{"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/voxforge","name":"VoxForge","full_name":"VoxForge","description_markdown":"**VoxForge** is an open speech dataset that was set up to collect transcribed speech for use with Free and Open Source Speech Recognition Engines (on Linux, Windows and Mac).\nImage Source: [http://www.voxforge.org/home](http://www.voxforge.org/home)","description_withheld":null,"homepage":"http://www.voxforge.org/home","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Audio","url":"/datasets/modality/audio"},{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Accented Speech Recognition","url":"/task/accented-speech-recognition","datasets_with_task":"/datasets/task/accented-speech-recognition"},{"name":"Keyword Spotting","url":"/task/keyword-spotting","datasets_with_task":"/datasets/task/keyword-spotting"},{"name":"Spoken language identification","url":"/task/spoken-language-identification","datasets_with_task":"/datasets/task/spoken-language-identification"},{"name":"Language Identification","url":"/task/language-identification","datasets_with_task":"/datasets/task/language-identification"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"French","url":"/datasets/language/french"},{"name":"Spanish","url":"/datasets/language/spanish"},{"name":"German","url":"/datasets/language/german"},{"name":"Italian","url":"/datasets/language/italian"},{"name":"Japanese","url":"/datasets/language/japanese"},{"name":"Russian","url":"/datasets/language/russian"}],"variants":["VoxForge American-Canadian","VoxForge Commonwealth","VoxForge European","VoxForge Indian","VoxForge"],"data_loaders":[{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/voxforge","frameworks":["tf","jax"]}],"num_papers_in_archive":11,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/spoken-language-identification-on-voxforge-1","task":"Spoken language identification","dataset_variant":"VoxForge European","rows":5,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"2D ConvNet(MixUp=YES)","paper":"/paper/spoken-language-identification-using-convnets","metrics":{"Accuracy (%)":"96.3"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/spoken-language-identification-on-voxforge","task":"Spoken language identification","dataset_variant":"VoxForge Commonwealth","rows":4,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"2D ConvNet(MixUp=YES)","paper":"/paper/spoken-language-identification-using-convnets","metrics":{"Accuracy (%)":"95.4"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/spoken-language-identification-on-voxforge-2","task":"Spoken language identification","dataset_variant":"VoxForge","rows":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"LEAF","paper":"/paper/efficientleaf-a-faster-learnable-audio","metrics":{"Accuracy":"91.5"},"code_links":[{"title":"cpjku/efficientleaf","url":"https://github.com/cpjku/efficientleaf"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/accented-speech-recognition-on-voxforge","task":"Accented Speech Recognition","dataset_variant":"VoxForge Indian","rows":2,"metrics":["Percentage error"],"first_row_in_archive_order":{"model":"Deep Speech 2","paper":"/paper/deep-speech-2-end-to-end-speech-recognition","metrics":{"Percentage error":"22.44"},"code_links":[{"title":"tensorflow/models","url":"https://github.com/tensorflow/models/tree/master/research/deep_speech"},{"title":"PaddlePaddle/PaddleSpeech","url":"https://github.com/PaddlePaddle/PaddleSpeech"},{"title":"PaddlePaddle/models","url":"https://github.com/PaddlePaddle/models"},{"title":"baidu-research/warp-ctc","url":"https://github.com/baidu-research/warp-ctc"},{"title":"SeanNaren/deepspeech.pytorch","url":"https://github.com/SeanNaren/deepspeech.pytorch"},{"title":"TensorSpeech/TensorFlowASR","url":"https://github.com/TensorSpeech/TensorFlowASR"},{"title":"DeepMark/deepmark","url":"https://github.com/DeepMark/deepmark"},{"title":"SeanNaren/deepspeech.torch","url":"https://github.com/SeanNaren/deepspeech.torch"},{"title":"robmsmt/KerasDeepSpeech","url":"https://github.com/robmsmt/KerasDeepSpeech"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/research/audio/deepspeech2"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/official/cv/warpctc"},{"title":"msalhab96/SpeeQ","url":"https://github.com/msalhab96/SpeeQ"},{"title":"myrtleSoftware/deepspeech","url":"https://github.com/myrtleSoftware/deepspeech"},{"title":"sooftware/End-to-End-Speech-Recognition-Models","url":"https://github.com/sooftware/End-to-End-Speech-Recognition-Models"},{"title":"sooftware/OpenSpeech","url":"https://github.com/sooftware/OpenSpeech"},{"title":"victor369basu/End2EndAutomaticSpeechRecognition","url":"https://github.com/victor369basu/End2EndAutomaticSpeechRecognition"},{"title":"raotnameh/End-to-end-E2E-Named-Entity-Recognition-from-English-Speech","url":"https://github.com/raotnameh/End-to-end-E2E-Named-Entity-Recognition-from-English-Speech"},{"title":"fd873630/deep_speech_2_korean","url":"https://github.com/fd873630/deep_speech_2_korean"},{"title":"mangelroman/audio2score","url":"https://github.com/mangelroman/audio2score"},{"title":"cosmoquester/speech-recognition","url":"https://github.com/cosmoquester/speech-recognition"},{"title":"switiz/deepspeech2.pytorch","url":"https://github.com/switiz/deepspeech2.pytorch"},{"title":"bjtommychen/Keras_DeepSpeech2_SpeechRecognition","url":"https://github.com/bjtommychen/Keras_DeepSpeech2_SpeechRecognition"},{"title":"GavinGuan95/Punctuator.Pytorch","url":"https://github.com/GavinGuan95/Punctuator.Pytorch"},{"title":"MangoMoe/VerbalVim","url":"https://github.com/MangoMoe/VerbalVim"},{"title":"umd-fire-coml/2020-Speech-Recognition","url":"https://github.com/umd-fire-coml/2020-Speech-Recognition"},{"title":"hkakitani/deepspeech.pytorch","url":"https://github.com/hkakitani/deepspeech.pytorch"},{"title":"sburud/master","url":"https://gitlab.com/sburud/master"},{"title":"raraz15/DeepTurkish","url":"https://github.com/raraz15/DeepTurkish"},{"title":"UnofficialJuliaMirror/DeepMark-deepmark","url":"https://github.com/UnofficialJuliaMirror/DeepMark-deepmark"},{"title":"freshtan/deepspeech2","url":"https://github.com/freshtan/deepspeech2"},{"title":"wangys102/MindSpore","url":"https://github.com/wangys102/MindSpore/tree/main/DeepSpeech2"},{"title":"2023-MindSpore-1/ms-code-63","url":"https://github.com/2023-MindSpore-1/ms-code-63"},{"title":"2023-MindSpore-1/ms-code-57","url":"https://github.com/2023-MindSpore-1/ms-code-57"},{"title":"UnofficialJuliaMirrorSnapshots/DeepMark-deepmark","url":"https://github.com/UnofficialJuliaMirrorSnapshots/DeepMark-deepmark"},{"title":"MindSpore-paper-code-2/code400","url":"https://github.com/MindSpore-paper-code-2/code400/tree/main/DeepSpeech2"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/accented-speech-recognition-on-voxforge-1","task":"Accented Speech Recognition","dataset_variant":"VoxForge Commonwealth","rows":2,"metrics":["Percentage error"],"first_row_in_archive_order":{"model":"Deep Speech 2","paper":"/paper/deep-speech-2-end-to-end-speech-recognition","metrics":{"Percentage error":"13.56"},"code_links":[{"title":"tensorflow/models","url":"https://github.com/tensorflow/models/tree/master/research/deep_speech"},{"title":"PaddlePaddle/PaddleSpeech","url":"https://github.com/PaddlePaddle/PaddleSpeech"},{"title":"PaddlePaddle/models","url":"https://github.com/PaddlePaddle/models"},{"title":"baidu-research/warp-ctc","url":"https://github.com/baidu-research/warp-ctc"},{"title":"SeanNaren/deepspeech.pytorch","url":"https://github.com/SeanNaren/deepspeech.pytorch"},{"title":"TensorSpeech/TensorFlowASR","url":"https://github.com/TensorSpeech/TensorFlowASR"},{"title":"DeepMark/deepmark","url":"https://github.com/DeepMark/deepmark"},{"title":"SeanNaren/deepspeech.torch","url":"https://github.com/SeanNaren/deepspeech.torch"},{"title":"robmsmt/KerasDeepSpeech","url":"https://github.com/robmsmt/KerasDeepSpeech"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/research/audio/deepspeech2"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/official/cv/warpctc"},{"title":"msalhab96/SpeeQ","url":"https://github.com/msalhab96/SpeeQ"},{"title":"myrtleSoftware/deepspeech","url":"https://github.com/myrtleSoftware/deepspeech"},{"title":"sooftware/End-to-End-Speech-Recognition-Models","url":"https://github.com/sooftware/End-to-End-Speech-Recognition-Models"},{"title":"sooftware/OpenSpeech","url":"https://github.com/sooftware/OpenSpeech"},{"title":"victor369basu/End2EndAutomaticSpeechRecognition","url":"https://github.com/victor369basu/End2EndAutomaticSpeechRecognition"},{"title":"raotnameh/End-to-end-E2E-Named-Entity-Recognition-from-English-Speech","url":"https://github.com/raotnameh/End-to-end-E2E-Named-Entity-Recognition-from-English-Speech"},{"title":"fd873630/deep_speech_2_korean","url":"https://github.com/fd873630/deep_speech_2_korean"},{"title":"mangelroman/audio2score","url":"https://github.com/mangelroman/audio2score"},{"title":"cosmoquester/speech-recognition","url":"https://github.com/cosmoquester/speech-recognition"},{"title":"switiz/deepspeech2.pytorch","url":"https://github.com/switiz/deepspeech2.pytorch"},{"title":"bjtommychen/Keras_DeepSpeech2_SpeechRecognition","url":"https://github.com/bjtommychen/Keras_DeepSpeech2_SpeechRecognition"},{"title":"GavinGuan95/Punctuator.Pytorch","url":"https://github.com/GavinGuan95/Punctuator.Pytorch"},{"title":"MangoMoe/VerbalVim","url":"https://github.com/MangoMoe/VerbalVim"},{"title":"umd-fire-coml/2020-Speech-Recognition","url":"https://github.com/umd-fire-coml/2020-Speech-Recognition"},{"title":"hkakitani/deepspeech.pytorch","url":"https://github.com/hkakitani/deepspeech.pytorch"},{"title":"sburud/master","url":"https://gitlab.com/sburud/master"},{"title":"raraz15/DeepTurkish","url":"https://github.com/raraz15/DeepTurkish"},{"title":"UnofficialJuliaMirror/DeepMark-deepmark","url":"https://github.com/UnofficialJuliaMirror/DeepMark-deepmark"},{"title":"freshtan/deepspeech2","url":"https://github.com/freshtan/deepspeech2"},{"title":"wangys102/MindSpore","url":"https://github.com/wangys102/MindSpore/tree/main/DeepSpeech2"},{"title":"2023-MindSpore-1/ms-code-63","url":"https://github.com/2023-MindSpore-1/ms-code-63"},{"title":"2023-MindSpore-1/ms-code-57","url":"https://github.com/2023-MindSpore-1/ms-code-57"},{"title":"UnofficialJuliaMirrorSnapshots/DeepMark-deepmark","url":"https://github.com/UnofficialJuliaMirrorSnapshots/DeepMark-deepmark"},{"title":"MindSpore-paper-code-2/code400","url":"https://github.com/MindSpore-paper-code-2/code400/tree/main/DeepSpeech2"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/accented-speech-recognition-on-voxforge-2","task":"Accented Speech Recognition","dataset_variant":"VoxForge European","rows":2,"metrics":["Percentage error"],"first_row_in_archive_order":{"model":"Deep Speech 2","paper":"/paper/deep-speech-2-end-to-end-speech-recognition","metrics":{"Percentage error":"17.55"},"code_links":[{"title":"tensorflow/models","url":"https://github.com/tensorflow/models/tree/master/research/deep_speech"},{"title":"PaddlePaddle/PaddleSpeech","url":"https://github.com/PaddlePaddle/PaddleSpeech"},{"title":"PaddlePaddle/models","url":"https://github.com/PaddlePaddle/models"},{"title":"baidu-research/warp-ctc","url":"https://github.com/baidu-research/warp-ctc"},{"title":"SeanNaren/deepspeech.pytorch","url":"https://github.com/SeanNaren/deepspeech.pytorch"},{"title":"TensorSpeech/TensorFlowASR","url":"https://github.com/TensorSpeech/TensorFlowASR"},{"title":"DeepMark/deepmark","url":"https://github.com/DeepMark/deepmark"},{"title":"SeanNaren/deepspeech.torch","url":"https://github.com/SeanNaren/deepspeech.torch"},{"title":"robmsmt/KerasDeepSpeech","url":"https://github.com/robmsmt/KerasDeepSpeech"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/research/audio/deepspeech2"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/official/cv/warpctc"},{"title":"msalhab96/SpeeQ","url":"https://github.com/msalhab96/SpeeQ"},{"title":"myrtleSoftware/deepspeech","url":"https://github.com/myrtleSoftware/deepspeech"},{"title":"sooftware/End-to-End-Speech-Recognition-Models","url":"https://github.com/sooftware/End-to-End-Speech-Recognition-Models"},{"title