{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/speech-recognition-1","name":"speech-recognition","slug":"speech-recognition-1","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":5715,"papers_with_code":1277,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":3,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/common-voice","name":"Common Voice","full_name":"Common Voice","num_papers_in_archive":449},{"url":"/dataset/voxpopuli","name":"VoxPopuli","full_name":"","num_papers_in_archive":113},{"url":"/dataset/openslr","name":"OpenSLR","full_name":"Open Speech and Language Resources","num_papers_in_archive":2}],"subtasks":[],"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":58,"rows_per_page":100,"shown":100,"of":5715,"of_with_code":1277,"tagged_in_all":5715,"counts":{"archive_papers_tagged":5715,"with_a_code_link":1277,"where_syntology_ran_a_sample":162,"not_listed_spam_title":0,"listed":5715,"listed_where_code_ran":162,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":133,"every_run_a_failure_of_syntologys_instrument":29,"listed_with_a_run_with_no_instrument_failure":133,"listed_every_run_a_failure_of_syntologys_instrument":29,"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/split-computing-and-early-exiting-for-deep","slug":"split-computing-and-early-exiting-for-deep","title":"Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges","date":"2021-03-08","arxiv_id":"2103.04505","repositories_listed":19,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/split-computing-and-early-exiting-for-deep#ran","syntology_url":"https://syntology.ai/paper/2103.04505","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.04505"}},"official":null}},{"url":"/paper/robust-speech-recognition-via-large-scale-1","slug":"robust-speech-recognition-via-large-scale-1","title":"Robust Speech Recognition via Large-Scale Weak Supervision","date":"2022-12-06","arxiv_id":"2212.04356","repositories_listed":15,"syntology":{"n":59,"n_ran":49,"n_constructed":0,"n_ran_checked":36,"n_instrument":13,"n_unverified":10,"n_honours":4,"n_violates":1,"n_no_contract":31,"n_pointer_only":21,"phrase":"49 ran (of which 0 constructed an object rather than computing a result; 36 with no instrument failure: 4 honoured, 1 violated, 31 with no contract checked; 13 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/robust-speech-recognition-via-large-scale-1#ran","syntology_url":"https://syntology.ai/paper/2212.04356","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.04356"}},"official":{"repos":["openai/whisper"],"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/wavlm-large-scale-self-supervised-pre","slug":"wavlm-large-scale-self-supervised-pre","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","date":"2021-10-26","arxiv_id":"2110.13900","repositories_listed":9,"syntology":null},{"url":"/paper/isynet-convolutional-neural-networks-design","slug":"isynet-convolutional-neural-networks-design","title":"ISyNet: Convolutional Neural Networks design for AI accelerator","date":"2021-09-04","arxiv_id":"2109.01932","repositories_listed":9,"syntology":null},{"url":"/paper/unsupervised-cross-lingual-representation-3","slug":"unsupervised-cross-lingual-representation-3","title":"Unsupervised Cross-lingual Representation Learning for Speech Recognition","date":"2020-06-24","arxiv_id":"2006.13979","repositories_listed":8,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/unsupervised-cross-lingual-representation-3#ran","syntology_url":"https://syntology.ai/paper/2006.13979","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.13979"}},"official":null}},{"url":"/paper/speecht5-unified-modal-encoder-decoder-pre","slug":"speecht5-unified-modal-encoder-decoder-pre","title":"SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing","date":"2021-10-14","arxiv_id":"2110.07205","repositories_listed":6,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/speecht5-unified-modal-encoder-decoder-pre#ran","syntology_url":"https://syntology.ai/paper/2110.07205","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.07205"}},"official":{"repos":["microsoft/speecht5"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/contextnet-improving-convolutional-neural","slug":"contextnet-improving-convolutional-neural","title":"ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context","date":"2020-05-07","arxiv_id":"2005.03191","repositories_listed":6,"syntology":null},{"url":"/paper/deep-gradient-compression-reducing-the","slug":"deep-gradient-compression-reducing-the","title":"Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training","date":"2017-12-05","arxiv_id":"1712.01887","repositories_listed":6,"syntology":null},{"url":"/paper/a-simple-way-to-initialize-recurrent-networks","slug":"a-simple-way-to-initialize-recurrent-networks","title":"A Simple Way to Initialize Recurrent Networks of Rectified Linear Units","date":"2015-04-03","arxiv_id":"1504.00941","repositories_listed":6,"syntology":null},{"url":"/paper/the-llama-3-herd-of-models","slug":"the-llama-3-herd-of-models","title":"The Llama 3 Herd of Models","date":"2024-07-31","arxiv_id":"2407.21783","repositories_listed":5,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/the-llama-3-herd-of-models#ran","syntology_url":"https://syntology.ai/paper/2407.21783","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.21783"}},"official":null}},{"url":"/paper/efficient-self-supervised-learning-with","slug":"efficient-self-supervised-learning-with","title":"Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language","date":"2022-12-14","arxiv_id":"2212.07525","repositories_listed":5,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"5 