{"id":"https://openalex.org/W4312356750","doi":"https://doi.org/10.1109/taslp.2022.3209942","title":"End-to-End Dereverberation, Beamforming, and Speech Recognition in a Cocktail Party","display_name":"End-to-End Dereverberation, Beamforming, and Speech Recognition in a Cocktail Party","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4312356750","doi":"https://doi.org/10.1109/taslp.2022.3209942"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3209942","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3209942","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071937621","display_name":"Wangyou Zhang","orcid":"https://orcid.org/0000-0003-4500-3515"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wangyou Zhang","raw_affiliation_strings":["X-LANCE Lab, Department of Computer Science and Engineering and MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","X-LANCE Lab, Department of Computer Science and Engineering and MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, P. R. China"],"raw_orcid":"https://orcid.org/0000-0003-4500-3515","affiliations":[{"raw_affiliation_string":"X-LANCE Lab, Department of Computer Science and Engineering and MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"X-LANCE Lab, Department of Computer Science and Engineering and MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050058892","display_name":"Xuankai Chang","orcid":"https://orcid.org/0000-0002-5221-5412"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuankai Chang","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","Language Technologies Institute at Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5221-5412","affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute at Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064522438","display_name":"Christoph Boeddeker","orcid":"https://orcid.org/0000-0002-8701-1567"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christoph Boeddeker","raw_affiliation_strings":["Paderborn University, Paderborn, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Paderborn University, Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Corporation, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0002-7487-7150","affiliations":[{"raw_affiliation_string":"NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","Language Technologies Institute at Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5970-8631","affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute at Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["X-LANCE Lab, Department of Computer Science and Engineering and MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","X-LANCE Lab, Department of Computer Science and Engineering and MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, P. R. China"],"raw_orcid":"https://orcid.org/0000-0002-0314-3790","affiliations":[{"raw_affiliation_string":"X-LANCE Lab, Department of Computer Science and Engineering and MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"X-LANCE Lab, Department of Computer Science and Engineering and MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5452,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.9018848,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"30","issue":null,"first_page":"3173","last_page":"3188"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9986000061035156,"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/T11309","display_name":"Music and Audio Processing","score":0.998199999332428,"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/computer-science","display_name":"Computer science","score":0.8215435743331909},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7466446161270142},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.665831446647644},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6345171928405762},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6004492044448853},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5625224709510803},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.4868697226047516},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4475288987159729},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.43470126390457153},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4259517192840576},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.41743823885917664},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.41330209374427795},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4121033549308777},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4109742045402527},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2747042775154114},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11877229809761047},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.10377806425094604}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8215435743331909},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7466446161270142},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.665831446647644},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6345171928405762},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6004492044448853},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5625224709510803},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.4868697226047516},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4475288987159729},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.43470126390457153},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4259517192840576},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.41743823885917664},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.41330209374427795},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4121033549308777},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4109742045402527},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2747042775154114},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11877229809761047},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.10377806425094604},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