{"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/automatic-speech-recognition-2","name":"Automatic Speech Recognition","slug":"automatic-speech-recognition-2","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":3174,"papers_with_code":677,"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":22,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/mnist","name":"MNIST","full_name":"","num_papers_in_archive":7651},{"url":"/dataset/librispeech","name":"LibriSpeech","full_name":"","num_papers_in_archive":2361},{"url":"/dataset/common-voice","name":"Common Voice","full_name":"Common Voice","num_papers_in_archive":449},{"url":"/dataset/ljspeech","name":"LJSpeech","full_name":"The LJ Speech Dataset","num_papers_in_archive":323},{"url":"/dataset/fleurs","name":"FLEURS","full_name":"Few-shot Learning Evaluation of Universal Representations of Speech","num_papers_in_archive":141},{"url":"/dataset/voxpopuli","name":"VoxPopuli","full_name":"","num_papers_in_archive":113},{"url":"/dataset/gigaspeech","name":"GigaSpeech","full_name":"","num_papers_in_archive":87},{"url":"/dataset/multilingual-librispeech","name":"Multilingual LibriSpeech","full_name":"MLS","num_papers_in_archive":77},{"url":"/dataset/ted-lium-3","name":"TED-LIUM","full_name":"","num_papers_in_archive":64},{"url":"/dataset/spgispeech","name":"SPGISpeech","full_name":"","num_papers_in_archive":16},{"url":"/dataset/callhome-american-english-speech","name":"CALLHOME American English Speech","full_name":"","num_papers_in_archive":11},{"url":"/dataset/earnings-22","name":"Earnings-22","full_name":"","num_papers_in_archive":10},{"url":"/dataset/italic","name":"ITALIC","full_name":"ITALIC","num_papers_in_archive":4},{"url":"/dataset/multimed","name":"MultiMed","full_name":"","num_papers_in_archive":3},{"url":"/dataset/jam-alt","name":"Jam-ALT","full_name":"JamALT: A Formatting-Aware Lyrics Transcription Benchmark","num_papers_in_archive":2},{"url":"/dataset/msc","name":"MSC","full_name":null,"num_papers_in_archive":2},{"url":"/dataset/npsc","name":"NPSC","full_name":"Norwegian Parliamentary Speech Corpus","num_papers_in_archive":2},{"url":"/dataset/openslr","name":"OpenSLR","full_name":"Open Speech and Language Resources","num_papers_in_archive":2},{"url":"/dataset/berst","name":"BERSt","full_name":"Basic Emotion Random phrase Shouts","num_papers_in_archive":1},{"url":"/dataset/masc","name":"MASC","full_name":"Manually Annotated Sub-Corpus","num_papers_in_archive":1},{"url":"/dataset/medibeng","name":"MediBeng","full_name":"Synthetic Code-Switched Bengali-English Speech Conversations for Healthcare Applications","num_papers_in_archive":1},{"url":"/dataset/storytelling-video-dataset","name":"Video Dataset","full_name":"Storytelling Video Dataset (Russian, Emotion, Gesture, Speech)","num_papers_in_archive":0}],"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":32,"rows_per_page":100,"shown":100,"of":3174,"of_with_code":677,"tagged_in_all":3174,"counts":{"archive_papers_tagged":3174,"with_a_code_link":677,"where_syntology_ran_a_sample":79,"not_listed_spam_title":0,"listed":3174,"listed_where_code_ran":79,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":61,"every_run_a_failure_of_syntologys_instrument":18,"listed_with_a_run_with_no_instrument_failure":61,"listed_every_run_a_failure_of_syntologys_instrument":18,"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/speech-commands-a-dataset-for-limited","slug":"speech-commands-a-dataset-for-limited","title":"Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition","date":"2018-04-09","arxiv_id":"1804.03209","repositories_listed":35,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/speech-commands-a-dataset-for-limited#ran","syntology_url":"https://syntology.ai/paper/1804.03209","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.03209"}},"official":null}},{"url":"/paper/specaugment-a-simple-data-augmentation-method","slug":"specaugment-a-simple-data-augmentation-method","title":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition","date":"2019-04-18","arxiv_id":"1904.08779","repositories_listed":30,"syntology":{"n":18,"n_ran":14,"n_constructed":0,"n_ran_checked":13,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":0,"phrase":"14 