":"sooftware/OpenSpeech","url":"https://github.com/sooftware/OpenSpeech"},{"title":"victor369basu/End2EndAutomaticSpeechRecognition","url":"https://github.com/victor369basu/End2EndAutomaticSpeechRecognition"},{"title":"raotnameh/End-to-end-E2E-Named-Entity-Recognition-from-English-Speech","url":"https://github.com/raotnameh/End-to-end-E2E-Named-Entity-Recognition-from-English-Speech"},{"title":"fd873630/deep_speech_2_korean","url":"https://github.com/fd873630/deep_speech_2_korean"},{"title":"mangelroman/audio2score","url":"https://github.com/mangelroman/audio2score"},{"title":"cosmoquester/speech-recognition","url":"https://github.com/cosmoquester/speech-recognition"},{"title":"switiz/deepspeech2.pytorch","url":"https://github.com/switiz/deepspeech2.pytorch"},{"title":"bjtommychen/Keras_DeepSpeech2_SpeechRecognition","url":"https://github.com/bjtommychen/Keras_DeepSpeech2_SpeechRecognition"},{"title":"GavinGuan95/Punctuator.Pytorch","url":"https://github.com/GavinGuan95/Punctuator.Pytorch"},{"title":"MangoMoe/VerbalVim","url":"https://github.com/MangoMoe/VerbalVim"},{"title":"umd-fire-coml/2020-Speech-Recognition","url":"https://github.com/umd-fire-coml/2020-Speech-Recognition"},{"title":"hkakitani/deepspeech.pytorch","url":"https://github.com/hkakitani/deepspeech.pytorch"},{"title":"sburud/master","url":"https://gitlab.com/sburud/master"},{"title":"raraz15/DeepTurkish","url":"https://github.com/raraz15/DeepTurkish"},{"title":"UnofficialJuliaMirror/DeepMark-deepmark","url":"https://github.com/UnofficialJuliaMirror/DeepMark-deepmark"},{"title":"freshtan/deepspeech2","url":"https://github.com/freshtan/deepspeech2"},{"title":"wangys102/MindSpore","url":"https://github.com/wangys102/MindSpore/tree/main/DeepSpeech2"},{"title":"2023-MindSpore-1/ms-code-63","url":"https://github.com/2023-MindSpore-1/ms-code-63"},{"title":"2023-MindSpore-1/ms-code-57","url":"https://github.com/2023-MindSpore-1/ms-code-57"},{"title":"UnofficialJuliaMirrorSnapshots/DeepMark-deepmark","url":"https://github.com/UnofficialJuliaMirrorSnapshots/DeepMark-deepmark"},{"title":"MindSpore-paper-code-2/code400","url":"https://github.com/MindSpore-paper-code-2/code400/tree/main/DeepSpeech2"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/accented-speech-recognition-on-voxforge-3","task":"Accented Speech Recognition","dataset_variant":"VoxForge American-Canadian","rows":2,"metrics":["Percentage error"],"first_row_in_archive_order":{"model":"Deep Speech 2","paper":"/paper/deep-speech-2-end-to-end-speech-recognition","metrics":{"Percentage error":"7.55"},"code_links":[{"title":"tensorflow/models","url":"https://github.com/tensorflow/models/tree/master/research/deep_speech"},{"title":"PaddlePaddle/PaddleSpeech","url":"https://github.com/PaddlePaddle/PaddleSpeech"},{"title":"PaddlePaddle/models","url":"https://github.com/PaddlePaddle/models"},{"title":"baidu-research/warp-ctc","url":"https://github.com/baidu-research/warp-ctc"},{"title":"SeanNaren/deepspeech.pytorch","url":"https://github.com/SeanNaren/deepspeech.pytorch"},{"title":"TensorSpeech/TensorFlowASR","url":"https://github.com/TensorSpeech/TensorFlowASR"},{"title":"DeepMark/deepmark","url":"https://github.com/DeepMark/deepmark"},{"title":"SeanNaren/deepspeech.torch","url":"https://github.com/SeanNaren/deepspeech.torch"},{"title":"robmsmt/KerasDeepSpeech","url":"https://github.com/robmsmt/KerasDeepSpeech"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/research/audio/deepspeech2"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/official/cv/warpctc"},{"title":"msalhab96/SpeeQ","url":"https://github.com/msalhab96/SpeeQ"},{"title":"myrtleSoftware/deepspeech","url":"https://github.com/myrtleSoftware/deepspeech"},{"title":"sooftware/End-to-End-Speech-Recognition-Models","url":"https://github.com/sooftware/End-to-End-Speech-Recognition-Models"},{"title":"sooftware/OpenSpeech","url":"https://github.com/sooftware/OpenSpeech"},{"title":"victor369basu/End2EndAutomaticSpeechRecognition","url":"https://github.com/victor369basu/End2EndAutomaticSpeechRecognition"},{"title":"raotnameh/End-to-end-E2E-Named-Entity-Recognition-from-English-Speech","url":"https://github.com/raotnameh/End-to-end-E2E-Named-Entity-Recognition-from-English-Speech"},{"title":"fd873630/deep_speech_2_korean","url":"https://github.com/fd873630/deep_speech_2_korean"},{"title":"mangelroman/audio2score","url":"https://github.com/mangelroman/audio2score"},{"title":"cosmoquester/speech-recognition","url":"https://github.com/cosmoquester/speech-recognition"},{"title":"switiz/deepspeech2.pytorch","url":"https://github.com/switiz/deepspeech2.pytorch"},{"title":"bjtommychen/Keras_DeepSpeech2_SpeechRecognition","url":"https://github.com/bjtommychen/Keras_DeepSpeech2_SpeechRecognition"},{"title":"GavinGuan95/Punctuator.Pytorch","url":"https://github.com/GavinGuan95/Punctuator.Pytorch"},{"title":"MangoMoe/VerbalVim","url":"https://github.com/MangoMoe/VerbalVim"},{"title":"umd-fire-coml/2020-Speech-Recognition","url":"https://github.com/umd-fire-coml/2020-Speech-Recognition"},{"title":"hkakitani/deepspeech.pytorch","url":"https://github.com/hkakitani/deepspeech.pytorch"},{"title":"sburud/master","url":"https://gitlab.com/sburud/master"},{"title":"raraz15/DeepTurkish","url":"https://github.com/raraz15/DeepTurkish"},{"title":"UnofficialJuliaMirror/DeepMark-deepmark","url":"https://github.com/UnofficialJuliaMirror/DeepMark-deepmark"},{"title":"freshtan/deepspeech2","url":"https://github.com/freshtan/deepspeech2"},{"title":"wangys102/MindSpore","url":"https://github.com/wangys102/MindSpore/tree/main/DeepSpeech2"},{"title":"2023-MindSpore-1/ms-code-63","url":"https://github.com/2023-MindSpore-1/ms-code-63"},{"title":"2023-MindSpore-1/ms-code-57","url":"https://github.com/2023-MindSpore-1/ms-code-57"},{"title":"UnofficialJuliaMirrorSnapshots/DeepMark-deepmark","url":"https://github.com/UnofficialJuliaMirrorSnapshots/DeepMark-deepmark"},{"title":"MindSpore-paper-code-2/code400","url":"https://github.com/MindSpore-paper-code-2/code400/tree/main/DeepSpeech2"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/keyword-spotting-on-voxforge","task":"Keyword Spotting","dataset_variant":"VoxForge","rows":2,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"1D-ConvNet","paper":"/paper/spoken-language-identification-using-convnets","metrics":{"Accuracy (%)":"93.7"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/language-identification-on-voxforge","task":"Language Identification","dataset_variant":"VoxForge","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ConformerG-P","paper":"/paper/bigssl-exploring-the-frontier-of-large-scale","metrics":{"Accuracy":"99.8"},"code_links":[]},"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":5,"of":5,"counts":{"papers_with_a_benchmark_row":5,"with_a_code_link":3,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":5,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":0,"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/efficientleaf-a-faster-learnable-audio","slug":"efficientleaf-a-faster-learnable-audio","title":"EfficientLEAF: A Faster LEarnable Audio Frontend of Questionable Use","date":"2022-07-12","arxiv_id":"2207.05508","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/bigssl-exploring-the-frontier-of-large-scale","slug":"bigssl-exploring-the-frontier-of-large-scale","title":"BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition","date":"2021-09-27","arxiv_id":"2109.13226","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/spoken-language-identification-using-convnets","slug":"spoken-language-identification-using-convnets","title":"Spoken Language Identification using ConvNets","date":"2019-10-09","arxiv_id":"1910.04269","rows_on_this_dataset":11,"code_links":0,"syntology":null},{"paper":"/paper/deep-speech-2-end-to-end-speech-recognition","slug":"deep-speech-2-end-to-end-speech-recognition","title":"Deep Speech 2: End-to-End Speech Recognition in English and