{"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":"/dataset/ljspeech","name":"LJSpeech","full_name":"The LJ Speech Dataset","description_markdown":"This is a public domain speech dataset consisting of 13,100 short audio clips of a single speaker reading passages from 7 non-fiction books. A transcription is provided for each clip. Clips vary in length from 1 to 10 seconds and have a total length of approximately 24 hours. The texts were published between 1884 and 1964, and are in the public domain. The audio was recorded in 2016-17 by the LibriVox project and is also in the public domain.\r\n\r\nSource: [The LJ Speech Dataset](https://keithito.com/LJ-Speech-Dataset/)\r\nImage Source: [https://keithito.com/LJ-Speech-Dataset/](https://keithito.com/LJ-Speech-Dataset/)\r\nAudio Source: [https://keithito.com/LJ-Speech-Dataset/](https://keithito.com/LJ-Speech-Dataset/)","description_withheld":null,"homepage":"https://keithito.com/LJ-Speech-Dataset/","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":null,"title":"The lj speech dataset","first_author":null,"url":"https://keithito.com/LJ-Speech-Dataset/"},"license":{"name":"Public domain","url":"https://librivox.org/pages/public-domain/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Automatic Speech Recognition","url":"/task/automatic-speech-recognition-2","datasets_with_task":"/datasets/task/automatic-speech-recognition-2"},{"name":"Speech Synthesis","url":"/task/speech-synthesis","datasets_with_task":"/datasets/task/speech-synthesis"},{"name":"Text-To-Speech Synthesis","url":"/task/text-to-speech-synthesis","datasets_with_task":"/datasets/task/text-to-speech-synthesis"},{"name":"Resynthesis","url":"/task/resynthesis","datasets_with_task":"/datasets/task/resynthesis"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["LJSpeech"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/keithito/lj_speech","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/lj_speech","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/ljspeech","frameworks":["tf","jax"]},{"repo":"https://github.com/pytorch/audio","url":"https://pytorch.org/audio/stable/datasets.html#torchaudio.datasets.LJSPEECH","frameworks":["pytorch"]}],"num_papers_in_archive":323,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-to-speech-synthesis-on-ljspeech","task":"Text-To-Speech Synthesis","dataset_variant":"LJSpeech","rows":16,"metrics":["Audio Quality MOS","Pleasantness MOS","Word Error Rate (WER)","MOS","WER (%)"],"first_row_in_archive_order":{"model":"NaturalSpeech","paper":"/paper/naturalspeech-end-to-end-text-to-speech","metrics":{"Audio Quality MOS":"4.56"},"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"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-synthesis-on-ljspeech","task":"Speech Synthesis","dataset_variant":"LJSpeech","rows":4,"metrics":["Mean Opinion Score"],"first_row_in_archive_order":{"model":"BDDM vocoder","paper":"/paper/bddm-bilateral-denoising-diffusion-models-for-1","metrics":{"Mean Opinion Score":"4.48"},"code_links":[{"title":"tencent-ailab/bddm","url":"https://github.com/tencent-ailab/bddm"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":13,"of":13,"counts":{"papers_with_a_benchmark_row":13,"with_a_code_link":13,"where_syntology_ran_a_sample":10,"not_listed_spam_title":0,"listed":13,"listed_where_code_ran":10,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":9,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":9,"listed_every_run_a_failure_of_syntologys_instrument":1,"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 with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/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","rows_on_this_dataset":3,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":4,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/bddm-bilateral-denoising-diffusion-models-for-1","slug":"bddm-bilateral-denoising-diffusion-models-for-1","title":"BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis","date":"2022-03-25","arxiv_id":"2203.13508","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["tencent-ailab/bddm"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bddm-bilateral-denoising-diffusion-models-for-1#ran","syntology_url":"https://syntology.ai/paper/2203.13508","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.13508"}}}},{"paper":"/paper/neural-hmms-are-all-you-need-for-high-quality","slug":"neural-hmms-are-all-you-need-for-high-quality","title":"Neural HMMs are all you need (for high-quality attention-free TTS)","date":"2021-08-30","arxiv_id":"2108.13320","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":18,"samples_ran":15,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":6,"samples_unverified":3,"pointer_only_for_licence":3,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/diffwave-a-versatile-diffusion-model-for","slug":"diffwave-a-versatile-diffusion-model-for","title":"DiffWave: A Versatile Diffusion Model for Audio