{"id":"https://openalex.org/W2983061588","doi":"https://doi.org/10.23919/eusipco.2019.8902524","title":"CNN-based Multichannel End-to-End Speech Recognition for Everyday Home Environments","display_name":"CNN-based Multichannel End-to-End Speech Recognition for Everyday Home Environments","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W2983061588","doi":"https://doi.org/10.23919/eusipco.2019.8902524","mag":"2983061588"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco.2019.8902524","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2019.8902524","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 27th 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/A5112575316","display_name":"Nelson Yalta","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":"Nelson Yalta","raw_affiliation_strings":["Waseda University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University","institution_ids":["https://openalex.org/I150744194"]}]},{"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/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091708408","display_name":"Kazuhiro Nakadai","orcid":"https://orcid.org/0000-0002-6134-4558"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuhiro Nakadai","raw_affiliation_strings":["Honda Research Institute,Japan","Honda Research Institute, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute,Japan","institution_ids":["https://openalex.org/I1283473643"]},{"raw_affiliation_string":"Honda Research Institute, Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055922202","display_name":"Tetsuya Ogata","orcid":"https://orcid.org/0000-0001-7015-0379"},"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":"Tetsuya Ogata","raw_affiliation_strings":["Waseda University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1696,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.88648122,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991999864578247,"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":0.789095938205719},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6463793516159058},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5757508277893066},{"id":"https://openalex.org/keywords/home-automation","display_name":"Home automation","score":0.5395528674125671},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.24048861861228943},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21216857433319092}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.789095938205719},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6463793516159058},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5757508277893066},{"id":"https://openalex.org/C507571656","wikidata":"https://www.wikidata.org/wiki/Q848436","display_name":"Home automation","level":2,"score":0.5395528674125671},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.24048861861228943},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21216857433319092}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco.2019.8902524","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2019.8902524","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 27th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4300000071525574,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W854541894","https://openalex.org/W1522301498","https://openalex.org/W1586532344","https://openalex.org/W1836465849","https://openalex.org/W1985368711","https://openalex.org/W2027499299","https://openalex.org/W2127141656","https://openalex.org/W2148613904","https://openalex.org/W2160815625","https://openalex.org/W2193413348","https://openalex.org/W2194775991","https://openalex.org/W2526425061","https://openalex.org/W2530876040","https://openalex.org/W2585476045","https://openalex.org/W2588610957","https://openalex.org/W2589857635","https://openalex.org/W2608712415","https://openalex.org/W2622203030","https://openalex.org/W2627092829","https://openalex.org/W2766219058","https://openalex.org/W2787663903","https://openalex.org/W2884797218","https://openalex.org/W2899853222","https://openalex.org/W2899867592","https://openalex.org/W2900091092","https://openalex.org/W2900440209","https://openalex.org/W2954695182","https://openalex.org/W2962780374","https://openalex.org/W2962824709","https://openalex.org/W2963211739","https://openalex.org/W2963300719","https://openalex.org/W2964121744","https://openalex.org/W3131736947","https://openalex.org/W6600284362","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6635078382","https://openalex.org/W6638667902","https://openalex.org/W6687566353","https://openalex.org/W6733260875","https://openalex.org/W6733590821","https://openalex.org/W6735168207","https://openalex.org/W6738686518"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Casual":[0],"conversations":[1],"involving":[2],"multiple":[3],"speakers":[4],"and":[5,88,113,121],"noises":[6],"from":[7,76,116],"surrounding":[8],"devices":[9],"are":[10,29],"common":[11],"in":[12,56],"everyday":[13,57],"environments,":[14],"which":[15,84],"degrades":[16],"the":[17,30,33,53,105,122,128],"performances":[18],"of":[19,27,32,62],"automatic":[20],"speech":[21,45],"recognition":[22,46],"systems.":[23],"These":[24],"challenging":[25],"characteristics":[26],"environments":[28],"target":[31],"CHiME-5":[34,129],"challenge.":[35],"By":[36],"employing":[37],"a":[38,71,77,117],"convolutional":[39],"neural":[40,66],"network":[41,67],"(CNN)-based":[42],"multichannel":[43,81],"end-to-end":[44,120],"system,":[47],"this":[48],"study":[49],"attempts":[50],"to":[51],"overcome":[52],"presents":[54],"difficulties":[55],"environments.":[58],"The":[59,80,100],"system":[60],"comprises":[61],"an":[63,74],"attention-based":[64],"encoder\u2013decoder":[65],"that":[68,104],"directly":[69],"generates":[70],"text":[72],"as":[73],"output":[75],"sound":[78],"input.":[79],"CNN":[82],"encoder,":[83],"uses":[85],"residual":[86],"connections":[87],"batch":[89],"renormalization,":[90],"is":[91,109],"trained":[92],"with":[93],"augmented":[94],"data,":[95],"including":[96],"white":[97],"noise":[98],"injection.":[99],"experimental":[101],"results":[102],"show":[103],"word":[106],"error":[107],"rate":[108],"reduced":[110],"by":[111],"8.5%":[112],"0.6%":[114],"absolute":[115],"single":[118],"channel":[119],"best":[123],"baseline":[124],"(LF-MMI":[125],"TDNN)":[126],"on":[127],"corpus,":[130],"respectively.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}