Mandarin","date":"2015-12-08","arxiv_id":"1512.02595","rows_on_this_dataset":4,"code_links":35,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":39,"samples_ran":33,"samples_constructed":0,"samples_ran_checked":32,"samples_ran_instrument_failed":1,"samples_unverified":6,"pointer_only_for_licence":0,"official":{"repos":["PaddlePaddle/PaddleSpeech"],"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/deep-speech-2-end-to-end-speech-recognition#ran","syntology_url":"https://syntology.ai/paper/1512.02595","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1512.02595"}}}},{"paper":"/paper/deep-speech-scaling-up-end-to-end-speech","slug":"deep-speech-scaling-up-end-to-end-speech","title":"Deep Speech: Scaling up end-to-end speech recognition","date":"2014-12-17","arxiv_id":"1412.5567","rows_on_this_dataset":4,"code_links":24,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":7,"samples_unverified":0,"pointer_only_for_licence":8,"official":{"repos":["PaddlePaddle/PaddleSpeech"],"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/deep-speech-scaling-up-end-to-end-speech#ran","syntology_url":"https://syntology.ai/paper/1412.5567","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1412.5567"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/efficientleaf-a-faster-learnable-audio","slug":"efficientleaf-a-faster-learnable-audio","title":"EfficientLEAF: A Faster LEarnable Audio Frontend of Questionable Use","date":"2022-07-12","arxiv_id":"2207.05508","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/bigssl-exploring-the-frontier-of-large-scale","slug":"bigssl-exploring-the-frontier-of-large-scale","title":"BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition","date":"2021-09-27","arxiv_id":"2109.13226","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/spoken-language-identification-using-convnets","slug":"spoken-language-identification-using-convnets","title":"Spoken Language Identification using ConvNets","date":"2019-10-09","arxiv_id":"1910.04269","rows_on_this_dataset":11,"code_links":0,"syntology":null},{"paper":"/paper/deep-speech-2-end-to-end-speech-recognition","slug":"deep-speech-2-end-to-end-speech-recognition","title":"Deep Speech 2: End-to-End Speech Recognition in English and Mandarin","date":"2015-12-08","arxiv_id":"1512.02595","rows_on_this_dataset":4,"code_links":35,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":39,"samples_ran":33,"samples_constructed":0,"samples_ran_checked":32,"samples_ran_instrument_failed":1,"samples_unverified":6,"pointer_only_for_licence":0,"official":{"repos":["PaddlePaddle/PaddleSpeech"],"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/deep-speech-2-end-to-end-speech-recognition#ran","syntology_url":"https://syntology.ai/paper/1512.02595","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1512.02595"}}}},{"paper":"/paper/deep-speech-scaling-up-end-to-end-speech","slug":"deep-speech-scaling-up-end-to-end-speech","title":"Deep Speech: Scaling up end-to-end speech recognition","date":"2014-12-17","arxiv_id":"1412.5567","rows_on_this_dataset":4,"code_links":24,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":7,"samples_unverified":0,"pointer_only_for_licence":8,"official":{"repos":["PaddlePaddle/PaddleSpeech"],"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/deep-speech-scaling-up-end-to-end-speech#ran","syntology_url":"https://syntology.ai/paper/1412.5567","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1412.5567"}}}}],"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/dataset/voxforge/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/voxforge/papers/ran/1","json":"/dataset/voxforge/papers/ran/1.json","rows":2}],"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":2,"samples_harvested":48,"samples_ran":42,"samples_constructed":0,"samples_ran_checked":34,"samples_ran_instrument_failed":8,"samples_unverified":6,"pointer_only_for_licence":8,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":2,"papers_with_a_run_with_no_instrument_failure":2,"papers_where_every_run_was_an_instrument_failure":0,"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":"24f286f545ca96f7cf891c8962c38aea23048b5a70afd7c588ec2e13ba7be67d","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}