{"id":"https://openalex.org/W4225264578","doi":"https://doi.org/10.1109/icassp43922.2022.9747204","title":"Speaker-Targeted Audio-Visual Speech Recognition Using a Hybrid CTC/Attention Model with Interference Loss","display_name":"Speaker-Targeted Audio-Visual Speech Recognition Using a Hybrid CTC/Attention Model with Interference Loss","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225264578","doi":"https://doi.org/10.1109/icassp43922.2022.9747204"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747204","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747204","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://da.lib.kobe-u.ac.jp/da/kernel/0100483306/0100483306.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055190483","display_name":"Ryota Tsunoda","orcid":null},"institutions":[{"id":"https://openalex.org/I65837984","display_name":"Kobe University","ror":"https://ror.org/03tgsfw79","country_code":"JP","type":"education","lineage":["https://openalex.org/I65837984"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryota Tsunoda","raw_affiliation_strings":["Kobe University,Graduate School of System Informatics,Japan","Graduate School of System Informatics, Kobe University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kobe University,Graduate School of System Informatics,Japan","institution_ids":["https://openalex.org/I65837984"]},{"raw_affiliation_string":"Graduate School of System Informatics, Kobe University, Japan","institution_ids":["https://openalex.org/I65837984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011355805","display_name":"Ryo Aihara","orcid":"https://orcid.org/0009-0006-6492-3754"},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Aihara","raw_affiliation_strings":["Mitsubishi Electric Corporation,Information Technology R&D Center,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Corporation,Information Technology R&D Center,Japan","institution_ids":["https://openalex.org/I4210133125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057295313","display_name":"Ryoichi Takashima","orcid":"https://orcid.org/0000-0002-9808-0250"},"institutions":[{"id":"https://openalex.org/I65837984","display_name":"Kobe University","ror":"https://ror.org/03tgsfw79","country_code":"JP","type":"education","lineage":["https://openalex.org/I65837984"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryoichi Takashima","raw_affiliation_strings":["Kobe University,Graduate School of System Informatics,Japan","Graduate School of System Informatics, Kobe University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kobe University,Graduate School of System Informatics,Japan","institution_ids":["https://openalex.org/I65837984"]},{"raw_affiliation_string":"Graduate School of System Informatics, Kobe University, Japan","institution_ids":["https://openalex.org/I65837984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009283470","display_name":"Tetsuya Takiguchi","orcid":"https://orcid.org/0000-0001-5005-7679"},"institutions":[{"id":"https://openalex.org/I65837984","display_name":"Kobe University","ror":"https://ror.org/03tgsfw79","country_code":"JP","type":"education","lineage":["https://openalex.org/I65837984"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuya Takiguchi","raw_affiliation_strings":["Kobe University,Graduate School of System Informatics,Japan","Graduate School of System Informatics, Kobe University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kobe University,Graduate School of System Informatics,Japan","institution_ids":["https://openalex.org/I65837984"]},{"raw_affiliation_string":"Graduate School of System Informatics, Kobe University, Japan","institution_ids":["https://openalex.org/I65837984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104120742","display_name":"Yoshie Imai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshie Imai","raw_affiliation_strings":["Mitsubishi Electric Corporation,Information Technology R&D Center,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Corporation,Information Technology R&D Center,Japan","institution_ids":["https://openalex.org/I4210133125"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"251","last_page":"255"},"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":0.9994999766349792,"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":0.9994000196456909,"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":0.839692234992981},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8169848918914795},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6847570538520813},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.6070067882537842},{"id":"https://openalex.org/keywords/interference","display_name":"Interference (communication)","score":0.4979982376098633},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4890359342098236},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42373326420783997},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.395523339509964},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.297976016998291},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.157709002494812}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.839692234992981},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8169848918914795},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6847570538520813},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.6070067882537842},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.4979982376098633},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4890359342098236},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42373326420783997},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.395523339509964},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.297976016998291},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.157709002494812},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747204","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747204","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"},{"id":"pmh:oai:da.lib.kobe-u.ac.jp:20.500.14094/0100483306","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.14094/0100483306","pdf_url":"https://da.lib.kobe-u.ac.jp/da/kernel/0100483306/0100483306.pdf","source":{"id":"https://openalex.org/S4306401924","display_name":"Kobe University Repository Kernel (Kobe University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I65837984","host_organization_name":"Kobe University","host_organization_lineage":["https://openalex.org/I65837984"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 251-255","raw_type":"conference paper"}],"best_oa_location":{"id":"pmh:oai:da.lib.kobe-u.ac.jp:20.500.14094/0100483306","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.14094/0100483306","pdf_url":"https://da.lib.kobe-u.ac.jp/da/kernel/0100483306/0100483306.pdf","source":{"id":"https://openalex.org/S4306401924","display_name":"Kobe University Repository Kernel (Kobe University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I65837984","host_organization_name":"Kobe University","host_organization_lineage":["https://openalex.org/I65837984"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 251-255","raw_type":"conference paper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4225264578.pdf","grobid_xml":"https://content.openalex.org/works/W4225264578.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W854541894","https://openalex.org/W1586532344","https://openalex.org/W2015394094","https://openalex.org/W2029199293","https://openalex.org/W2051360208","https://openalex.org/W2064675550","https://openalex.org/W2076462394","https://openalex.org/W2102113734","https://openalex.org/W2157331557","https://openalex.org/W2514741789","https://openalex.org/W2526425061","https://openalex.org/W2551572271","https://openalex.org/W2606974598","https://openalex.org/W2766219058","https://openalex.org/W2807126412","https://openalex.org/W2889624961","https://openalex.org/W2890952074","https://openalex.org/W2962780374","https://openalex.org/W2963654155","https://openalex.org/W2963785710","https://openalex.org/W2972568703","https://openalex.org/W3011234510","https://openalex.org/W3102469722","https://openalex.org/W3106423890","https://openalex.org/W3154262773","https://openalex.org/W6600284362","https://openalex.org/W6623517193","https://openalex.org/W6635078382","https://openalex.org/W6675365184","https://openalex.org/W6754392867"],"related_works":["https://openalex.org/W2071828724","https://openalex.org/W1491159402","https://openalex.org/W1994694193","https://openalex.org/W4297807400","https://openalex.org/W4313854686","https://openalex.org/W321304764","https://openalex.org/W2249138175","https://openalex.org/W2161865195","https://openalex.org/W3188427489","https://openalex.org/W2189295099"],"abstract_inverted_index":{"Audio-visual":[0],"(AV)-automatic":[1],"speech":[2,7,25,78,82,91,151],"recognition":[3,8,56,67,92,114,152],"(ASR)":[4],"can":[5],"improve":[6,89],"accuracy":[9,57,68,93,115],"by":[10,43],"using":[11,44,133],"lip":[12],"images,":[13],"especially":[14],"in":[15,55,58,71,98,153],"noisy":[16],"environments.":[17,156],"The":[18,130],"recently":[19],"proposed":[20],"AV":[21,50],"Align":[22,51],"system":[23],"integrates":[24],"and":[26,79,120],"image":[27],"features":[28,40,46],"based":[29],"on":[30],"a":[31,76,103],"cross-modal":[32],"attention":[33,36],"mechanism,":[34],"where":[35,75],"weights":[37],"for":[38,125],"visual":[39],"are":[41],"estimated":[42],"acoustic":[45],"as":[47],"queries.":[48],"Although":[49],"shows":[52],"an":[53,80],"improvement":[54],"background":[59],"noise":[60],"environments,":[61,74],"we":[62,101],"have":[63],"observed":[64],"that":[65,105,111,138],"the":[66,90,95,107,113,117,121,127,134,139,147],"degrades":[69],"significantly":[70],"interference":[72,118,154],"speaker":[73,97,119,155],"target":[77,96],"interfering":[81],"overlap":[83],"each":[84],"other.":[85],"In":[86],"order":[87],"to":[88],"of":[94,116,141,149],"such":[99],"situations,":[100],"propose":[102],"method":[104],"combines":[106],"auxiliary":[108,143],"loss":[109,123,144],"function":[110,124],"maximizes":[112],"CTC":[122],"training":[126],"AV-ASR":[128],"model.":[129],"experimental":[131],"results":[132],"TCD-TIMIT":[135],"dataset":[136],"show":[137],"use":[140],"these":[142],"functions":[145],"improves":[146],"performance":[148],"target-speaker":[150]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}