{"id":"https://openalex.org/W4224916606","doi":"https://doi.org/10.1109/icassp43922.2022.9747535","title":"Channel-Wise AV-Fusion Attention for Multi-Channel Audio-Visual Speech Recognition","display_name":"Channel-Wise AV-Fusion Attention for Multi-Channel Audio-Visual Speech Recognition","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224916606","doi":"https://doi.org/10.1109/icassp43922.2022.9747535"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747535","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747535","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 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/A5109577487","display_name":"Gaopeng Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210092066","display_name":"Nitto Chemical Industry (Japan)","ror":"https://ror.org/00dcjap62","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210092066","https://openalex.org/I4210140025"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Gaopeng Xu","raw_affiliation_strings":["NIO Co., Ltd"],"affiliations":[{"raw_affiliation_string":"NIO Co., Ltd","institution_ids":["https://openalex.org/I4210092066"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104305105","display_name":"Song Yang","orcid":"https://orcid.org/0009-0007-6837-1739"},"institutions":[{"id":"https://openalex.org/I4210092066","display_name":"Nitto Chemical Industry (Japan)","ror":"https://ror.org/00dcjap62","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210092066","https://openalex.org/I4210140025"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Song Yang","raw_affiliation_strings":["NIO Co., Ltd"],"affiliations":[{"raw_affiliation_string":"NIO Co., Ltd","institution_ids":["https://openalex.org/I4210092066"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100318161","display_name":"Wei Li","orcid":"https://orcid.org/0000-0002-3135-0447"},"institutions":[{"id":"https://openalex.org/I4210092066","display_name":"Nitto Chemical Industry (Japan)","ror":"https://ror.org/00dcjap62","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210092066","https://openalex.org/I4210140025"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":["NIO Co., Ltd"],"affiliations":[{"raw_affiliation_string":"NIO Co., Ltd","institution_ids":["https://openalex.org/I4210092066"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082259804","display_name":"Song Wang","orcid":"https://orcid.org/0000-0003-4152-5295"},"institutions":[{"id":"https://openalex.org/I4210092066","display_name":"Nitto Chemical Industry (Japan)","ror":"https://ror.org/00dcjap62","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210092066","https://openalex.org/I4210140025"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Song Wang","raw_affiliation_strings":["NIO Co., Ltd"],"affiliations":[{"raw_affiliation_string":"NIO Co., Ltd","institution_ids":["https://openalex.org/I4210092066"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107310977","display_name":"Guo Wei","orcid":"https://orcid.org/0009-0000-1918-184X"},"institutions":[{"id":"https://openalex.org/I4210092066","display_name":"Nitto Chemical Industry (Japan)","ror":"https://ror.org/00dcjap62","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210092066","https://openalex.org/I4210140025"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Guo Wei","raw_affiliation_strings":["NIO Co., Ltd"],"affiliations":[{"raw_affiliation_string":"NIO Co., Ltd","institution_ids":["https://openalex.org/I4210092066"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010272559","display_name":"Junfeng Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210092066","display_name":"Nitto Chemical Industry (Japan)","ror":"https://ror.org/00dcjap62","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210092066","https://openalex.org/I4210140025"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junfeng Yuan","raw_affiliation_strings":["NIO Co., Ltd"],"affiliations":[{"raw_affiliation_string":"NIO Co., Ltd","institution_ids":["https://openalex.org/I4210092066"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073887901","display_name":"Jie Gao","orcid":"https://orcid.org/0000-0001-9579-1703"},"institutions":[{"id":"https://openalex.org/I4210092066","display_name":"Nitto Chemical Industry (Japan)","ror":"https://ror.org/00dcjap62","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210092066","https://openalex.org/I4210140025"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jie Gao","raw_affiliation_strings":["NIO Co., Ltd"],"affiliations":[{"raw_affiliation_string":"NIO Co., Ltd","institution_ids":["https://openalex.org/I4210092066"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5109577487"],"corresponding_institution_ids":["https://openalex.org/I4210092066"],"apc_list":null,"apc_paid":null,"fwci":0.8581,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.72417062,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"9251","last_page":"9255"},"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":0.9995999932289124,"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":0.9990000128746033,"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/speech-recognition","display_name":"Speech recognition","score":0.8082382678985596},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8025177717208862},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6697728633880615},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.6021323800086975},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5317574739456177},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4481566846370697},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.42002102732658386},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41445744037628174},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32883331179618835},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11041882634162903}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8082382678985596},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8025177717208862},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6697728633880615},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.6021323800086975},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5317574739456177},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4481566846370697},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.42002102732658386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41445744037628174},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32883331179618835},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11041882634162903},{"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/icassp43922.2022.9747535","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747535","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4099999964237213,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1985690171","https://openalex.org/W2148613904","https://openalex.org/W2892009249","https://openalex.org/W2900212944","https://openalex.org/W2901907199","https://openalex.org/W2936078256","https://openalex.org/W2936774411","https://openalex.org/W2963197115","https://openalex.org/W2963211739","https://openalex.org/W2963242190","https://openalex.org/W2971840980","https://openalex.org/W2972492143","https://openalex.org/W2972641669","https://openalex.org/W3004597053","https://openalex.org/W3016011581","https://openalex.org/W3097777922","https://openalex.org/W3097966334","https://openalex.org/W3163211337","https://openalex.org/W3169722760","https://openalex.org/W4224933780","https://openalex.org/W6766380642","https://openalex.org/W6777479377"],"related_works":["https://openalex.org/W3081187864","https://openalex.org/W4380605396","https://openalex.org/W2803306015","https://openalex.org/W3133352777","https://openalex.org/W151018310","https://openalex.org/W2784059283","https://openalex.org/W4319779560","https://openalex.org/W2008737763","https://openalex.org/W4385611764","https://openalex.org/W2519224033"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"our":[5],"work":[6],"for":[7],"automatic":[8],"speech":[9,32],"recognition":[10],"(ASR)":[11],"in":[12,75,81],"the":[13,27,62,73,82,86],"Multimodal":[14],"Information":[15],"Based":[16],"Speech":[17],"Processing":[18],"(MISP)":[19],"Challenge":[20],"2021.":[21],"We":[22],"proposed":[23],"a":[24,36,48],"combination":[25,50],"of":[26,51,88],"guided":[28],"source":[29],"separation-based":[30],"(GSS)":[31],"enhancement":[33],"technique":[34],"and":[35,45],"novel":[37],"Channel-wise":[38],"Av-fusion":[39],"encoder":[40],"(CAE)":[41],"based":[42],"acoustic":[43],"model":[44],"found":[46],"that":[47],"kindly":[49],"these":[52],"techniques":[53],"provided":[54],"essential":[55],"accuracy":[56],"improvements.":[57],"Our":[58],"ASR":[59],"system":[60],"reduces":[61],"Chinese":[63],"Character":[64],"Error":[65],"Rate":[66],"(CCER)":[67],"by":[68],"37.67%":[69],"absolute":[70],"compared":[71],"to":[72],"baseline":[74],"track":[76],"2,":[77],"achieving":[78],"first":[79],"place":[80],"evaluation":[83],"period":[84],"with":[85],"CCER":[87],"25.07%.":[89]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}