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; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/efficient-self-supervised-learning-with#ran","syntology_url":"https://syntology.ai/paper/2212.07525","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.07525"}},"official":{"repos":["facebookresearch/fairseq"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/unispeech-sat-universal-speech-representation","slug":"unispeech-sat-universal-speech-representation","title":"UniSpeech-SAT: Universal Speech Representation Learning with Speaker Aware Pre-Training","date":"2021-10-12","arxiv_id":"2110.05752","repositories_listed":5,"syntology":null},{"url":"/paper/unispeech-unified-speech-representation","slug":"unispeech-unified-speech-representation","title":"UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data","date":"2021-01-19","arxiv_id":"2101.07597","repositories_listed":5,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unispeech-unified-speech-representation#ran","syntology_url":"https://syntology.ai/paper/2101.07597","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.07597"}},"official":{"repos":["cywang97/unispeech"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/unified-streaming-and-non-streaming-two-pass","slug":"unified-streaming-and-non-streaming-two-pass","title":"Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognition","date":"2020-12-10","arxiv_id":"2012.05481","repositories_listed":5,"syntology":null},{"url":"/paper/stochastic-attention-head-removal-a-simple","slug":"stochastic-attention-head-removal-a-simple","title":"Stochastic Attention Head Removal: A simple and effective method for improving Transformer Based ASR Models","date":"2020-11-08","arxiv_id":"2011.04004","repositories_listed":5,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/stochastic-attention-head-removal-a-simple#ran","syntology_url":"https://syntology.ai/paper/2011.04004","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.04004"}},"official":{"repos":["s1603602/attention_head_removal"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/fairseq-s2t-fast-speech-to-text-modeling-with","slug":"fairseq-s2t-fast-speech-to-text-modeling-with","title":"fairseq S2T: Fast Speech-to-Text Modeling with fairseq","date":"2020-10-11","arxiv_id":"2010.05171","repositories_listed":5,"syntology":null},{"url":"/paper/transformer-transducer-a-streamable-speech","slug":"transformer-transducer-a-streamable-speech","title":"Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss","date":"2020-02-07","arxiv_id":"2002.02562","repositories_listed":5,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/transformer-transducer-a-streamable-speech#ran","syntology_url":"https://syntology.ai/paper/2002.02562","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.02562"}},"official":null}},{"url":"/paper/voicefilter-targeted-voice-separation-by","slug":"voicefilter-targeted-voice-separation-by","title":"VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Masking","date":"2018-10-11","arxiv_id":"1810.04826","repositories_listed":5,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/voicefilter-targeted-voice-separation-by#ran","syntology_url":"https://syntology.ai/paper/1810.04826","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.04826"}},"official":null}},{"url":"/paper/an-overview-of-multi-task-learning-in-deep","slug":"an-overview-of-multi-task-learning-in-deep","title":"An Overview of Multi-Task Learning in Deep Neural Networks","date":"2017-06-15","arxiv_id":"1706.05098","repositories_listed":5,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/an-overview-of-multi-task-learning-in-deep#ran","syntology_url":"https://syntology.ai/paper/1706.05098","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.05098"}},"official":null}},{"url":"/paper/first-pass-large-vocabulary-continuous-speech","slug":"first-pass-large-vocabulary-continuous-speech","title":"First-Pass Large Vocabulary Continuous Speech Recognition using Bi-Directional Recurrent DNNs","date":"2014-08-12","arxiv_id":"1408.2873","repositories_listed":5,"syntology":null},{"url":"/paper/speech-slytherin-examining-the-performance","slug":"speech-slytherin-examining-the-performance","title":"Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech Separation, Recognition, and Synthesis","date":"2024-07-13","arxiv_id":"2407.09732","repositories_listed":4,"syntology":null},{"url":"/paper/scaling-speech-technology-to-1000-languages-1","slug":"scaling-speech-technology-to-1000-languages-1","title":"Scaling Speech Technology to 1,000+ Languages","date":"2023-05-22","arxiv_id":"2305.13516","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/scaling-speech-technology-to-1000-languages-1#ran","syntology_url":"https://syntology.ai/paper/2305.13516","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13516"}},"official":{"repos":["facebookresearch/fairseq","pytorch/fairseq"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/multi-blank-transducers-for-speech","slug":"multi-blank-transducers-for-speech","title":"Multi-blank Transducers for Speech Recognition","date":"2022-11-04","arxiv_id":"2211.03541","repositories_listed":4,"syntology":null},{"url":"/paper/self-supervised-learning-with-random","slug":"self-supervised-learning-with-random","title":"Self-supervised Learning with Random-projection Quantizer for Speech Recognition","date":"2022-02-03","arxiv_id":"2202.01855","repositories_listed":4,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":9,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":4,"n_no_contract":4,"n_pointer_only":3,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 4 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/self-supervised-learning-with-random#ran","syntology_url":"https://syntology.ai/paper/2202.01855","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.01855"}},"official":null}},{"url":"/paper/fine-tuning-wav2vec2-for-speaker-recognition","slug":"fine-tuning-wav2vec2-for-speaker-recognition","title":"Fine-tuning