Synthesis","date":"2020-09-21","arxiv_id":"2009.09761","rows_on_this_dataset":1,"code_links":11,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":33,"samples_ran":20,"samples_constructed":11,"samples_ran_checked":13,"samples_ran_instrument_failed":7,"samples_unverified":13,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/diffwave-a-versatile-diffusion-model-for#ran","syntology_url":"https://syntology.ai/paper/2009.09761","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.09761"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":37,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":119,"samples_ran":83,"samples_constructed":27,"samples_ran_checked":70,"samples_ran_instrument_failed":13,"samples_unverified":36,"pointer_only_for_licence":40,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":13,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":3,"samples_unverified":1,"pointer_only_for_licence":2,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":19,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":3,"samples_unverified":8,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":2,"code_links":22,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":3,"samples_unverified":1,"pointer_only_for_licence":3,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":6,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/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","rows_on_this_dataset":3,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":4,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/bddm-bilateral-denoising-diffusion-models-for-1","slug":"bddm-bilateral-denoising-diffusion-models-for-1","title":"BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis","date":"2022-03-25","arxiv_id":"2203.13508","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["tencent-ailab/bddm"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bddm-bilateral-denoising-diffusion-models-for-1#ran","syntology_url":"https://syntology.ai/paper/2203.13508","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.13508"}}}},{"paper":"/paper/neural-hmms-are-all-you-need-for-high-quality","slug":"neural-hmms-are-all-you-need-for-high-quality","title":"Neural HMMs are all you need (for high-quality attention-free TTS)","date":"2021-08-30","arxiv_id":"2108.13320","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":18,"samples_ran":15,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":6,"samples_unverified":3,"pointer_only_for_licence":3,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/diffwave-a-versatile-diffusion-model-for","slug":"diffwave-a-versatile-diffusion-model-for","title":"DiffWave: A Versatile Diffusion Model for Audio Synthesis","date":"2020-09-21","arxiv_id":"2009.09761","rows_on_this_dataset":1,"code_links":11,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":33,"samples_ran":20,"samples_constructed":11,"samples_ran_checked":13,"samples_ran_instrument_failed":7,"samples_unverified":13,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/diffwave-a-versatile-diffusion-model-for#ran","syntology_url":"https://syntology.ai/paper/2009.09761","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.09761"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":37,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":119,"samples_ran":83,"samples_constructed":27,"samples_ran_checked":70,"samples_ran_instrument_failed":13,"samples_unverified":36,"pointer_only_for_licence":40,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":13,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":3,"samples_unverified":1,"pointer_only_for_licence":2,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":19,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":3,"samples_unverified":8,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":2,"code_links":22,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":3,"samples_unverified":1,"pointer_only_for_licence":3,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":6,"syntology":null}],"papers_where_code_ran":10,"papers_where_code_ran_first_page":"/dataset/ljspeech/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/ljspeech/papers/ran/1","json":"/dataset/ljspeech/papers/ran/1.json","rows":10}],"row_route":"each paper's syntology object 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","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":10,"samples_harvested":229,"samples_ran":164,"samples_constructed":38,"samples_ran_checked":126,"samples_ran_instrument_failed":38,"samples_unverified":65,"pointer_only_for_licence":52,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":10,"papers_with_a_run_with_no_instrument_failure":9,"papers_where_every_run_was_an_instrument_failure":1,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_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'","samples_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_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"36debb7e663a86be21571639d080c1be0601bc696fff0e0859c5c33dc9019f7c","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}