{"id":"https://openalex.org/W3197459407","doi":"https://doi.org/10.21437/interspeech.2021-37","title":"Attention-Based Cross-Modal Fusion for Audio-Visual Voice Activity Detection in Musical Video Streams","display_name":"Attention-Based Cross-Modal Fusion for Audio-Visual Voice Activity Detection in Musical Video Streams","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3197459407","doi":"https://doi.org/10.21437/interspeech.2021-37","mag":"3197459407"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-37","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-37","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://biblio.ugent.be/publication/8741372/file/8741392.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063248625","display_name":"Yuanbo Hou","orcid":"https://orcid.org/0000-0001-8469-5740"},"institutions":[{"id":"https://openalex.org/I2801227569","display_name":"Ghent University Hospital","ror":"https://ror.org/00xmkp704","country_code":"BE","type":"healthcare","lineage":["https://openalex.org/I2801227569"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Yuanbo Hou","raw_affiliation_strings":["Ghent University, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University, Belgium","institution_ids":["https://openalex.org/I2801227569"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031063108","display_name":"Zhesong Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhesong Yu","raw_affiliation_strings":["ByteDance AI Lab, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042222287","display_name":"Xia Liang","orcid":"https://orcid.org/0000-0001-6252-2195"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia Liang","raw_affiliation_strings":["ByteDance AI Lab, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091528537","display_name":"Xingjian Du","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xingjian Du","raw_affiliation_strings":["ByteDance AI Lab, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100934338","display_name":"Bilei Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bilei Zhu","raw_affiliation_strings":["ByteDance AI Lab, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110851569","display_name":"Zejun Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zejun Ma","raw_affiliation_strings":["ByteDance AI Lab, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069519911","display_name":"Dick Botteldooren","orcid":"https://orcid.org/0000-0002-7756-7238"},"institutions":[{"id":"https://openalex.org/I2801227569","display_name":"Ghent University Hospital","ror":"https://ror.org/00xmkp704","country_code":"BE","type":"healthcare","lineage":["https://openalex.org/I2801227569"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Dick Botteldooren","raw_affiliation_strings":["Ghent University, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University, Belgium","institution_ids":["https://openalex.org/I2801227569"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"321","last_page":"325"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.983299970626831,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7991275787353516},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6338565945625305},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.5772494077682495},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4469355046749115},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.43161740899086},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4218471944332123},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4165263772010803},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4102931022644043},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3336092233657837},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08907976746559143}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7991275787353516},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6338565945625305},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.5772494077682495},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4469355046749115},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.43161740899086},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4218471944332123},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4165263772010803},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4102931022644043},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3336092233657837},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08907976746559143},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2021-37","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-37","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:archive.ugent.be:8741372","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-8741372","pdf_url":"https://biblio.ugent.be/publication/8741372/file/8741392.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"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":"ISSN: 2308-457X","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:archive.ugent.be:8741372","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-8741372","pdf_url":"https://biblio.ugent.be/publication/8741372/file/8741392.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"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":"ISSN: 2308-457X","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3197459407.pdf"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1503933356","https://openalex.org/W1522301498","https://openalex.org/W1622676895","https://openalex.org/W1836465849","https://openalex.org/W1993583497","https://openalex.org/W2022186940","https://openalex.org/W2022799064","https://openalex.org/W2029320154","https://openalex.org/W2095705004","https://openalex.org/W2110992439","https://openalex.org/W2118977726","https://openalex.org/W2122647985","https://openalex.org/W2124867748","https://openalex.org/W2129120544","https://openalex.org/W2164637175","https://openalex.org/W2187089797","https://openalex.org/W2191779130","https://openalex.org/W2198815242","https://openalex.org/W2303024254","https://openalex.org/W2408239454","https://openalex.org/W2467206671","https://openalex.org/W2567070169","https://openalex.org/W2893386644","https://openalex.org/W2928717951","https://openalex.org/W2938440247","https://openalex.org/W2963273475","https://openalex.org/W2963677766","https://openalex.org/W2963723765","https://openalex.org/W2964235767","https://openalex.org/W2965002127","https://openalex.org/W3096787185","https://openalex.org/W3101998545","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"Many":[0],"previous":[1],"audio-visual":[2,54,101],"voice-related":[3],"works":[4],"focus":[5],"on":[6,20,83,119],"speech,":[7],"ignoring":[8],"the":[9,13,21,41,76,88,92,99,106,114],"singing":[10,44],"voice":[11,29],"in":[12,49,109],"growing":[14],"number":[15],"of":[16,46,59,94],"musical":[17,26,50],"video":[18,27,51],"streams":[19,52],"Internet.":[22],"For":[23],"processing":[24],"diverse":[25],"data,":[28],"activity":[30],"detection":[31],"is":[32,67,122],"a":[33,64],"necessary":[34],"step.":[35],"This":[36],"paper":[37],"attempts":[38],"to":[39,69,86],"detect":[40],"speech":[42],"and":[43,61,72,75,124],"voices":[45],"target":[47],"performers":[48],"using":[53],"information.":[55],"To":[56],"integrate":[57],"information":[58,116],"audio":[60,71],"visual":[62],"modalities,":[63],"multi-branch":[65,102],"network":[66,103],"proposed":[68,100],"learn":[70],"image":[73],"representations,":[74],"representations":[77,90],"are":[78],"fused":[79],"by":[80],"attention":[81],"based":[82,118],"semantic":[84,120],"similarity":[85],"shape":[87],"acoustic":[89,111],"through":[91],"probability":[93],"anchor":[95],"vocalization.":[96],"Experiments":[97],"show":[98],"far":[104],"outperforms":[105],"audio-only":[107],"model":[108],"challenging":[110],"environments,":[112],"indicating":[113],"cross-modal":[115],"fusion":[117],"correlation":[121],"sensible":[123],"successful.":[125]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