wav2vec2 for speaker recognition","date":"2021-09-30","arxiv_id":"2109.15053","repositories_listed":4,"syntology":null},{"url":"/paper/unsupervised-speech-recognition","slug":"unsupervised-speech-recognition","title":"Unsupervised Speech Recognition","date":"2021-05-24","arxiv_id":"2105.11084","repositories_listed":4,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unsupervised-speech-recognition#ran","syntology_url":"https://syntology.ai/paper/2105.11084","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.11084"}},"official":{"repos":["pytorch/fairseq"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/okwugbe-end-to-end-speech-recognition-for-fon","slug":"okwugbe-end-to-end-speech-recognition-for-fon","title":"OkwuGbé: End-to-End Speech Recognition for Fon and Igbo","date":"2021-03-13","arxiv_id":"2103.07762","repositories_listed":4,"syntology":null},{"url":"/paper/wenet-production-first-and-production-ready","slug":"wenet-production-first-and-production-ready","title":"WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkit","date":"2021-02-02","arxiv_id":"2102.01547","repositories_listed":4,"syntology":null},{"url":"/paper/multi-modal-dense-video-captioning","slug":"multi-modal-dense-video-captioning","title":"Multi-modal Dense Video Captioning","date":"2020-03-17","arxiv_id":"2003.07758","repositories_listed":4,"syntology":null},{"url":"/paper/fully-quantizing-a-simplified-transformer-for","slug":"fully-quantizing-a-simplified-transformer-for","title":"A Simplified Fully Quantized Transformer for End-to-end Speech Recognition","date":"2019-11-09","arxiv_id":"1911.03604","repositories_listed":4,"syntology":null},{"url":"/paper/when-does-label-smoothing-help","slug":"when-does-label-smoothing-help","title":"When Does Label Smoothing Help?","date":"2019-06-06","arxiv_id":"1906.02629","repositories_listed":4,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/when-does-label-smoothing-help#ran","syntology_url":"https://syntology.ai/paper/1906.02629","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.02629"}},"official":null}},{"url":"/paper/transformers-with-convolutional-context-for","slug":"transformers-with-convolutional-context-for","title":"Transformers with convolutional context for ASR","date":"2019-04-26","arxiv_id":"1904.11660","repositories_listed":4,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"8 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/transformers-with-convolutional-context-for#ran","syntology_url":"https://syntology.ai/paper/1904.11660","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.11660"}},"official":null}},{"url":"/paper/bi-directional-lattice-recurrent-neural","slug":"bi-directional-lattice-recurrent-neural","title":"Bi-Directional Lattice Recurrent Neural Networks for Confidence Estimation","date":"2018-10-30","arxiv_id":"1810.13024","repositories_listed":4,"syntology":null},{"url":"/paper/deep-audio-visual-speech-recognition","slug":"deep-audio-visual-speech-recognition","title":"Deep Audio-Visual Speech Recognition","date":"2018-09-06","arxiv_id":"1809.02108","repositories_listed":4,"syntology":null},{"url":"/paper/tools-and-resources-for-romanian-text-to","slug":"tools-and-resources-for-romanian-text-to","title":"Tools and resources for Romanian text-to-speech and speech-to-text applications","date":"2018-02-15","arxiv_id":"1802.05583","repositories_listed":4,"syntology":null},{"url":"/paper/audio-adversarial-examples-targeted-attacks","slug":"audio-adversarial-examples-targeted-attacks","title":"Audio Adversarial Examples: Targeted Attacks on Speech-to-Text","date":"2018-01-05","arxiv_id":"1801.01944","repositories_listed":4,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/audio-adversarial-examples-targeted-attacks#ran","syntology_url":"https://syntology.ai/paper/1801.01944","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1801.01944"}},"official":null}},{"url":"/paper/deep-gradient-compression-reduce-the","slug":"deep-gradient-compression-reduce-the","title":"Deep Gradient Compression Reduce the Communication Bandwidth For distributed Traning","date":"2017-12-05","arxiv_id":null,"repositories_listed":4,"syntology":null},{"url":"/paper/state-of-the-art-speech-recognition-with","slug":"state-of-the-art-speech-recognition-with","title":"State-of-the-art Speech Recognition With Sequence-to-Sequence Models","date":"2017-12-05","arxiv_id":"1712.01769","repositories_listed":4,"syntology":null},{"url":"/paper/honk-a-pytorch-reimplementation-of","slug":"honk-a-pytorch-reimplementation-of","title":"Honk: A PyTorch Reimplementation of Convolutional Neural Networks for Keyword Spotting","date":"2017-10-18","arxiv_id":"1710.06554","repositories_listed":4,"syntology":null},{"url":"/paper/combining-residual-networks-with-lstms-for","slug":"combining-residual-networks-with-lstms-for","title":"Combining Residual Networks with LSTMs for Lipreading","date":"2017-03-12","arxiv_id":"1703.04105","repositories_listed":4,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/combining-residual-networks-with-lstms-for#ran","syntology_url":"https://syntology.ai/paper/1703.04105","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.04105"}},"official":{"repos":["tstafylakis/Lipreading-ResNet"],"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/geometric-deep-learning-on-graphs-and","slug":"geometric-deep-learning-on-graphs-and","title":"Geometric deep learning on graphs and manifolds using mixture model CNNs","date":"2016-11-25","arxiv_id":"1611.08402","repositories_listed":4,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"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) · 3 