{"id":"https://openalex.org/W3200669029","doi":"https://doi.org/10.1109/asru51503.2021.9688103","title":"Dual-Encoder Architecture with Encoder Selection for Joint Close-Talk and Far-Talk Speech Recognition","display_name":"Dual-Encoder Architecture with Encoder Selection for Joint Close-Talk and Far-Talk Speech Recognition","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W3200669029","doi":"https://doi.org/10.1109/asru51503.2021.9688103","mag":"3200669029"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688103","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5016747567","display_name":"Felix Weninger","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Felix Weninger","raw_affiliation_strings":["Nuance Communications,Burlington,MA,USA","Nuance Communications, Burlington, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications,Burlington,MA,USA","institution_ids":["https://openalex.org/I4210125787"]},{"raw_affiliation_string":"Nuance Communications, Burlington, MA, USA","institution_ids":["https://openalex.org/I4210125787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050683447","display_name":"Marco Gaudesi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127533","display_name":"Nuance Communications (Italy)","ror":"https://ror.org/038333j82","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210125787","https://openalex.org/I4210127533"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marco Gaudesi","raw_affiliation_strings":["Nuance Communications,Torino,Italy","Nuance Communications, Torino, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications,Torino,Italy","institution_ids":["https://openalex.org/I4210127533"]},{"raw_affiliation_string":"Nuance Communications, Torino, Italy","institution_ids":["https://openalex.org/I4210127533"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091159990","display_name":"Ralf Leibold","orcid":null},"institutions":[{"id":"https://openalex.org/I1292318990","display_name":"Nuance Communications (Austria)","ror":"https://ror.org/04ggpbw68","country_code":"AT","type":"company","lineage":["https://openalex.org/I1292318990","https://openalex.org/I4210125787"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Ralf Leibold","raw_affiliation_strings":["Nuance Communications,Aachen,Germany","Nuance Communications, Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications,Aachen,Germany","institution_ids":["https://openalex.org/I1292318990"]},{"raw_affiliation_string":"Nuance Communications, Aachen, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056510268","display_name":"Roberto Gemello","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127533","display_name":"Nuance Communications (Italy)","ror":"https://ror.org/038333j82","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210125787","https://openalex.org/I4210127533"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Roberto Gemello","raw_affiliation_strings":["Nuance Communications,Torino,Italy","Nuance Communications, Torino, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications,Torino,Italy","institution_ids":["https://openalex.org/I4210127533"]},{"raw_affiliation_string":"Nuance Communications, Torino, Italy","institution_ids":["https://openalex.org/I4210127533"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109588257","display_name":"Puming Zhan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Puming Zhan","raw_affiliation_strings":["Nuance Communications,Burlington,MA,USA","Nuance Communications, Burlington, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications,Burlington,MA,USA","institution_ids":["https://openalex.org/I4210125787"]},{"raw_affiliation_string":"Nuance Communications, Burlington, MA, USA","institution_ids":["https://openalex.org/I4210125787"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"534","last_page":"540"},"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":0.9958999752998352,"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/encoder","display_name":"Encoder","score":0.8260650634765625},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7885136604309082},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5314646363258362},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.4929540157318115},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.4777902066707611},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4553854465484619},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4220846891403198},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.42044878005981445},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40756550431251526},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13079315423965454},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10823619365692139}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.8260650634765625},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7885136604309082},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5314646363258362},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.4929540157318115},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.4777902066707611},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4553854465484619},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4220846891403198},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.42044878005981445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40756550431251526},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13079315423965454},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10823619365692139},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","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/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9688103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688103","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W1904457459","https://openalex.org/W1932968309","https://openalex.org/W1973669708","https://openalex.org/W1992475611","https://openalex.org/W2037769258","https://openalex.org/W2103621378","https://openalex.org/W2133564696","https://openalex.org/W2136439176","https://openalex.org/W2327501763","https://openalex.org/W2516857479","https://openalex.org/W2517616541","https://openalex.org/W2622203030","https://openalex.org/W2767071179","https://openalex.org/W2889367162","https://openalex.org/W2889664202","https://openalex.org/W2900092534","https://openalex.org/W2921214093","https://openalex.org/W2921496354","https://openalex.org/W2936774411","https://openalex.org/W2962736520","https://openalex.org/W2962946733","https://openalex.org/W2963050656","https://openalex.org/W2963213832","https://openalex.org/W2964308564","https://openalex.org/W2964391865","https://openalex.org/W2972799770","https://openalex.org/W2995025901","https://openalex.org/W3002595344","https://openalex.org/W3008191852","https://openalex.org/W3015834770","https://openalex.org/W3016010032","https://openalex.org/W3016010944","https://openalex.org/W3086154751","https://openalex.org/W3096273170","https://openalex.org/W3097747488","https://openalex.org/W3097777922","https://openalex.org/W3140783160","https://openalex.org/W3140910706","https://openalex.org/W3151287998","https://openalex.org/W3160207687","https://openalex.org/W3163203022","https://openalex.org/W6638749077","https://openalex.org/W6679434410","https://openalex.org/W6759957882","https://openalex.org/W6763847309","https://openalex.org/W6766096327"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2357191878","https://openalex.org/W2181948922","https://openalex.org/W1997078944","https://openalex.org/W2384362569","https://openalex.org/W2142795561","https://openalex.org/W1968065688","https://openalex.org/W1552846815","https://openalex.org/W2142945567","https://openalex.org/W107154053"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,58,65,105,114,118],"dual-encoder":[6,127],"ASR":[7,95],"architecture":[8,128],"for":[9,30,61,73],"joint":[10],"modeling":[11],"of":[12,25],"close-talk":[13],"(CT)":[14],"and":[15,27,52,64,91,117,140,150],"far-talk":[16],"(FT)":[17],"speech,":[18,75],"in":[19,152],"order":[20],"to":[21,37,43,131,144],"combine":[22],"the":[23,45,53,81,125,145],"advantages":[24],"CT":[26,62,115,139],"FT":[28,74,141],"devices":[29],"better":[31],"accuracy.":[32],"The":[33,97],"key":[34],"idea":[35],"is":[36,110],"add":[38],"an":[39],"encoder":[40,60,67,82],"selection":[41],"network":[42],"choose":[44],"optimal":[46],"input":[47],"source":[48],"(CT":[49],"or":[50],"FT)":[51],"corresponding":[54],"encoder.":[55],"We":[56,84],"use":[57,107],"single-channel":[59],"speech":[63,103],"multi-channel":[66],"with":[68,80,101,113],"Spatial":[69],"Filtering":[70],"neural":[71],"beamforming":[72],"which":[76,109],"are":[77,99],"jointly":[78],"trained":[79,149],"selection.":[83],"validate":[85],"our":[86],"approach":[87],"on":[88],"both":[89,138],"attention-based":[90],"RNN":[92],"Transducer":[93],"end-to-end":[94],"systems.":[96],"experiments":[98],"done":[100],"conversational":[102],"from":[104],"medical":[106],"case,":[108],"recorded":[111],"simultaneously":[112],"device":[116],"microphone":[119],"array.":[120],"Our":[121],"results":[122],"show":[123],"that":[124],"proposed":[126],"obtains":[129],"up":[130],"9%":[132],"relative":[133],"WER":[134],"reduction":[135],"when":[136],"using":[137],"input,":[142],"compared":[143],"best":[146],"single-encoder":[147],"system":[148],"tested":[151],"matched":[153],"condition.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