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; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/specaugment-a-simple-data-augmentation-method#ran","syntology_url":"https://syntology.ai/paper/1904.08779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.08779"}},"official":null}},{"url":"/paper/conformer-convolution-augmented-transformer","slug":"conformer-convolution-augmented-transformer","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","date":"2020-05-16","arxiv_id":"2005.08100","repositories_listed":25,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":3,"n_no_contract":2,"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, 3 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/conformer-convolution-augmented-transformer#ran","syntology_url":"https://syntology.ai/paper/2005.08100","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.08100"}},"official":null}},{"url":"/paper/snips-voice-platform-an-embedded-spoken","slug":"snips-voice-platform-an-embedded-spoken","title":"Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces","date":"2018-05-25","arxiv_id":"1805.10190","repositories_listed":16,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"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) · 2 unverified","sample_list":"/paper/snips-voice-platform-an-embedded-spoken#ran","syntology_url":"https://syntology.ai/paper/1805.10190","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.10190"}},"official":{"repos":["snipsco/nlu-benchmark","snipsco/snips-nlu"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/a-baseline-for-detecting-misclassified-and","slug":"a-baseline-for-detecting-misclassified-and","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","date":"2016-10-07","arxiv_id":"1610.02136","repositories_listed":14,"syntology":{"n":21,"n_ran":19,"n_constructed":0,"n_ran_checked":16,"n_instrument":3,"n_unverified":2,"n_honours":4,"n_violates":0,"n_no_contract":12,"n_pointer_only":6,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 4 honoured, 0 violated, 12 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-baseline-for-detecting-misclassified-and#ran","syntology_url":"https://syntology.ai/paper/1610.02136","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1610.02136"}},"official":{"repos":["hendrycks/error-detection"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"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/advances-in-joint-ctc-attention-based-end-to","slug":"advances-in-joint-ctc-attention-based-end-to","title":"Advances in Joint CTC-Attention based End-to-End Speech Recognition with a Deep CNN Encoder and RNN-LM","date":"2017-06-08","arxiv_id":"1706.02737","repositories_listed":6,"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/seamlessm4t-massively-multilingual-multimodal","slug":"seamlessm4t-massively-multilingual-multimodal","title":"SeamlessM4T: Massively Multilingual & Multimodal Machine Translation","date":"2023-08-22","arxiv_id":"2308.11596","repositories_listed":4,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/seamlessm4t-massively-multilingual-multimodal#ran","syntology_url":"https://syntology.ai/paper/2308.11596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.11596"}},"official":{"repos":["facebookresearch/seamless_communication"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/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/squeezeformer-an-efficient-transformer-for","slug":"squeezeformer-an-efficient-transformer-for","title":"Squeezeformer: An Efficient Transformer for Automatic Speech Recognition","date":"2022-06-02","arxiv_id":"2206.00888","repositories_listed":4,"syntology":{"n":49,"n_ran":31,"n_constructed":12,"n_ran_checked":28,"n_instrument":3,"n_unverified":18,"n_honours":3,"n_violates":0,"n_no_contract":25,"n_pointer_only":0,"phrase":"31 ran (of which 12 constructed an object rather than