unverified","sample_list":"/paper/geometric-deep-learning-on-graphs-and#ran","syntology_url":"https://syntology.ai/paper/1611.08402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.08402"}},"official":null}},{"url":"/paper/tensorflow-large-scale-machine-learning-on","slug":"tensorflow-large-scale-machine-learning-on","title":"TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems","date":"2016-03-14","arxiv_id":"1603.04467","repositories_listed":4,"syntology":null},{"url":"/paper/eesen-end-to-end-speech-recognition-using","slug":"eesen-end-to-end-speech-recognition-using","title":"EESEN: End-to-End Speech Recognition using Deep RNN Models and WFST-based Decoding","date":"2015-07-29","arxiv_id":"1507.08240","repositories_listed":4,"syntology":null},{"url":"/paper/neural-nilm-deep-neural-networks-applied-to","slug":"neural-nilm-deep-neural-networks-applied-to","title":"Neural NILM: Deep Neural Networks Applied to Energy Disaggregation","date":"2015-07-23","arxiv_id":"1507.06594","repositories_listed":4,"syntology":{"n":17,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":0,"phrase":"13 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; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/neural-nilm-deep-neural-networks-applied-to#ran","syntology_url":"https://syntology.ai/paper/1507.06594","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1507.06594"}},"official":{"repos":["JackKelly/neuralnilm_prototype"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/an-exact-mapping-between-the-variational","slug":"an-exact-mapping-between-the-variational","title":"An exact mapping between the Variational Renormalization Group and Deep Learning","date":"2014-10-14","arxiv_id":"1410.3831","repositories_listed":4,"syntology":null},{"url":"/paper/moshi-a-speech-text-foundation-model-for-real","slug":"moshi-a-speech-text-foundation-model-for-real","title":"Moshi: a speech-text foundation model for real-time dialogue","date":"2024-09-17","arxiv_id":"2410.00037","repositories_listed":3,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/moshi-a-speech-text-foundation-model-for-real#ran","syntology_url":"https://syntology.ai/paper/2410.00037","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.00037"}},"official":{"repos":["kyutai-labs/moshi"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/funaudiollm-voice-understanding-and","slug":"funaudiollm-voice-understanding-and","title":"FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs","date":"2024-07-04","arxiv_id":"2407.04051","repositories_listed":3,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":4,"n_instrument":6,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/funaudiollm-voice-understanding-and#ran","syntology_url":"https://syntology.ai/paper/2407.04051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04051"}},"official":{"repos":["FunAudioLLM/SenseVoice","funaudiollm/cosyvoice"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/an-embarrassingly-simple-approach-for-llm","slug":"an-embarrassingly-simple-approach-for-llm","title":"An Embarrassingly Simple Approach for LLM with Strong ASR Capacity","date":"2024-02-13","arxiv_id":"2402.08846","repositories_listed":3,"syntology":null},{"url":"/paper/a-comparative-analysis-between-conformer","slug":"a-comparative-analysis-between-conformer","title":"A comparative analysis between Conformer-Transducer, Whisper, and wav2vec2 for improving the child speech recognition","date":"2023-11-07","arxiv_id":"2311.04936","repositories_listed":3,"syntology":null},{"url":"/paper/sthg-spatial-temporal-heterogeneous-graph","slug":"sthg-spatial-temporal-heterogeneous-graph","title":"STHG: Spatial-Temporal Heterogeneous Graph Learning for Advanced Audio-Visual Diarization","date":"2023-06-18","arxiv_id":"2306.10608","repositories_listed":3,"syntology":null},{"url":"/paper/atco2-corpus-a-large-scale-dataset-for","slug":"atco2-corpus-a-large-scale-dataset-for","title":"ATCO2 corpus: A Large-Scale Dataset for Research on Automatic Speech Recognition and Natural Language Understanding of Air Traffic Control Communications","date":"2022-11-08","arxiv_id":"2211.04054","repositories_listed":3,"syntology":null},{"url":"/paper/branchformer-parallel-mlp-attention","slug":"branchformer-parallel-mlp-attention","title":"Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understanding","date":"2022-07-06","arxiv_id":"2207.02971","repositories_listed":3,"syntology":null},{"url":"/paper/shallow-fusion-of-weighted-finite-state","slug":"shallow-fusion-of-weighted-finite-state","title":"Shallow Fusion of Weighted Finite-State Transducer and Language Model for Text Normalization","date":"2022-03-29","arxiv_id":"2203.15917","repositories_listed":3,"syntology":null},{"url":"/paper/wenet-2-0-more-productive-end-to-end-speech","slug":"wenet-2-0-more-productive-end-to-end-speech","title":"WeNet 2.0: More Productive End-to-End Speech Recognition Toolkit","date":"2022-03-29","arxiv_id":"2203.15455","repositories_listed":3,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":9,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/wenet-2-0-more-productive-end-to-end-speech#ran","syntology_url":"https://syntology.ai/paper/2203.15455","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15455"}},"official":{"repos":["wenet-e2e/wenet"],"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/mt3-multi-task-multitrack-music-transcription-1","slug":"mt3-multi-task-multitrack-music-transcription-1","title":"MT3: Multi-Task Multitrack Music Transcription","date":"2021-11-04","arxiv_id":"2111.03017","repositories_listed":3,"syntology":{"n":6,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 6 unverified","sample_list":"/paper/mt3-multi-task-multitrack-music-transcription-1#ran","syntology_url":"https://syntology.ai/paper/2111.03017","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.03017"}},"official":{"repos":["magenta/mt3"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":6,"ran_from_kinds":[]}}},{"url":"/paper/fast-rir-fast-neural-diffuse-room-impulse","slug":"fast-rir-fast-neural-diffuse-room-impulse","title":"FAST-RIR: Fast neural diffuse room impulse response generator","date":"2021-10-07","arxiv_id":"2110.04057","repositories_listed":3,"syntology":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/gigaspeech-an-evolving-multi-domain-asr","slug":"gigaspeech-an-evolving-multi-domain-asr","title":"GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio","date":"2021-06-13","arxiv_id":"2106.06909","repositories_listed":3,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/gigaspeech-an-evolving-multi-domain-asr#ran","syntology_url":"https://syntology.ai/paper/2106.06909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.06909"}},"official":{"repos":["SpeechColab/GigaSpeech"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/end-to-end-audio-visual-speech-recognition","slug":"end-to-end-audio-visual-speech-recognition","title":"End-to-end Audio-visual Speech Recognition with Conformers","date":"2021-02-12","arxiv_id":"2102.06657","repositories_listed":3,"syntology":null},{"url":"/paper/self-training-and-pre-training-are","slug":"self-training-and-pre-training-are","title":"Self-training and Pre-training are Complementary for Speech Recognition","date":"2020-10-22","arxiv_id":"2010.11430","repositories_listed":3,"syntology":null},{"url":"/paper/the-sequence-to-sequence-baseline-for-the","slug":"the-sequence-to-sequence-baseline-for-the","title":"The Sequence-to-Sequence Baseline for the Voice Conversion Challenge 2020: Cascading ASR and TTS","date":"2020-10-06","arxiv_id":"2010.02434","repositories_listed":3,"syntology":null},{"url":"/paper/kospeech-open-source-toolkit-for-end-to-end","slug":"kospeech-open-source-toolkit-for-end-to-end","title":"KoSpeech: Open-Source Toolkit for End-to-End Korean Speech Recognition","date":"2020-09-07","arxiv_id":"2009.03092","repositories_listed":3,"syntology":null},{"url":"/paper/automatic-speech-recognition-benchmark-for","slug":"automatic-speech-recognition-benchmark-for","title":"Automatic Speech Recognition Benchmark for Air-Traffic Communications","date":"2020-06-18","arxiv_id":"2006.10304","repositories_listed":3,"syntology":null},{"url":"/paper/distilling-knowledge-from-ensembles-of","slug":"distilling-knowledge-from-ensembles-of","title":"Distilling Knowledge from Ensembles of Acoustic Models for Joint CTC-Attention End-to-End Speech Recognition","date":"2020-05-19","arxiv_id":"2005.09310","repositories_listed":3,"syntology":null},{"url":"/paper/speech-recognition-and-multi-speaker","slug":"speech-recognition-and-multi-speaker","title":"Speech Recognition and Multi-Speaker Diarization of Long Conversations","date":"2020-05-16","arxiv_id":"2005.08072","repositories_listed":3,"syntology":null},{"url":"/paper/macsen-a-voice-assistant-for-speakers-of-a","slug":"macsen-a-voice-assistant-for-speakers-of-a","title":"Macsen: A Voice Assistant for Speakers of a Lesser Resourced Language","date":"2020-05-01","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/unsupervised-pretraining-transfers-well","slug":"unsupervised-pretraining-transfers-well","title":"Unsupervised pretraining transfers well across languages","date":"2020-02-07","arxiv_id":"2002.02848","repositories_listed":3,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/unsupervised-pretraining-transfers-well#ran","syntology_url":"https://syntology.ai/paper/2002.02848","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.02848"}},"official":{"repos":["facebookresearch/CPC_audio"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/non-intrusive-load-monitoring-with-an","slug":"non-intrusive-load-monitoring-with-an","title":"Improving Non-Intrusive Load Disaggregation through an Attention-Based Deep Neural Network","date":"2019-11-15","arxiv_id":"1912.00759","repositories_listed":3,"syntology":null},{"url":"/paper/espnet-tts-unified-reproducible-and","slug":"espnet-tts-unified-reproducible-and","title":"ESPnet-TTS: Unified, Reproducible, and Integratable Open Source End-to-End Text-to-Speech Toolkit","date":"2019-10-24","arxiv_id":"1910.10909","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/espnet-tts-unified-reproducible-and#ran","syntology_url":"https://syntology.ai/paper/1910.10909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.10909"}},"official":{"repos":["r9y9/wavenet_vocoder","espnet/espnet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/vq-wav2vec-self-supervised-learning-of-1","slug":"vq-wav2vec-self-supervised-learning-of-1","title":"vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations","date":"2019-10-12","arxiv_id":"1910.05453","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/vq-wav2vec-self-supervised-learning-of-1#ran","syntology_url":"https://syntology.ai/paper/1910.05453","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.05453"}},"official":null}},{"url":"/paper/stochastic-gradient-methods-with-layer-wise","slug":"stochastic-gradient-methods-with-layer-wise","title":"Stochastic Gradient Methods with Layer-wise Adaptive Moments for Training of Deep Networks","date":"2019-05-27","arxiv_id":"1905.11286","repositories_listed":3,"syntology":{"n":16,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/stochastic-gradient-methods-with-layer-wise#ran","syntology_url":"https://syntology.ai/paper/1905.11286","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.11286"}},"official":null}},{"url":"/paper/videobert-a-joint-model-for-video-and","slug":"videobert-a-joint-model-for-video-and","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","date":"2019-04-03","arxiv_id":"1904.01766","repositories_listed":3,"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/videobert-a-joint-model-for-video-and#ran","syntology_url":"https://syntology.ai/paper/1904.01766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.01766"}},"official":null}},{"url":"/paper/model-unit-exploration-for-sequence-to","slug":"model-unit-exploration-for-sequence-to","title":"On