{"id":"https://openalex.org/W3140783160","doi":"https://doi.org/10.1109/slt48900.2021.9383500","title":"Exploring End-to-End Multi-Channel ASR with Bias Information for Meeting Transcription","display_name":"Exploring End-to-End Multi-Channel ASR with Bias Information for Meeting Transcription","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3140783160","doi":"https://doi.org/10.1109/slt48900.2021.9383500","mag":"3140783160"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383500","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383500","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100363470","display_name":"Xiaofei Wang","orcid":"https://orcid.org/0000-0002-7223-1030"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaofei Wang","raw_affiliation_strings":["Microsoft Corp., Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corp., Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016279564","display_name":"Naoyuki Kanda","orcid":"https://orcid.org/0000-0002-8628-3288"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Naoyuki Kanda","raw_affiliation_strings":["Microsoft Corp., Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corp., Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034136587","display_name":"Yashesh Gaur","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yashesh Gaur","raw_affiliation_strings":["Microsoft Corp., Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corp., Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345092","display_name":"Zhuo Chen","orcid":"https://orcid.org/0000-0002-9011-7928"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":["Microsoft Corp., Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corp., Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101749753","display_name":"Zhong Meng","orcid":"https://orcid.org/0000-0001-7814-5929"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhong Meng","raw_affiliation_strings":["Microsoft Corp., Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corp., Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takuya Yoshioka","raw_affiliation_strings":["Microsoft Corp., Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corp., Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"833","last_page":"840"},"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":0.9998999834060669,"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/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":0.8077423572540283},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6219780445098877},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6101229786872864},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5715743899345398},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.5415428876876831},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5383096933364868},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5227344632148743},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.48814353346824646},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.47943276166915894},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.4691174328327179},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4354100823402405},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3657130300998688},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24287351965904236},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11270886659622192}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8077423572540283},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6219780445098877},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6101229786872864},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5715743899345398},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.5415428876876831},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5383096933364868},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5227344632148743},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.48814353346824646},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.47943276166915894},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.4691174328327179},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4354100823402405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3657130300998688},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24287351965904236},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11270886659622192},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt48900.2021.9383500","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383500","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1983812858","https://openalex.org/W2000466020","https://openalex.org/W2061074721","https://openalex.org/W2101045344","https://openalex.org/W2117678320","https://openalex.org/W2125336414","https://openalex.org/W2398042854","https://openalex.org/W2460742184","https://openalex.org/W2517616541","https://openalex.org/W2533523411","https://openalex.org/W2577366047","https://openalex.org/W2589857635","https://openalex.org/W2622203030","https://openalex.org/W2636483419","https://openalex.org/W2726515241","https://openalex.org/W2747732471","https://openalex.org/W2767071179","https://openalex.org/W2803322398","https://openalex.org/W2808631503","https://openalex.org/W2884797218","https://openalex.org/W2889503488","https://openalex.org/W2900212944","https://openalex.org/W2900440209","https://openalex.org/W2909607850","https://openalex.org/W2921496354","https://openalex.org/W2936774411","https://openalex.org/W2938646939","https://openalex.org/W2939690918","https://openalex.org/W2962824709","https://openalex.org/W2962866211","https://openalex.org/W2963970535","https://openalex.org/W2972474532","https://openalex.org/W2998616931","https://openalex.org/W2999547272","https://openalex.org/W3008283340","https://openalex.org/W3015636705","https://openalex.org/W3016131876","https://openalex.org/W3016232124","https://openalex.org/W3016400019","https://openalex.org/W3020336359","https://openalex.org/W3032969657","https://openalex.org/W3096073522","https://openalex.org/W3112742522","https://openalex.org/W6623517193","https://openalex.org/W6678809451","https://openalex.org/W6728841359","https://openalex.org/W6732447497","https://openalex.org/W6787533431"],"related_works":["https://openalex.org/W2373577936","https://openalex.org/W4221148444","https://openalex.org/W4387678054","https://openalex.org/W2389596151","https://openalex.org/W3095575180","https://openalex.org/W2593532750","https://openalex.org/W3207232378","https://openalex.org/W2642467014","https://openalex.org/W2889523925","https://openalex.org/W3080080512"],"abstract_inverted_index":{"Joint":[0],"optimization":[1],"of":[2,57,82,97,105,120,145,151],"multi-channel":[3,107,124],"front-end":[4],"and":[5,86,100,122,135,153],"automatic":[6],"speech":[7],"recognition":[8,130],"(ASR)":[9],"has":[10],"attracted":[11],"much":[12],"interest.":[13],"While":[14],"promising":[15],"results":[16],"have":[17,94],"been":[18],"reported":[19],"for":[20,48,65,109,167],"various":[21,143,175],"tasks,":[22],"past":[23],"studies":[24],"on":[25,78,174],"its":[26],"meeting":[27,176],"transcription":[28],"application":[29],"were":[30],"limited":[31],"to":[32],"small":[33,103],"scale":[34],"experiments.":[35],"It":[36],"is":[37],"still":[38],"unclear":[39],"whether":[40],"such":[41,148],"a":[42,49,54,67,83,101,118,132,185],"joint":[43,80],"framework":[44,183],"can":[45,62],"be":[46,63],"beneficial":[47],"more":[50],"practical":[51],"setup":[52],"where":[53,92],"massive":[55],"amount":[56,104],"single":[58],"channel":[59],"training":[60,115,125],"data":[61,99,108],"leveraged":[64],"building":[66],"strong":[68],"ASR":[69,88],"back-end.":[70],"In":[71,171],"this":[72],"work,":[73],"we":[74,93,140,178],"present":[75],"our":[76,172],"investigation":[77],"the":[79,90,129,168,181],"modeling":[81],"mask-based":[84],"beamformer":[85,169],"Attention-Encoder-Decoder-based":[87],"in":[89],"setting":[91],"75k":[95],"hours":[96],"single-channel":[98],"relatively":[102],"real":[106,123],"model":[110],"training.":[111],"We":[112,156],"explore":[113,142],"effective":[114,159],"procedures,":[116],"including":[117],"comparison":[119],"simulated":[121],"data.":[126],"To":[127],"guide":[128],"towards":[131],"target":[133],"speaker":[134,154],"deal":[136],"with":[137],"overlapped":[138],"speech,":[139],"also":[141],"combinations":[144],"bias":[146,161],"information,":[147],"as":[149],"direction":[150],"arrivals":[152],"profiles.":[155],"propose":[157],"an":[158],"location":[160],"integration":[162],"method":[163],"called":[164],"deep":[165],"concatenation":[166],"network.":[170],"evaluation":[173],"recordings,":[177],"show":[179],"that":[180],"proposed":[182],"achieves":[184],"substantial":[186],"word":[187],"error":[188],"rate":[189],"reduction.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}