{"id":"https://openalex.org/W2891980359","doi":"https://doi.org/10.1109/icassp.2018.8462161","title":"Speaker Adaptation for Multichannel End-to-End Speech Recognition","display_name":"Speaker Adaptation for Multichannel End-to-End Speech Recognition","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2891980359","doi":"https://doi.org/10.1109/icassp.2018.8462161","mag":"2891980359"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462161","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462161","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5103151157","display_name":"Tsubasa Ochiai","orcid":"https://orcid.org/0000-0002-5422-6617"},"institutions":[{"id":"https://openalex.org/I133984924","display_name":"Doshisha University","ror":"https://ror.org/01fxdkm29","country_code":"JP","type":"education","lineage":["https://openalex.org/I133984924"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Tsubasa Ochiai","raw_affiliation_strings":["Graduate School of Science and Engineering, Doshisha University, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Science and Engineering, Doshisha University, Kyoto, Japan","institution_ids":["https://openalex.org/I133984924"]}]},{"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/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories, Massachusetts, USA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories, Massachusetts, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027443847","display_name":"Shigeru Katagiri","orcid":"https://orcid.org/0000-0003-4738-5385"},"institutions":[{"id":"https://openalex.org/I133984924","display_name":"Doshisha University","ror":"https://ror.org/01fxdkm29","country_code":"JP","type":"education","lineage":["https://openalex.org/I133984924"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shigeru Katagiri","raw_affiliation_strings":["Graduate School of Science and Engineering, Doshisha University, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Science and Engineering, Doshisha University, Kyoto, Japan","institution_ids":["https://openalex.org/I133984924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087554069","display_name":"Takaaki Hori","orcid":"https://orcid.org/0000-0003-4560-8039"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takaaki Hori","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories, Massachusetts, USA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories, Massachusetts, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112763337","display_name":"John R. Hershey","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Hershey","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories, Massachusetts, USA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories, Massachusetts, USA","institution_ids":["https://openalex.org/I4210159266"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103151157"],"corresponding_institution_ids":["https://openalex.org/I133984924"],"apc_list":null,"apc_paid":null,"fwci":5.6149,"has_fulltext":false,"cited_by_count":54,"citation_normalized_percentile":{"value":0.96850759,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6707","last_page":"6711"},"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":0.9972000122070312,"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":0.8275342583656311},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.804625391960144},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.792534351348877},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6789149641990662},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6284011602401733},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5565626621246338},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4638533592224121},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4615177810192108},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.46044597029685974},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3645011782646179}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8275342583656311},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.804625391960144},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.792534351348877},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6789149641990662},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6284011602401733},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5565626621246338},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4638533592224121},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4615177810192108},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.46044597029685974},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3645011782646179},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462161","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462161","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":29,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1513862252","https://openalex.org/W1552314771","https://openalex.org/W2009086942","https://openalex.org/W2010362084","https://openalex.org/W2024490156","https://openalex.org/W2061074721","https://openalex.org/W2079623482","https://openalex.org/W2080005694","https://openalex.org/W2102113734","https://openalex.org/W2127851351","https://openalex.org/W2160815625","https://openalex.org/W2168729028","https://openalex.org/W2289394825","https://openalex.org/W2526425061","https://openalex.org/W2559260703","https://openalex.org/W2627092829","https://openalex.org/W2767071179","https://openalex.org/W2771275309","https://openalex.org/W2911392256","https://openalex.org/W2954695182","https://openalex.org/W2962826786","https://openalex.org/W3112742522","https://openalex.org/W6623517193","https://openalex.org/W6675365184","https://openalex.org/W6728030952","https://openalex.org/W6730321509","https://openalex.org/W6735168207","https://openalex.org/W6746298117"],"related_works":["https://openalex.org/W2151749779","https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2097963413","https://openalex.org/W2294335174","https://openalex.org/W2025614924","https://openalex.org/W3179968364","https://openalex.org/W3145575561","https://openalex.org/W2001275470","https://openalex.org/W1992908141"],"abstract_inverted_index":{"Recent":[0],"work":[1],"on":[2],"multichannel":[3,12,73],"end-to-end":[4,72,90],"automatic":[5],"speech":[6,13,16,80],"recognition":[7,17],"(ASR)":[8],"has":[9,57],"shown":[10,35],"that":[11,98],"enhancement":[14],"and":[15,29,39,108],"functions":[18],"can":[19],"be":[20],"integrated":[21],"into":[22],"a":[23,67,83],"deep":[24],"neural":[25,120],"network":[26,113],"(DNN)-based":[27],"system,":[28],"promising":[30],"experimental":[31],"results":[32,94],"have":[33],"been":[34,58],"using":[36,95],"the":[37,52,77,111,119],"CHiME-4":[38,96],"AMI":[40],"corpora.":[41],"In":[42],"other":[43],"recent":[44],"DNN-based":[45],"hidden":[46],"Markov":[47],"model":[48],"(DNN-HMM)":[49],"hybrid":[50],"architectures,":[51],"effectiveness":[53],"of":[54],"speaker":[55],"adaptation":[56,69,103],"well":[59],"established.":[60],"Motivated":[61],"by":[62],"these":[63],"results,":[64],"we":[65],"propose":[66],"multi-path":[68,102],"scheme":[70,104],"for":[71],"ASR,":[74],"which":[75],"combines":[76],"unprocessed":[78],"noisy":[79],"features":[81],"with":[82],"speech-enhanced":[84],"pathway":[85],"to":[86],"improve":[87],"upon":[88],"previous":[89],"ASR":[91,106],"approaches.":[92],"Experimental":[93],"show":[97],"(1)":[99],"our":[100],"proposed":[101],"improves":[105],"performance":[107],"(2)":[109],"adapting":[110,118],"encoder":[112],"is":[114],"more":[115],"effective":[116],"than":[117],"beamformer,":[121],"attention":[122],"mechanism,":[123],"or":[124],"decoder":[125],"network.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}