the Choice of Modeling Unit for Sequence-to-Sequence Speech Recognition","date":"2019-02-05","arxiv_id":"1902.01955","repositories_listed":3,"syntology":null},{"url":"/paper/pansori-asr-corpus-generation-from-open","slug":"pansori-asr-corpus-generation-from-open","title":"Pansori: ASR Corpus Generation from Open Online Video Contents","date":"2018-12-23","arxiv_id":"1812.09798","repositories_listed":3,"syntology":null},{"url":"/paper/improved-speech-enhancement-with-the-wave-u","slug":"improved-speech-enhancement-with-the-wave-u","title":"Improved Speech Enhancement with the Wave-U-Net","date":"2018-11-27","arxiv_id":"1811.11307","repositories_listed":3,"syntology":null},{"url":"/paper/learning-to-detect-dysarthria-from-raw-speech","slug":"learning-to-detect-dysarthria-from-raw-speech","title":"Learning to detect dysarthria from raw speech","date":"2018-11-27","arxiv_id":"1811.11101","repositories_listed":3,"syntology":null},{"url":"/paper/attention-based-audio-visual-fusion-for","slug":"attention-based-audio-visual-fusion-for","title":"Attention-based Audio-Visual Fusion for Robust Automatic Speech Recognition","date":"2018-09-05","arxiv_id":"1809.01728","repositories_listed":3,"syntology":null},{"url":"/paper/big-little-net-an-efficient-multi-scale","slug":"big-little-net-an-efficient-multi-scale","title":"Big-Little Net: An Efficient Multi-Scale Feature Representation for Visual and Speech Recognition","date":"2018-07-10","arxiv_id":"1807.03848","repositories_listed":3,"syntology":null},{"url":"/paper/quaternion-recurrent-neural-networks","slug":"quaternion-recurrent-neural-networks","title":"Quaternion Recurrent Neural Networks","date":"2018-06-12","arxiv_id":"1806.04418","repositories_listed":3,"syntology":null},{"url":"/paper/mixed-precision-training-for-nlp-and-speech","slug":"mixed-precision-training-for-nlp-and-speech","title":"Mixed-Precision Training for NLP and Speech Recognition with OpenSeq2Seq","date":"2018-05-25","arxiv_id":"1805.10387","repositories_listed":3,"syntology":null},{"url":"/paper/returnn-as-a-generic-flexible-neural-toolkit","slug":"returnn-as-a-generic-flexible-neural-toolkit","title":"RETURNN as a Generic Flexible Neural Toolkit with Application to Translation and Speech Recognition","date":"2018-05-14","arxiv_id":"1805.05225","repositories_listed":3,"syntology":null},{"url":"/paper/ted-lium-3-twice-as-much-data-and-corpus","slug":"ted-lium-3-twice-as-much-data-and-corpus","title":"TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptation","date":"2018-05-12","arxiv_id":"1805.04699","repositories_listed":3,"syntology":null},{"url":"/paper/spoken-squad-a-study-of-mitigating-the-impact","slug":"spoken-squad-a-study-of-mitigating-the-impact","title":"Spoken SQuAD: A Study of Mitigating the Impact of Speech Recognition Errors on Listening Comprehension","date":"2018-04-01","arxiv_id":"1804.00320","repositories_listed":3,"syntology":null},{"url":"/paper/a-deep-relevance-matching-model-for-ad-hoc","slug":"a-deep-relevance-matching-model-for-ad-hoc","title":"A Deep Relevance Matching Model for Ad-hoc Retrieval","date":"2017-11-23","arxiv_id":"1711.08611","repositories_listed":3,"syntology":null},{"url":"/paper/unsupervised-learning-of-disentangled-and","slug":"unsupervised-learning-of-disentangled-and","title":"Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data","date":"2017-09-22","arxiv_id":"1709.07902","repositories_listed":3,"syntology":null},{"url":"/paper/transfer-learning-for-speech-recognition-on-a","slug":"transfer-learning-for-speech-recognition-on-a","title":"Transfer Learning for Speech Recognition on a Budget","date":"2017-06-01","arxiv_id":"1706.00290","repositories_listed":3,"syntology":null},{"url":"/paper/residual-lstm-design-of-a-deep-recurrent","slug":"residual-lstm-design-of-a-deep-recurrent","title":"Residual LSTM: Design of a Deep Recurrent Architecture for Distant Speech Recognition","date":"2017-01-10","arxiv_id":"1701.03360","repositories_listed":3,"syntology":null},{"url":"/paper/mambattention-mamba-with-multi-head-attention","slug":"mambattention-mamba-with-multi-head-attention","title":"MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech Enhancement","date":"2025-07-01","arxiv_id":"2507.00966","repositories_listed":2,"syntology":null},{"url":"/paper/cosyvoice-3-towards-in-the-wild-speech","slug":"cosyvoice-3-towards-in-the-wild-speech","title":"CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training","date":"2025-05-23","arxiv_id":"2505.17589","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/cosyvoice-3-towards-in-the-wild-speech#ran","syntology_url":"https://syntology.ai/paper/2505.17589","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.17589"}},"official":{"repos":["funaudiollm/cosyvoice"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/whisper-lm-improving-asr-models-with-language","slug":"whisper-lm-improving-asr-models-with-language","title":"Whisper-LM: Improving ASR Models with Language Models for Low-Resource Languages","date":"2025-03-30","arxiv_id":"2503.23542","repositories_listed":2,"syntology":null},{"url":"/paper/emg2qwerty-a-large-dataset-with-baselines-for","slug":"emg2qwerty-a-large-dataset-with-baselines-for","title":"emg2qwerty: A Large Dataset with Baselines for Touch Typing using Surface Electromyography","date":"2024-10-26","arxiv_id":"2410.20081","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/emg2qwerty-a-large-dataset-with-baselines-for#ran","syntology_url":"https://syntology.ai/paper/2410.20081","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.20081"}},"official":{"repos":["facebookresearch/emg2qwerty"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/ichigo-mixed-modal-early-fusion-realtime","slug":"ichigo-mixed-modal-early-fusion-realtime","title":"Ichigo: Mixed-Modal Early-Fusion Realtime Voice Assistant","date":"2024-10-20","arxiv_id":"2410.15316","repositories_listed":2,"syntology":null},{"url":"/paper/recent-advances-in-speech-language-models-a","slug":"recent-advances-in-speech-language-models-a","title":"Recent Advances in Speech Language Models: A Survey","date":"2024-10-01","arxiv_id":"2410.03751","repositories_listed":2,"syntology":null},{"url":"/paper/vhasr-a-multimodal-speech-recognition-system","slug":"vhasr-a-multimodal-speech-recognition-system","title":"VHASR: A Multimodal Speech Recognition System With Vision Hotwords","date":"2024-10-01","arxiv_id":"2410.00822","repositories_listed":2,"syntology":null},{"url":"/paper/whisperner-unified-open-named-entity-and","slug":"whisperner-unified-open-named-entity-and","title":"WhisperNER: Unified Open Named Entity and Speech Recognition","date":"2024-09-12","arxiv_id":"2409.08107","repositories_listed":2,"syntology":null},{"url":"/paper/2407-21054","slug":"2407-21054","title":"Sentiment Reasoning for Healthcare","date":"2024-07-24","arxiv_id":"2407.21054","repositories_listed":2,"syntology":null},{"url":"/paper/text-based-detection-of-on-hold-scripts-in","slug":"text-based-detection-of-on-hold-scripts-in","title":"Text-Based Detection of On-Hold Scripts in Contact Center Calls","date":"2024-07-13","arxiv_id":"2407.09849","repositories_listed":2,"syntology":null},{"url":"/paper/pretraining-end-to-end-keyword-search-with","slug":"pretraining-end-to-end-keyword-search-with","title":"Pretraining End-to-End Keyword Search with Automatically Discovered Acoustic Units","date":"2024-07-05","arxiv_id":"2407.04652","repositories_listed":2,"syntology":null},{"url":"/paper/gigaspeech-2-an-evolving-large-scale-and","slug":"gigaspeech-2-an-evolving-large-scale-and","title":"GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement","date":"2024-06-17","arxiv_id":"2406.11546","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/gigaspeech-2-an-evolving-large-scale-and#ran","syntology_url":"https://syntology.ai/paper/2406.11546","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11546"}},"official":{"repos":["SpeechColab/GigaSpeech2"],"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/diarizationlm-speaker-diarization-post","slug":"diarizationlm-speaker-diarization-post","title":"DiarizationLM: Speaker Diarization Post-Processing with Large Language Models","date":"2024-01-07","arxiv_id":"2401.03506","repositories_listed":2,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/diarizationlm-speaker-diarization-post#ran","syntology_url":"https://syntology.ai/paper/2401.03506","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.03506"}},"official":{"repos":["google/speaker-id"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}}],"syntology_records":34,"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":162,"papers_where_code_ran_first_page":"/task/speech-recognition-1/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":58,"url":"/task/speech-recognition-1/papers/2","json":"/task/speech-recognition-1/papers/2.json","rows":100},{"order":"archive","page":3,"of":58,"url":"/task/speech-recognition-1/papers/3","json":"/task/speech-recognition-1/papers/3.json","rows":100},{"order":"archive","page":4,"of":58,"url":"/task/speech-recognition-1/papers/4","json":"/task/speech-recognition-1/papers/4.json","rows":100},{"order":"archive","page":5,"of":58,"url":"/task/speech-recognition-1/papers/5","json":"/task/speech-recognition-1/papers/5.json","rows":100},{"order":"archive","page":6,"of":58,"url":"/task/speech-recognition-1/papers/6","json":"/task/speech-recognition-1/papers/6.json","rows":100},{"order":"archive","page":7,"of":58,"url":"/task/speech-recognition-1/papers/7","json":"/task/speech-recognition-1/papers/7.json","rows":100},{"order":"archive","page":8,"of":58,"url":"/task/speech-recognition-1/papers/8","json":"/task/speech-recognition-1/papers/8.json","rows":100},{"order":"archive","page":9,"of":58,"url":"/task/speech-recognition-1/papers/9","json":"/task/speech-recognition-1/papers/9.json","rows":100},{"order":"archive","page":10,"of":58,"url":"/task/speech-recognition-1/papers/10","json":"/task/speech-recognition-1/papers/10.json","rows":100},{"order":"archive","page":11,"of":58,"url":"/task/speech-recognition-1/papers/11","json":"/task/speech-recognition-1/papers/11.json","rows":100},{"order":"archive","page":12,"of":58,"url":"/task/speech-recognition-1/papers/12","json":"/task/speech-recognition-1/papers/12.json","rows":100},{"order":"archive","page":13,"of":58,"url":"/task/speech-recognition-1/papers/13","json":"/task/speech-recognition-1/papers/13.json","rows":100},{"order":"archive","page":14,"of":58,"url":"/task/speech-recognition-1/papers/14","json":"/task/speech-recognition-1/papers/14.json","rows":100},{"order":"archive","page":15,"of":58,"url":"/task/speech-recognition-1/papers/15","json":"/task/speech-recognition-1/papers/15.json","rows":100},{"order":"archive","page":16,"of":58,"url":"/task/speech-recognition-1/papers/16","json":"/task/speech-recognition-1/papers/16.json","rows":100},{"order":"archive","page":17,"of":58,"url":"/task/speech-recognition-1/papers/17","json":"/task/speech-recognition-1/papers/17.json","rows":100},{"order":"archive","page":18,"of":58,"url":"/task/speech-recognition-1/papers/18","json":"/task/speech-recognition-1/papers/18.json","rows":100},{"order":"archive","page":19,"of":58,"url":"/task/speech-recognition-1/papers/19","json":"/task/speech-recognition-1/papers/19.json","rows":100},{"order":"archive","page":20,"of":58,"url":"/task/speech-recognition-1/papers/20","json":"/task/speech-recognition-1/papers/20.json","rows":100},{"order":"archive","page":21,"of":58,"url":"/task/speech-recognition-1/papers/21","json":"/task/speech-recognition