computing a result; 28 with no instrument failure: 3 honoured, 0 violated, 25 with no contract checked; 3 where Syntology's instrument failed) · 18 unverified","sample_list":"/paper/squeezeformer-an-efficient-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2206.00888","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.00888"}},"official":{"repos":["kssteven418/squeezeformer"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":10,"ran_from_kinds":["listed","official"]}}},{"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/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/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/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/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-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/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/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/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/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/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/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/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/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/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/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/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/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/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/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"]}}},{"url":"/paper/automatic-disfluency-detection-from","slug":"automatic-disfluency-detection-from","title":"Automatic Disfluency Detection from Untranscribed Speech","date":"2023-11-01","arxiv_id":"2311.00867","repositories_listed":2,"syntology":null},{"url":"/paper/lauragpt-listen-attend-understand-and","slug":"lauragpt-listen-attend-understand-and","title":"LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT","date":"2023-10-07","arxiv_id":"2310.04673","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lauragpt-listen-attend-understand-and#ran","syntology_url":"https://syntology.ai/paper/2310.04673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04673"}},"official":null}},{"url":"/paper/librispeech-pc-benchmark-for-evaluation-of","slug":"librispeech-pc-benchmark-for-evaluation-of","title":"LibriSpeech-PC: Benchmark for Evaluation of Punctuation and Capitalization Capabilities of end-to-end ASR Models","date":"2023-10-04","arxiv_id":"2310.02943","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/librispeech-pc-benchmark-for-evaluation-of#ran","syntology_url":"https://syntology.ai/paper/2310.02943","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.02943"}},"official":null}},{"url":"/paper/encodecmae-leveraging-neural-codecs-for","slug":"encodecmae-leveraging-neural-codecs-for","title":"EnCodecMAE: Leveraging neural codecs for universal audio representation learning","date":"2023-09-14","arxiv_id":"2309.07391","repositories_listed":2,"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/encodecmae-leveraging-neural-codecs-for#ran","syntology_url":"https://syntology.ai/paper/2309.07391","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.07391"}},"official":{"repos":["habla-liaa/encodecmae"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/promptasr-for-contextualized-asr-with","slug":"promptasr-for-contextualized-asr-with","title":"PromptASR for contextualized ASR with controllable style","date":"2023-09-14","arxiv_id":"2309.07414","repositories_listed":2,"syntology":null},{"url":"/paper/conformer-based-target-speaker-automatic","slug":"conformer-based-target-speaker-automatic","title":"Conformer-based Target-Speaker Automatic Speech Recognition for Single-Channel Audio","date":"2023-08-09","arxiv_id":"2308.05218","repositories_listed":2,"syntology":null},{"url":"/paper/learning-multi-modal-representations-by","slug":"learning-multi-modal-representations-by","title":"Learning Multi-modal Representations by Watching Hundreds of