2022.3209942","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3209942","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":84,"referenced_works":["https://openalex.org/W1536252645","https://openalex.org/W1552314771","https://openalex.org/W1555217905","https://openalex.org/W1693006369","https://openalex.org/W1978752674","https://openalex.org/W1991139021","https://openalex.org/W2004406124","https://openalex.org/W2026655013","https://openalex.org/W2041256929","https://openalex.org/W2050551142","https://openalex.org/W2060108923","https://openalex.org/W2062572859","https://openalex.org/W2066218102","https://openalex.org/W2096855653","https://openalex.org/W2127851351","https://openalex.org/W2140571699","https://openalex.org/W2141998673","https://openalex.org/W2152536723","https://openalex.org/W2152649161","https://openalex.org/W2155638623","https://openalex.org/W2164502538","https://openalex.org/W2221409856","https://openalex.org/W2283145987","https://openalex.org/W2398042854","https://openalex.org/W2460742184","https://openalex.org/W2517616541","https://openalex.org/W2526425061","https://openalex.org/W2640112133","https://openalex.org/W2734774145","https://openalex.org/W2747732471","https://openalex.org/W2750446090","https://openalex.org/W2786105640","https://openalex.org/W2795822145","https://openalex.org/W2886180730","https://openalex.org/W2889206679","https://openalex.org/W2889224938","https://openalex.org/W2890244912","https://openalex.org/W2892163332","https://openalex.org/W2897977894","https://openalex.org/W2902894493","https://openalex.org/W2905402910","https://openalex.org/W2909607850","https://openalex.org/W2916979304","https://openalex.org/W2939497224","https://openalex.org/W2939777271","https://openalex.org/W2963177459","https://openalex.org/W2963574857","https://openalex.org/W2963773971","https://openalex.org/W2963843276","https://openalex.org/W2964058413","https://openalex.org/W2972664737","https://openalex.org/W2972818416","https://openalex.org/W2982456909","https://openalex.org/W2995166068","https://openalex.org/W2998616931","https://openalex.org/W3007328579","https://openalex.org/W3008762051","https://openalex.org/W3015191643","https://openalex.org/W3015306655","https://openalex.org/W3015834770","https://openalex.org/W3016257794","https://openalex.org/W3020336359","https://openalex.org/W3086154751","https://openalex.org/W3096073522","https://openalex.org/W3097173744","https://openalex.org/W3144062511","https://openalex.org/W3151596526","https://openalex.org/W3162315798","https://openalex.org/W3162341667","https://openalex.org/W3163217847","https://openalex.org/W3194338569","https://openalex.org/W3197479040","https://openalex.org/W3198667862","https://openalex.org/W3203119473","https://openalex.org/W3209490467","https://openalex.org/W4285787282","https://openalex.org/W4288366110","https://openalex.org/W6631190155","https://openalex.org/W6734797129","https://openalex.org/W6735168207","https://openalex.org/W6761806390","https://openalex.org/W6766380642","https://openalex.org/W6769802879","https://openalex.org/W6802205285"],"related_works":["https://openalex.org/W1656519308","https://openalex.org/W2042717753","https://openalex.org/W2037265366","https://openalex.org/W2022849831","https://openalex.org/W2391832549","https://openalex.org/W2286653370","https://openalex.org/W1499578372","https://openalex.org/W2368849850","https://openalex.org/W1799937301","https://openalex.org/W2401089611"],"abstract_inverted_index":{"Far-field":[0],"multi-speaker":[1,95,175],"automatic":[2],"speech":[3,60,63,123],"recognition":[4],"(ASR)":[5],"has":[6],"drawn":[7],"increasing":[8],"attention":[9],"in":[10,97,151],"recent":[11],"years.":[12],"Most":[13],"existing":[14],"methods":[15],"feature":[16],"a":[17,43,74,98,107,117,130,152],"signal":[18],"processing":[19],"frontend":[20,68,103],"and":[21,66,69,94,116,122,147,178,195],"an":[22,52],"ASR":[23,71,96,135,159,186],"backend.":[24],"In":[25,47],"realistic":[26],"scenarios,":[27],"these":[28],"modules":[29],"are":[30],"usually":[31],"trained":[32],"separately":[33],"or":[34,42],"progressively,":[35],"which":[36],"suffers":[37],"from":[38],"either":[39],"inter-module":[40],"mismatch":[41],"complicated":[44],"training":[45],"process.":[46],"this":[48,83],"paper,":[49],"we":[50,128],"propose":[51],"end-to-end":[53,100,133,154],"multi-channel":[54],"model":[55,144,172,187],"that":[56,88,141,182],"jointly":[57],"optimizes":[58],"the":[59,70,78,85,126,142,158,162,170,183,208],"enhancement":[61],"(including":[62],"dereverberation,":[64,92],"denoising,":[65],"separation)":[67],"backend":[72],"as":[73],"single":[75],"system.":[76],"To":[77],"best":[79],"of":[80,106,164],"our":[81],"knowledge,":[82],"is":[84,138,145],"first":[86],"work":[87],"proposes":[89],"to":[90],"optimize":[91],"beamforming,":[93],"fully":[99,153,184],"manner.":[101],"The":[102],"module":[104],"consists":[105],"weighted":[108],"prediction":[109],"error":[110,203],"(WPE)":[111],"based":[112],"submodule":[113],"for":[114,120],"dereverberation":[115],"neural":[118],"beamformer":[119],"denoising":[121],"separation.":[124],"For":[125],"backend,":[127],"adopt":[129],"widely":[131],"used":[132],"(E2E)":[134],"architecture.":[136],"It":[137],"worth":[139],"noting":[140],"entire":[143],"differentiable":[146],"can":[148,188],"be":[149],"optimized":[150],"manner":[155],"using":[156],"only":[157],"criterion,":[160],"without":[161],"need":[163],"parallel":[165],"signal-level":[166],"labels.":[167],"We":[168],"evaluate":[169],"proposed":[171],"on":[173,192],"several":[174],"benchmark":[176],"datasets,":[177],"experimental":[179],"results":[180],"show":[181],"E2E":[185],"achieve":[189],"competitive":[190],"performance":[191],"both":[193],"noisy":[194],"reverberant":[196],"conditions,":[197],"with":[198],"over":[199,207],"30%":[200],"relative":[201],"word":[202],"rate":[204],"(WER)":[205],"reduction":[206],"single-channel":[209],"baseline":[210],"systems.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}