-1/papers/21.json","rows":100},{"order":"archive","page":22,"of":58,"url":"/task/speech-recognition-1/papers/22","json":"/task/speech-recognition-1/papers/22.json","rows":100},{"order":"archive","page":23,"of":58,"url":"/task/speech-recognition-1/papers/23","json":"/task/speech-recognition-1/papers/23.json","rows":100},{"order":"archive","page":24,"of":58,"url":"/task/speech-recognition-1/papers/24","json":"/task/speech-recognition-1/papers/24.json","rows":100},{"order":"archive","page":25,"of":58,"url":"/task/speech-recognition-1/papers/25","json":"/task/speech-recognition-1/papers/25.json","rows":100},{"order":"archive","page":26,"of":58,"url":"/task/speech-recognition-1/papers/26","json":"/task/speech-recognition-1/papers/26.json","rows":100},{"order":"archive","page":27,"of":58,"url":"/task/speech-recognition-1/papers/27","json":"/task/speech-recognition-1/papers/27.json","rows":100},{"order":"archive","page":28,"of":58,"url":"/task/speech-recognition-1/papers/28","json":"/task/speech-recognition-1/papers/28.json","rows":100},{"order":"archive","page":29,"of":58,"url":"/task/speech-recognition-1/papers/29","json":"/task/speech-recognition-1/papers/29.json","rows":100},{"order":"archive","page":30,"of":58,"url":"/task/speech-recognition-1/papers/30","json":"/task/speech-recognition-1/papers/30.json","rows":100},{"order":"archive","page":31,"of":58,"url":"/task/speech-recognition-1/papers/31","json":"/task/speech-recognition-1/papers/31.json","rows":100},{"order":"archive","page":32,"of":58,"url":"/task/speech-recognition-1/papers/32","json":"/task/speech-recognition-1/papers/32.json","rows":100},{"order":"archive","page":33,"of":58,"url":"/task/speech-recognition-1/papers/33","json":"/task/speech-recognition-1/papers/33.json","rows":100},{"order":"archive","page":34,"of":58,"url":"/task/speech-recognition-1/papers/34","json":"/task/speech-recognition-1/papers/34.json","rows":100},{"order":"archive","page":35,"of":58,"url":"/task/speech-recognition-1/papers/35","json":"/task/speech-recognition-1/papers/35.json","rows":100},{"order":"archive","page":36,"of":58,"url":"/task/speech-recognition-1/papers/36","json":"/task/speech-recognition-1/papers/36.json","rows":100},{"order":"archive","page":37,"of":58,"url":"/task/speech-recognition-1/papers/37","json":"/task/speech-recognition-1/papers/37.json","rows":100},{"order":"archive","page":38,"of":58,"url":"/task/speech-recognition-1/papers/38","json":"/task/speech-recognition-1/papers/38.json","rows":100},{"order":"archive","page":39,"of":58,"url":"/task/speech-recognition-1/papers/39","json":"/task/speech-recognition-1/papers/39.json","rows":100},{"order":"archive","page":40,"of":58,"url":"/task/speech-recognition-1/papers/40","json":"/task/speech-recognition-1/papers/40.json","rows":100},{"order":"archive","page":41,"of":58,"url":"/task/speech-recognition-1/papers/41","json":"/task/speech-recognition-1/papers/41.json","rows":100},{"order":"archive","page":42,"of":58,"url":"/task/speech-recognition-1/papers/42","json":"/task/speech-recognition-1/papers/42.json","rows":100},{"order":"archive","page":43,"of":58,"url":"/task/speech-recognition-1/papers/43","json":"/task/speech-recognition-1/papers/43.json","rows":100},{"order":"archive","page":44,"of":58,"url":"/task/speech-recognition-1/papers/44","json":"/task/speech-recognition-1/papers/44.json","rows":100},{"order":"archive","page":45,"of":58,"url":"/task/speech-recognition-1/papers/45","json":"/task/speech-recognition-1/papers/45.json","rows":100},{"order":"archive","page":46,"of":58,"url":"/task/speech-recognition-1/papers/46","json":"/task/speech-recognition-1/papers/46.json","rows":100},{"order":"archive","page":47,"of":58,"url":"/task/speech-recognition-1/papers/47","json":"/task/speech-recognition-1/papers/47.json","rows":100},{"order":"archive","page":48,"of":58,"url":"/task/speech-recognition-1/papers/48","json":"/task/speech-recognition-1/papers/48.json","rows":100},{"order":"archive","page":49,"of":58,"url":"/task/speech-recognition-1/papers/49","json":"/task/speech-recognition-1/papers/49.json","rows":100},{"order":"archive","page":50,"of":58,"url":"/task/speech-recognition-1/papers/50","json":"/task/speech-recognition-1/papers/50.json","rows":100},{"order":"archive","page":51,"of":58,"url":"/task/speech-recognition-1/papers/51","json":"/task/speech-recognition-1/papers/51.json","rows":100},{"order":"archive","page":52,"of":58,"url":"/task/speech-recognition-1/papers/52","json":"/task/speech-recognition-1/papers/52.json","rows":100},{"order":"archive","page":53,"of":58,"url":"/task/speech-recognition-1/papers/53","json":"/task/speech-recognition-1/papers/53.json","rows":100},{"order":"archive","page":54,"of":58,"url":"/task/speech-recognition-1/papers/54","json":"/task/speech-recognition-1/papers/54.json","rows":100},{"order":"archive","page":55,"of":58,"url":"/task/speech-recognition-1/papers/55","json":"/task/speech-recognition-1/papers/55.json","rows":100},{"order":"archive","page":56,"of":58,"url":"/task/speech-recognition-1/papers/56","json":"/task/speech-recognition-1/papers/56.json","rows":100},{"order":"archive","page":57,"of":58,"url":"/task/speech-recognition-1/papers/57","json":"/task/speech-recognition-1/papers/57.json","rows":100},{"order":"archive","page":58,"of":58,"url":"/task/speech-recognition-1/papers/58","json":"/task/speech-recognition-1/papers/58.json","rows":15},{"order":"ran","page":1,"of":2,"url":"/task/speech-recognition-1/papers/ran/1","json":"/task/speech-recognition-1/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":2,"url":"/task/speech-recognition-1/papers/ran/2","json":"/task/speech-recognition-1/papers/ran/2.json","rows":62}],"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":"abf8eb5b51bfaf0930e4a9ed1c4ff613dc5e629ae485faed757b28752fc1df6f","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}