{"id":"https://openalex.org/W3115290769","doi":"https://doi.org/10.23919/eusipco47968.2020.9287488","title":"Noise-robust Attention Learning for End-to-End Speech Recognition","display_name":"Noise-robust Attention Learning for End-to-End Speech Recognition","publication_year":2020,"publication_date":"2020-12-18","ids":{"openalex":"https://openalex.org/W3115290769","doi":"https://doi.org/10.23919/eusipco47968.2020.9287488","mag":"3115290769"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco47968.2020.9287488","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco47968.2020.9287488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th European Signal Processing Conference (EUSIPCO)","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/A5102017467","display_name":"Yosuke Higuchi","orcid":"https://orcid.org/0000-0003-4500-8957"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yosuke Higuchi","raw_affiliation_strings":["Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073111123","display_name":"Naohiro Tawara","orcid":null},"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":"Naohiro Tawara","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101949937","display_name":"Atsunori Ogawa","orcid":"https://orcid.org/0000-0002-2888-101X"},"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":"Atsunori Ogawa","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034538103","display_name":"Tomoharu Iwata","orcid":"https://orcid.org/0000-0003-4425-1971"},"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":"Tomoharu Iwata","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101188700","display_name":"Tetsunori Kobayashi","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsunori Kobayashi","raw_affiliation_strings":["Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087632404","display_name":"Tetsuji Ogawa","orcid":"https://orcid.org/0000-0002-7316-2073"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuji Ogawa","raw_affiliation_strings":["Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102017467"],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":0.2706,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.66253451,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"2020","issue":null,"first_page":"311","last_page":"315"},"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/T11309","display_name":"Music and Audio Processing","score":0.9980999827384949,"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/T10860","display_name":"Speech and Audio Processing","score":0.9977999925613403,"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/robustness","display_name":"Robustness (evolution)","score":0.8379829525947571},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.8090816140174866},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.804151177406311},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7715358734130859},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5119425058364868},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.49126118421554565},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45823433995246887},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4349609315395355},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4259929955005646},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.39136800169944763}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8379829525947571},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8090816140174866},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.804151177406311},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7715358734130859},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5119425058364868},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.49126118421554565},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45823433995246887},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4349609315395355},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4259929955005646},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.39136800169944763},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/eusipco47968.2020.9287488","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco47968.2020.9287488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},{"id":"mag:3087357565","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=202002266276831853","pdf_url":null,"source":{"id":"https://openalex.org/S4306551642","display_name":"\u65e5\u672c\u97f3\u97ff\u5b66\u4f1a\u7814\u7a76\u767a\u8868\u4f1a\u8b1b\u6f14\u8ad6\u6587\u96c6(CD-ROM)","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":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"\u65e5\u672c\u97f3\u97ff\u5b66\u4f1a\u7814\u7a76\u767a\u8868\u4f1a\u8b1b\u6f14\u8ad6\u6587\u96c6(CD-ROM)","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1731081199","https://openalex.org/W1922655562","https://openalex.org/W1992475611","https://openalex.org/W2062164080","https://openalex.org/W2064675550","https://openalex.org/W2096653978","https://openalex.org/W2102113734","https://openalex.org/W2127141656","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2136439176","https://openalex.org/W2219249508","https://openalex.org/W2327501763","https://openalex.org/W2510867321","https://openalex.org/W2526425061","https://openalex.org/W2559260703","https://openalex.org/W2584667682","https://openalex.org/W2627092829","https://openalex.org/W2799800213","https://openalex.org/W2885724687","https://openalex.org/W2890964092","https://openalex.org/W2892009249","https://openalex.org/W2944255943","https://openalex.org/W2962780374","https://openalex.org/W2962826786","https://openalex.org/W2964308564","https://openalex.org/W2972389417","https://openalex.org/W6623517193","https://openalex.org/W6637618735","https://openalex.org/W6640090968","https://openalex.org/W6675365184","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6688816777","https://openalex.org/W6732862412","https://openalex.org/W7027429494"],"related_works":["https://openalex.org/W4379116102","https://openalex.org/W3210882018","https://openalex.org/W2970990331","https://openalex.org/W3207178610","https://openalex.org/W3211782752","https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W2069501481","https://openalex.org/W3126788496"],"abstract_inverted_index":{"We":[0],"propose":[1,81],"a":[2,24,97,111,120],"method":[3],"for":[4,48],"improving":[5],"the":[6,39,49,54,58,67,70,74,89,106,116,128,133,139,143],"noise":[7,140],"robustness":[8,141],"of":[9,26,69,73,99,142],"an":[10],"end-to-end":[11,75,144],"automatic":[12],"speech":[13,60,101,113],"recognition":[14,71],"(ASR)":[15],"model":[16],"using":[17],"attention":[18,31,50,83,90,107],"weights.":[19],"Several":[20],"studies":[21],"have":[22],"adopted":[23],"combination":[25],"recurrent":[27],"neural":[28],"networks":[29],"and":[30,62],"mechanisms":[32,51],"to":[33,52,66,93,114],"achieve":[34],"direct":[35],"speech-to-text":[36],"translation.":[37],"In":[38,77],"real-world":[40],"environment,":[41],"however,":[42],"noisy":[43,100,112],"conditions":[44],"make":[45],"it":[46],"difficult":[47],"estimate":[53],"accurate":[55],"alignment":[56],"between":[57],"input":[59],"frames":[61],"output":[63],"characters,":[64],"leading":[65],"degradation":[68],"performance":[72],"model.":[76,146],"this":[78],"work,":[79],"we":[80,104],"noise-robust":[82],"learning":[84],"(NRAL)":[85],"which":[86],"explicitly":[87],"tells":[88],"mechanism":[91],"where":[92],"\"listen":[94],"at\"":[95],"in":[96],"sequence":[98],"features.":[102],"Specifically,":[103],"train":[105],"weights":[108,117],"estimated":[109,118],"from":[110,119],"approximate":[115],"clean":[121],"speech.":[122],"The":[123],"experimental":[124],"results":[125],"based":[126],"on":[127],"CHiME-4":[129],"task":[130],"indicate":[131],"that":[132],"proposed":[134],"NRAL":[135],"approach":[136],"effectively":[137],"improves":[138],"ASR":[145]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}