Surgical Video Lectures","date":"2023-07-27","arxiv_id":"2307.15220","repositories_listed":2,"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/learning-multi-modal-representations-by#ran","syntology_url":"https://syntology.ai/paper/2307.15220","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.15220"}},"official":{"repos":["camma-public/peskavlp","camma-public/surgvlp"],"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/quilt-1m-one-million-image-text-pairs-for-1","slug":"quilt-1m-one-million-image-text-pairs-for-1","title":"Quilt-1M: One Million Image-Text Pairs for Histopathology","date":"2023-06-20","arxiv_id":"2306.11207","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/quilt-1m-one-million-image-text-pairs-for-1#ran","syntology_url":"https://syntology.ai/paper/2306.11207","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.11207"}},"official":{"repos":["wisdomikezogwo/quilt1m"],"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"]}}},{"url":"/paper/unit-based-speech-to-speech-translation","slug":"unit-based-speech-to-speech-translation","title":"Textless Speech-to-Speech Translation With Limited Parallel Data","date":"2023-05-24","arxiv_id":"2305.15405","repositories_listed":2,"syntology":null},{"url":"/paper/a-comparative-study-on-e-branchformer-vs","slug":"a-comparative-study-on-e-branchformer-vs","title":"A Comparative Study on E-Branchformer vs Conformer in Speech Recognition, Translation, and Understanding Tasks","date":"2023-05-18","arxiv_id":"2305.11073","repositories_listed":2,"syntology":null},{"url":"/paper/reproducibility-is-nothing-without","slug":"reproducibility-is-nothing-without","title":"When Good and Reproducible Results are a Giant with Feet of Clay: The Importance of Software Quality in NLP","date":"2023-03-28","arxiv_id":"2303.16166","repositories_listed":2,"syntology":null},{"url":"/paper/auto-avsr-audio-visual-speech-recognition","slug":"auto-avsr-audio-visual-speech-recognition","title":"Auto-AVSR: Audio-Visual Speech Recognition with Automatic Labels","date":"2023-03-25","arxiv_id":"2303.14307","repositories_listed":2,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"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/auto-avsr-audio-visual-speech-recognition#ran","syntology_url":"https://syntology.ai/paper/2303.14307","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.14307"}},"official":{"repos":["mpc001/auto_avsr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/knowledge-transfer-from-pre-trained-language","slug":"knowledge-transfer-from-pre-trained-language","title":"Knowledge Transfer from Pre-trained Language Models to Cif-based Speech Recognizers via Hierarchical Distillation","date":"2023-01-30","arxiv_id":"2301.13003","repositories_listed":2,"syntology":null},{"url":"/paper/unsupervised-data-selection-for-tts-using","slug":"unsupervised-data-selection-for-tts-using","title":"Unsupervised Data Selection for TTS: Using Arabic Broadcast News as a Case Study","date":"2023-01-22","arxiv_id":"2301.09099","repositories_listed":2,"syntology":null},{"url":"/paper/a-persian-asr-based-ser-modification-of","slug":"a-persian-asr-based-ser-modification-of","title":"A Persian ASR-based SER: Modification of Sharif Emotional Speech Database and Investigation of Persian Text Corpora","date":"2022-11-18","arxiv_id":"2211.09956","repositories_listed":2,"syntology":null},{"url":"/paper/esb-a-benchmark-for-multi-domain-end-to-end","slug":"esb-a-benchmark-for-multi-domain-end-to-end","title":"ESB: A Benchmark For Multi-Domain End-to-End Speech Recognition","date":"2022-10-24","arxiv_id":"2210.13352","repositories_listed":2,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/esb-a-benchmark-for-multi-domain-end-to-end#ran","syntology_url":"https://syntology.ai/paper/2210.13352","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.13352"}},"official":null}},{"url":"/paper/speechut-bridging-speech-and-text-with-hidden","slug":"speechut-bridging-speech-and-text-with-hidden","title":"SpeechUT: Bridging Speech and Text with Hidden-Unit for