2011.03568","repositories_listed":1,"syntology":null},{"url":"/paper/semi-supervised-url-segmentation-with","slug":"semi-supervised-url-segmentation-with","title":"Semi-supervised URL Segmentation with Recurrent Neural NetworksPre-trained on Knowledge Graph Entities","date":"2020-11-05","arxiv_id":"2011.03138","repositories_listed":1,"syntology":null},{"url":"/paper/effective-deep-learning-models-for-automatic","slug":"effective-deep-learning-models-for-automatic","title":"Effective Deep Learning Models for Automatic Diacritization of Arabic Text","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/mia-prognosis-a-deep-learning-framework-to","slug":"mia-prognosis-a-deep-learning-framework-to","title":"MIA-Prognosis: A Deep Learning Framework to Predict Therapy Response","date":"2020-10-08","arxiv_id":"2010.04062","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-speech-intelligibility-in-text-to","slug":"enhancing-speech-intelligibility-in-text-to","title":"Enhancing Speech Intelligibility in Text-To-Speech Synthesis using Speaking Style Conversion","date":"2020-08-13","arxiv_id":"2008.05809","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"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) · 0 unverified","sample_list":"/paper/enhancing-speech-intelligibility-in-text-to#ran","syntology_url":"https://syntology.ai/paper/2008.05809","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.05809"}},"official":null}},{"url":"/paper/independent-and-automatic-evaluation-of","slug":"independent-and-automatic-evaluation-of","title":"Independent and automatic evaluation of acoustic-to-articulatory inversion models","date":"2019-11-15","arxiv_id":"1911.06573","repositories_listed":1,"syntology":null},{"url":"/paper/spoofing-speaker-verification-systems-with","slug":"spoofing-speaker-verification-systems-with","title":"Spoofing Speaker Verification Systems with Deep Multi-speaker Text-to-speech Synthesis","date":"2019-10-29","arxiv_id":"1910.13054","repositories_listed":1,"syntology":null},{"url":"/paper/effective-parameter-estimation-methods-for-an","slug":"effective-parameter-estimation-methods-for-an","title":"Effective parameter estimation methods for an ExcitNet model in generative text-to-speech systems","date":"2019-05-21","arxiv_id":"1905.08486","repositories_listed":1,"syntology":null},{"url":"/paper/direct-speech-to-speech-translation-with-a","slug":"direct-speech-to-speech-translation-with-a","title":"Direct speech-to-speech translation with a sequence-to-sequence model","date":"2019-04-12","arxiv_id":"1904.06037","repositories_listed":1,"syntology":null}],"syntology_records":37,"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":37,"papers_where_code_ran_first_page":"/task/text-to-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":4,"url":"/task/text-to-speech-synthesis/papers/2","json":"/task/text-to-speech-synthesis/papers/2.json","rows":100},{"order":"archive","page":3,"of":4,"url":"/task/text-to-speech-synthesis/papers/3","json":"/task/text-to-speech-synthesis/papers/3.json","rows":100},{"order":"archive","page":4,"of":4,"url":"/task/text-to-speech-synthesis/papers/4","json":"/task/text-to-speech-synthesis/papers/4.json","rows":32},{"order":"ran","page":1,"of":1,"url":"/task/text-to-speech-synthesis/papers/ran/1","json":"/task/text-to-speech-synthesis/papers/ran/1.json","rows":37}],"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":"42070f5e9e9bb92b940792864104640f09a4ffe00a4f25e1d193e29521a9edb8","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}