{"id":"https://openalex.org/W3018441253","doi":"https://doi.org/10.21437/interspeech.2020-1074","title":"Towards a Competitive End-to-End Speech Recognition for CHiME-6 Dinner Party Transcription","display_name":"Towards a Competitive End-to-End Speech Recognition for CHiME-6 Dinner Party Transcription","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3018441253","doi":"https://doi.org/10.21437/interspeech.2020-1074","mag":"3018441253"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1074","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1074","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2004.10799","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054253945","display_name":"Andrei Andrusenko","orcid":"https://orcid.org/0000-0002-8697-832X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrei Andrusenko","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089101632","display_name":"Aleksandr Laptev","orcid":"https://orcid.org/0000-0002-4690-705X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aleksandr Laptev","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5022587932","display_name":"Ivan Medennikov","orcid":"https://orcid.org/0000-0001-5381-3433"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ivan Medennikov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0815,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.89622202,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"319","last_page":"323"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.98089998960495,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.8732789158821106},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.732414722442627},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.717144787311554},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6398802399635315},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5944793224334717},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5519853234291077},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.530817985534668},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.44205307960510254},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4095911383628845},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36004528403282166},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16366514563560486}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8732789158821106},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.732414722442627},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.717144787311554},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6398802399635315},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5944793224334717},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5519853234291077},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.530817985534668},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.44205307960510254},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4095911383628845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36004528403282166},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16366514563560486},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2020-1074","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1074","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2004.10799","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.10799","pdf_url":"https://arxiv.org/pdf/2004.10799","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2004.10799","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.10799","pdf_url":"https://arxiv.org/pdf/2004.10799","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1828163288","https://openalex.org/W2101045344","https://openalex.org/W2127141656","https://openalex.org/W2160815625","https://openalex.org/W2327501763","https://openalex.org/W2526425061","https://openalex.org/W2799800213","https://openalex.org/W2884797218","https://openalex.org/W2899867592","https://openalex.org/W2900091092","https://openalex.org/W2900212944","https://openalex.org/W2900440209","https://openalex.org/W2936774411","https://openalex.org/W2940526039","https://openalex.org/W2962784628","https://openalex.org/W2962832505","https://openalex.org/W2963403868","https://openalex.org/W2963812242","https://openalex.org/W2972818416","https://openalex.org/W2972821391","https://openalex.org/W2973049979","https://openalex.org/W2973215447","https://openalex.org/W2976556660","https://openalex.org/W2982413405","https://openalex.org/W2983061588","https://openalex.org/W2987019345","https://openalex.org/W2991213871","https://openalex.org/W3004597053","https://openalex.org/W3008762051","https://openalex.org/W3016400019","https://openalex.org/W3103005696","https://openalex.org/W3131736947"],"related_works":["https://openalex.org/W2160451571","https://openalex.org/W4288365749","https://openalex.org/W2936497627","https://openalex.org/W3013624417","https://openalex.org/W4287826556","https://openalex.org/W2916997151","https://openalex.org/W3098382480","https://openalex.org/W4287598411","https://openalex.org/W3094871513","https://openalex.org/W2495256954"],"abstract_inverted_index":{"While":[0],"end-to-end":[1,38,112,159],"ASR":[2],"systems":[3],"have":[4],"proven":[5],"competitive":[6],"with":[7,78,118],"the":[8,44,52,97,131,138,149,158],"conventional":[9],"hybrid":[10,45,150],"approach,":[11],"they":[12],"are":[13],"prone":[14],"to":[15,21,43],"accuracy":[16],"degradation":[17],"when":[18],"it":[19],"comes":[20],"noisy":[22,63],"and":[23,62,71,91,157],"low-resource":[24,108],"conditions.":[25,109],"In":[26],"this":[27,146],"paper,":[28],"we":[29,50,95],"argue":[30],"that,":[31],"even":[32],"in":[33,107],"such":[34],"difficult":[35],"cases,":[36],"some":[37],"approaches":[39,76],"show":[40],"performance":[41],"close":[42],"baseline.":[46,136],"To":[47],"demonstrate":[48],"this,":[49],"use":[51],"CHiME-6":[53,134],"Challenge":[54,135],"data":[55,144],"as":[56],"an":[57],"example":[58],"of":[59,65,88,99],"challenging":[60],"environments":[61],"conditions":[64],"everyday":[66],"speech.":[67],"We":[68,83],"experimentally":[69],"compare":[70],"analyze":[72],"CTC-Attention":[73],"versus":[74,80],"RNN-Transducer":[75],"along":[77],"RNN":[79],"Transformer":[81],"architectures.":[82],"also":[84],"provide":[85],"a":[86],"comparison":[87],"acoustic":[89],"features":[90],"speech":[92],"enhancements.":[93],"Besides,":[94],"evaluate":[96],"effectiveness":[98],"neural":[100],"network":[101],"language":[102],"models":[103],"for":[104],"hypothesis":[105],"re-scoring":[106],"Our":[110],"best":[111,161],"model":[113],"based":[114,142],"on":[115],"RNN-Transducer,":[116],"together":[117],"improved":[119],"beam":[120],"search,":[121],"reaches":[122],"quality":[123],"by":[124,153,164],"only":[125],"3.8%":[126],"WER":[127,155,166],"abs.":[128,156,167],"worse":[129],"than":[130],"LF-MMI":[132],"TDNN-F":[133],"With":[137],"Guided":[139],"Source":[140],"Separation":[141],"training":[143],"augmentation,":[145],"approach":[147],"outperforms":[148],"baseline":[151],"system":[152,160],"2.7%":[154],"known":[162],"before":[163],"25.7%":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2020-05-01T00:00:00"}