Encoder-Decoder Based Speech-Text Pre-training","date":"2022-10-07","arxiv_id":"2210.03730","repositories_listed":2,"syntology":null},{"url":"/paper/cmgan-conformer-based-metric-gan-for-monaural","slug":"cmgan-conformer-based-metric-gan-for-monaural","title":"CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancement","date":"2022-09-22","arxiv_id":"2209.11112","repositories_listed":2,"syntology":null},{"url":"/paper/improving-mandarin-speech-recogntion-with","slug":"improving-mandarin-speech-recogntion-with","title":"Improving Mandarin Speech Recogntion with Block-augmented Transformer","date":"2022-07-24","arxiv_id":"2207.11697","repositories_listed":2,"syntology":null},{"url":"/paper/soundspaces-2-0-a-simulation-platform-for","slug":"soundspaces-2-0-a-simulation-platform-for","title":"SoundSpaces 2.0: A Simulation Platform for Visual-Acoustic Learning","date":"2022-06-16","arxiv_id":"2206.08312","repositories_listed":2,"syntology":null},{"url":"/paper/how-does-pre-trained-wav2vec2-0-perform-on","slug":"how-does-pre-trained-wav2vec2-0-perform-on","title":"How Does Pre-trained Wav2Vec 2.0 Perform on Domain Shifted ASR? An Extensive Benchmark on Air Traffic Control Communications","date":"2022-03-31","arxiv_id":"2203.16822","repositories_listed":2,"syntology":null},{"url":"/paper/listen-adapt-better-wer-source-free-single","slug":"listen-adapt-better-wer-source-free-single","title":"Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech Recognition","date":"2022-03-27","arxiv_id":"2203.14222","repositories_listed":2,"syntology":null},{"url":"/paper/learning-audio-visual-speech-representation-1","slug":"learning-audio-visual-speech-representation-1","title":"Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction","date":"2022-01-05","arxiv_id":"2201.02184","repositories_listed":2,"syntology":null},{"url":"/paper/attention-based-multi-hypothesis-fusion-for","slug":"attention-based-multi-hypothesis-fusion-for","title":"Attention-based Multi-hypothesis Fusion for Speech Summarization","date":"2021-11-16","arxiv_id":"2111.08201","repositories_listed":2,"syntology":null},{"url":"/paper/coraa-a-large-corpus-of-spontaneous-and","slug":"coraa-a-large-corpus-of-spontaneous-and","title":"CORAA: a large corpus of spontaneous and prepared speech manually validated for speech recognition in Brazilian Portuguese","date":"2021-10-14","arxiv_id":"2110.15731","repositories_listed":2,"syntology":null},{"url":"/paper/bertraffic-a-robust-bert-based-approach-for","slug":"bertraffic-a-robust-bert-based-approach-for","title":"BERTraffic: BERT-based Joint Speaker Role and Speaker Change Detection for Air Traffic Control Communications","date":"2021-10-12","arxiv_id":"2110.05781","repositories_listed":2,"syntology":null},{"url":"/paper/interactive-feature-fusion-for-end-to-end","slug":"interactive-feature-fusion-for-end-to-end","title":"Interactive Feature Fusion for End-to-End Noise-Robust Speech Recognition","date":"2021-10-11","arxiv_id":"2110.05267","repositories_listed":2,"syntology":null},{"url":"/paper/k-wav2vec-2-0-automatic-speech-recognition","slug":"k-wav2vec-2-0-automatic-speech-recognition","title":"K-Wav2vec 2.0: Automatic Speech Recognition based on Joint Decoding of Graphemes and Syllables","date":"2021-10-11","arxiv_id":"2110.05172","repositories_listed":2,"syntology":null},{"url":"/paper/a-comparison-of-methods-for-oov-word","slug":"a-comparison-of-methods-for-oov-word","title":"A Comparison of Methods for OOV-word Recognition on a New Public Dataset","date":"2021-07-16","arxiv_id":"2107.08091","repositories_listed":2,"syntology":null},{"url":"/paper/lightweight-adapter-tuning-for-multilingual","slug":"lightweight-adapter-tuning-for-multilingual","title":"Lightweight Adapter Tuning for Multilingual Speech Translation","date":"2021-06-02","arxiv_id":"2106.01463","repositories_listed":2,"syntology":null},{"url":"/paper/fdlp-spectrogram-capturing-speech-dynamics-in","slug":"fdlp-spectrogram-capturing-speech-dynamics-in","title":"Radically Old Way of Computing Spectra: Applications in End-to-End