{"id":"https://openalex.org/W3163440581","doi":"https://doi.org/10.1109/icassp39728.2021.9413418","title":"Rule-Embedded Network for Audio-Visual Voice Activity Detection in Live Musical Video Streams","display_name":"Rule-Embedded Network for Audio-Visual Voice Activity Detection in Live Musical Video Streams","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163440581","doi":"https://doi.org/10.1109/icassp39728.2021.9413418","mag":"3163440581"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413418","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413418","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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":"http://hdl.handle.net/1854/LU-8708156","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/A5015076117","display_name":"Yi Deng","orcid":"https://orcid.org/0000-0003-2657-4689"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Deng","raw_affiliation_strings":["New York University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"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":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4165","last_page":"4169"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9936000108718872,"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":0.8190386295318604},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6819195747375488},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.6052721738815308},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.5654510259628296},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5634000301361084},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5579748749732971},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5445918440818787},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.5339770317077637},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4310763478279114},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3725709915161133},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.30732637643814087},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.21599683165550232},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07705757021903992}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8190386295318604},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6819195747375488},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.6052721738815308},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.5654510259628296},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5634000301361084},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5579748749732971},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5445918440818787},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.5339770317077637},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4310763478279114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3725709915161133},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.30732637643814087},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.21599683165550232},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07705757021903992},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413418","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413418","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:archive.ugent.be:8708156","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-8708156","pdf_url":null,"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":"ISBN: 9781728176055","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:zenodo.org:6191248","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ICASSP39728.2021.9413418","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"info:eu-repo/semantics/other"}],"best_oa_location":{"id":"pmh:oai:archive.ugent.be:8708156","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-8708156","pdf_url":null,"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":"ISBN: 9781728176055","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6299999952316284}],"awards":[],"funders":[{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W33176171","https://openalex.org/W1478687540","https://openalex.org/W1522301498","https://openalex.org/W1993583497","https://openalex.org/W2044916317","https://openalex.org/W2059203007","https://openalex.org/W2124867748","https://openalex.org/W2154278880","https://openalex.org/W2198815242","https://openalex.org/W2394553851","https://openalex.org/W2408239454","https://openalex.org/W2567070169","https://openalex.org/W2753897885","https://openalex.org/W2767895109","https://openalex.org/W2904769598","https://openalex.org/W2928717951","https://openalex.org/W2938440247","https://openalex.org/W2963608065","https://openalex.org/W2963680395","https://openalex.org/W2963970792","https://openalex.org/W2964121744","https://openalex.org/W2964235767","https://openalex.org/W2965002127","https://openalex.org/W3096787185","https://openalex.org/W4255788608","https://openalex.org/W6631190155","https://openalex.org/W6712206848","https://openalex.org/W6731370813","https://openalex.org/W6752254909"],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W2494533082","https://openalex.org/W1975359510","https://openalex.org/W4214771044","https://openalex.org/W4387698063","https://openalex.org/W4382560817","https://openalex.org/W3004352674","https://openalex.org/W3110605476","https://openalex.org/W3043119899","https://openalex.org/W1620668332"],"abstract_inverted_index":{"Detecting":[0],"anchor\u2019s":[1],"voice":[2,21,40],"in":[3,41,69,123],"live":[4,171],"musical":[5,172],"streams":[6],"is":[7,32,72,152,178],"an":[8],"important":[9],"preprocessing":[10],"step":[11],"for":[12,56,155],"music":[13,164],"and":[14,81,149,165],"speech":[15],"signal":[16,167],"processing.":[17],"Existing":[18],"approaches":[19],"to":[20,34,50,73,88,161],"activity":[22],"detection":[23,58,111],"(VAD)":[24],"primarily":[25],"rely":[26],"on":[27,37],"audio,":[28],"however,":[29],"audio-based":[30],"VAD":[31],"difficult":[33],"effectively":[35],"focus":[36],"the":[38,52,60,67,70,75,78,91,101,107,110,114,120,124,129,132,144,162],"target":[39,61],"noisy":[42],"environments.":[43],"This":[44],"paper":[45],"proposes":[46],"a":[47,86,169],"rule-embedded":[48],"network":[49],"fuse":[51],"audio-visual":[53],"(A-V)":[54],"inputs":[55],"better":[57],"of":[59,66,93,103,113,119,131,139,146],"voice.":[62],"The":[63],"core":[64],"role":[65],"rule":[68],"model":[71,126,135],"coordinate":[74],"relation":[76],"between":[77],"bi-modal":[79],"information":[80,92],"use":[82],"visual":[83,150],"representations":[84],"as":[85],"mask":[87],"filter":[89],"out":[90],"non-target":[94],"sound.":[95],"Experiments":[96],"show":[97],"that:":[98],"1)":[99],"with":[100,175],"help":[102],"cross-modal":[104,163],"fusion":[105],"using":[106],"proposed":[108],"rule,":[109],"results":[112],"A-V":[115,134],"branch":[116,122],"outperform":[117],"that":[118,138,143],"audio":[121,148,166],"same":[125],"framework;":[127],"2)":[128],"performance":[130],"bimodal":[133],"far":[136],"outperforms":[137],"audio-only":[140],"models,":[141],"indicating":[142],"incorporation":[145],"both":[147],"signals":[151],"highly":[153],"beneficial":[154],"VAD.":[156],"To":[157],"attract":[158],"more":[159],"attention":[160],"processing,":[168],"new":[170],"video":[173],"corpus":[174],"frame-level":[176],"labels":[177],"introduced.":[179]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}