ASR","date":"2021-03-25","arxiv_id":"2103.14129","repositories_listed":2,"syntology":null},{"url":"/paper/bembaspeech-a-speech-recognition-corpus-for","slug":"bembaspeech-a-speech-recognition-corpus-for","title":"BembaSpeech: A Speech Recognition Corpus for the Bemba Language","date":"2021-02-09","arxiv_id":"2102.04889","repositories_listed":2,"syntology":null},{"url":"/paper/a-comprehensive-evaluation-of-incremental","slug":"a-comprehensive-evaluation-of-incremental","title":"A Comprehensive Evaluation of Incremental Speech Recognition and Diarization for Conversational AI","date":"2020-12-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/decentralizing-feature-extraction-with","slug":"decentralizing-feature-extraction-with","title":"Decentralizing Feature Extraction with Quantum Convolutional Neural Network for Automatic Speech Recognition","date":"2020-10-26","arxiv_id":"2010.13309","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":2,"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/decentralizing-feature-extraction-with#ran","syntology_url":"https://syntology.ai/paper/2010.13309","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.13309"}},"official":{"repos":["huckiyang/speech_quantum_dl"],"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/representation-learning-for-sequence-data-1","slug":"representation-learning-for-sequence-data-1","title":"Representation Learning for Sequence Data with Deep Autoencoding Predictive Components","date":"2020-10-07","arxiv_id":"2010.03135","repositories_listed":2,"syntology":{"n":29,"n_ran":22,"n_constructed":0,"n_ran_checked":22,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":22,"n_pointer_only":2,"phrase":"22 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 0 honoured, 0 violated, 22 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/representation-learning-for-sequence-data-1#ran","syntology_url":"https://syntology.ai/paper/2010.03135","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.03135"}},"official":{"repos":["JunwenBai/DAPC"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed"]}}},{"url":"/paper/end-to-end-speech-recognition-and-disfluency","slug":"end-to-end-speech-recognition-and-disfluency","title":"End-to-End Speech Recognition and Disfluency Removal","date":"2020-09-22","arxiv_id":"2009.10298","repositories_listed":2,"syntology":null},{"url":"/paper/pretraining-techniques-for-sequence-to","slug":"pretraining-techniques-for-sequence-to","title":"Pretraining Techniques for Sequence-to-Sequence Voice Conversion","date":"2020-08-07","arxiv_id":"2008.03088","repositories_listed":2,"syntology":null},{"url":"/paper/common-voice-a-massively-multilingual-speech","slug":"common-voice-a-massively-multilingual-speech","title":"Common Voice: A Massively-Multilingual Speech Corpus","date":"2019-12-13","arxiv_id":"1912.06670","repositories_listed":2,"syntology":null},{"url":"/paper/cat-crf-based-asr-toolkit","slug":"cat-crf-based-asr-toolkit","title":"CAT: CRF-based ASR Toolkit","date":"2019-11-20","arxiv_id":"1911.08747","repositories_listed":2,"syntology":null},{"url":"/paper/confidence-estimation-for-black-box-automatic","slug":"confidence-estimation-for-black-box-automatic","title":"Confidence Estimation for Black Box Automatic Speech Recognition Systems Using Lattice Recurrent Neural Networks","date":"2019-10-25","arxiv_id":"1910.11933","repositories_listed":2,"syntology":null},{"url":"/paper/speech-vgg-a-deep-feature-extractor-for","slug":"speech-vgg-a-deep-feature-extractor-for","title":"Word-level Embeddings for Cross-Task Transfer Learning in Speech Processing","date":"2019-10-22","arxiv_id":"1910.09909","repositories_listed":2,"syntology":null},{"url":"/paper/a-comparative-study-on-transformer-vs-rnn-in","slug":"a-comparative-study-on-transformer-vs-rnn-in","title":"A Comparative Study on Transformer vs RNN in Speech Applications","date":"2019-09-13","arxiv_id":"1909.06317","repositories_listed":2,"syntology":null},{"url":"/paper/rwth-asr-systems-for-librispeech-hybrid-vs","slug":"rwth-asr-systems-for-librispeech-hybrid-vs","title":"RWTH ASR Systems for LibriSpeech: Hybrid vs Attention -- w/o Data Augmentation","date":"2019-05-08","arxiv_id":"1905.03072","repositories_listed":2,"syntology":null},{"url":"/paper/mitigating-the-impact-of-speech-recognition-1","slug":"mitigating-the-impact-of-speech-recognition-1","title":"Mitigating the Impact of Speech Recognition Errors on Spoken Question Answering by Adversarial Domain Adaptation","date":"2019-04-16","arxiv_id":"1904.07904","repositories_listed":2,"syntology":null},{"url":"/paper/bidirectional-quaternion-long-short-term","slug":"bidirectional-quaternion-long-short-term","title":"Bidirectional Quaternion Long-Short Term Memory Recurrent Neural Networks for Speech Recognition","date":"2018-11-06","arxiv_id":"1811.02566","repositories_listed":2,"syntology":null},{"url":"/paper/how2-a-large-scale-dataset-for-multimodal","slug":"how2-a-large-scale-dataset-for-multimodal","title":"How2: A Large-scale Dataset for Multimodal Language Understanding","date":"2018-11-01","arxiv_id":"1811.00347","repositories_listed":2,"syntology":null},{"url":"/paper/open-source-automatic-speech-recognition-for","slug":"open-source-automatic-speech-recognition-for","title":"Open Source Automatic Speech Recognition for German","date":"2018-07-26","arxiv_id":"1807.10311","repositories_listed":2,"syntology":null},{"url":"/paper/minimum-word-error-rate-training-for","slug":"minimum-word-error-rate-training-for","title":"Minimum Word Error Rate Training for Attention-based Sequence-to-Sequence Models","date":"2017-12-05","arxiv_id":"1712.01818","repositories_listed":2,"syntology":null},{"url":"/paper/single-channel-multi-speaker-separation-using","slug":"single-channel-multi-speaker-separation-using","title":"Single-Channel Multi-Speaker Separation using Deep Clustering","date":"2016-07-07","arxiv_id":"1607.02173","repositories_listed":2,"syntology":null},{"url":"/paper/splitformer-an-improved-early-exit","slug":"splitformer-an-improved-early-exit","title":"Splitformer: An improved early-exit architecture for automatic speech recognition on edge devices","date":"2025-06-22","arxiv_id":"2506.18035","repositories_listed":1,"syntology":null},{"url":"/paper/advances-in-small-footprint-keyword-spotting","slug":"advances-in-small-footprint-keyword-spotting","title":"Advances in Small-Footprint Keyword Spotting: A Comprehensive Review of Efficient Models and Algorithms","date":"2025-06-12","arxiv_id":"2506.11169","repositories_listed":1,"syntology":null}],"syntology_records":27,"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":79,"papers_where_code_ran_first_page":"/task/automatic-speech-recognition-2/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":32,"url":"/task/automatic-speech-recognition-2/papers/2","json":"/task/automatic-speech-recognition-2/papers/2.json","rows":100},{"order":"archive","page":3,"of":32,"url":"/task/automatic-speech-recognition-2/papers/3","json":"/task/automatic-speech-recognition-2/papers/3.json","rows":100},{"order":"archive","page":4,"of":32,"url":"/task/automatic-speech-recognition-2/papers/4","json":"/task/automatic-speech-recognition-2/papers/4.json","rows":100},{"order":"archive","page":5,"of":32,"url":"/task/automatic-speech-recognition-2/papers/5","json":"/task/automatic-speech-recognition-2/papers/5.json","rows":100},{"order":"archive","page":6,"of":32,"url":"/task/automatic-speech-recognition-2/papers/6","json":"/task/automatic-speech-recognition-2/papers/6.json","rows":100},{"order":"archive","page":7,"of":32,"url":"/task/automatic-speech-recognition-2/papers/7","json":"/task/automatic-speech-recognition-2/papers/7.json","rows":100},{"order":"archive","page":8,"of":32,"url":"/task/automatic-speech-recognition-2/papers/8","json":"/task/automatic-speech-recognition-2/papers/8.json","rows":100},{"order":"archive","page":9,"of":32,"url":"/task/automatic-speech-recognition-2/papers/9","json":"/task/automatic-speech-recognition-2/papers/9.json","rows":100},{"order":"archive","page":10,"of":32,"url":"/task/automatic-speech-recognition-2/papers/10","json":"/task/automatic-speech-recognition-2/papers/10.json","rows":100},{"order":"archive","page":11,"of":32,"url":"/task/automatic-speech-recognition-2/papers/11","json":"/task/automatic-speech-recognition-2/papers/11.json","rows":100},{"order":"archive","page":12,"of":32,"url":"/task/automatic-speech-recognition-2/papers/12","json":"/task/automatic-speech-recognition-2/papers/12.json","rows":100},{"order":"archive","page":13,"of":32,"url":"/task/automatic-speech-recognition-2/papers/13","json":"/task/automatic-speech-recognition-2/papers/13.json","rows":100},{"order":"archive","page":14,"of":32,"url":"/task/automatic-speech-recognition-2/papers/14","json":"/task/automatic-speech-recognition-2/papers/14.json","rows":100},{"order":"archive","page":15,"of":32,"url":"/task/automatic-speech-recognition-2/papers/15","json":"/task/automatic-speech-recognition-2/papers/15.json","rows":100},{"order":"archive","page":16,"of":32,"url":"/task/automatic-speech-recognition-2/papers/16","json":"/task/automatic-speech-recognition-2/papers/16.json","rows":100},{"order":"archive","page":17,"of":32,"url":"/task/automatic-speech-recognition-2/papers/17","json":"/task/automatic-speech-recognition-2/papers/17.json","rows":100},{"order":"archive","page":18,"of":32,"url":"/task/automatic-speech-recognition-2/papers/18","json":"/task/automatic-speech-recognition-2/papers/18.json","rows":100},{"order":"archive","page":19,"of":32,"url":"/task/automatic-speech-recognition-2/papers/19","json":"/task/automatic-speech-recognition-2/papers/19.json","rows":100},{"order":"archive","page":20,"of":32,"url":"/task/automatic-speech-recognition-2/papers/20","json":"/task/automatic-speech-recognition-2/papers/20.json","rows":100},{"order":"archive","page":21,"of":32,"url":"/task/automatic-speech-recognition-2/papers/21","json":"/task/automatic-speech-recognition-2/papers/21.json","rows":100},{"order":"archive","page":22,"of":32,"url":"/task/automatic-speech-recognition-2/papers/22","json":"/task/automatic-speech-recognition-2/papers/22.json","rows":100},{"order":"archive","page":23,"of":32,"url":"/task/automatic-speech-recognition-2/papers/23","json":"/task/automatic-speech-recognition-2/papers/23.json","rows":100},{"order":"archive","page":24,"of":32,"url":"/task/automatic-speech-recognition-2/papers/24","json":"/task/automatic-speech-recognition-2/papers/24.json","rows":100},{"order":"archive","page":25,"of":32,"url":"/task/automatic-speech-recognition-2/papers/25","json":"/task/automatic-speech-recognition-2/papers/25.json","rows":100},{"order":"archive","page":26,"of":32,"url":"/task/automatic-speech-recognition-2/papers/26","json":"/task/automatic-speech-recognition-2/papers/26.json","rows":100},{"order":"archive","page":27,"of":32,"url":"/task/automatic-speech-recognition-2/papers/27","json":"/task/automatic-speech-recognition-2/papers/27.json","rows":100},{"order":"archive","page":28,"of":32,"url":"/task/automatic-speech-recognition-2/papers/28","json":"/task/automatic-speech-recognition-2/papers/28.json","rows":100},{"order":"archive","page":29,"of":32,"url":"/task/automatic-speech-recognition-2/papers/29","json":"/task/automatic-speech-recognition-2/papers/29.json","rows":100},{"order":"archive","page":30,"of":32,"url":"/task/automatic-speech-recognition-2/papers/30","json":"/task/automatic-speech-recognition-2/papers/30.json","rows":100},{"order":"archive","page":31,"of":32,"url":"/task/automatic-speech-recognition-2/papers/31","json":"/task/automatic-speech-recognition-2/papers/31.json","rows":100},{"order":"archive","page":32,"of":32,"url":"/task/automatic-speech-recognition-2/papers/32","json":"/task/automatic-speech-recognition-2/papers/32.json","rows":74},{"order":"ran","page":1,"of":1,"url":"/task/automatic-speech-recognition-2/papers/ran/1","json":"/task/automatic-speech-recognition-2/papers/ran/1.json","rows":79}],"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":"fb4104e401a57df794dc22c1b8f88f684013451ad84444db4e27e0400d23a773","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}