{"id":"https://openalex.org/W4292862526","doi":"https://doi.org/10.1109/mwscas54063.2022.9859533","title":"Audio-visual Speaker Diarization: Improved Voice Activity Detection with CNN based Feature Extraction","display_name":"Audio-visual Speaker Diarization: Improved Voice Activity Detection with CNN based Feature Extraction","publication_year":2022,"publication_date":"2022-08-07","ids":{"openalex":"https://openalex.org/W4292862526","doi":"https://doi.org/10.1109/mwscas54063.2022.9859533"},"language":"en","primary_location":{"id":"doi:10.1109/mwscas54063.2022.9859533","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mwscas54063.2022.9859533","pdf_url":null,"source":{"id":"https://openalex.org/S4363606568","display_name":"2022 IEEE 65th International Midwest Symposium on Circuits and Systems (MWSCAS)","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":"2022 IEEE 65th International Midwest Symposium on Circuits and Systems (MWSCAS)","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/A5033329367","display_name":"Konstantinos Fanaras","orcid":null},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Konstantinos Fanaras","raw_affiliation_strings":["King Abdullah University of Science and Technology (KAUST),Innovative Technologies Laboratories (ITL),Thuwal,Saudi Arabia","Innovative Technologies Laboratories (ITL), King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology (KAUST),Innovative Technologies Laboratories (ITL),Thuwal,Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]},{"raw_affiliation_string":"Innovative Technologies Laboratories (ITL), King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009913094","display_name":"Antonios Tragoudaras","orcid":"https://orcid.org/0000-0001-6091-9615"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Antonios Tragoudaras","raw_affiliation_strings":["King Abdullah University of Science and Technology (KAUST),Innovative Technologies Laboratories (ITL),Thuwal,Saudi Arabia","Innovative Technologies Laboratories (ITL), King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology (KAUST),Innovative Technologies Laboratories (ITL),Thuwal,Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]},{"raw_affiliation_string":"Innovative Technologies Laboratories (ITL), King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041803182","display_name":"Charalampos Antoniadis","orcid":"https://orcid.org/0000-0002-5902-5240"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Charalampos Antoniadis","raw_affiliation_strings":["King Abdullah University of Science and Technology (KAUST),Innovative Technologies Laboratories (ITL),Thuwal,Saudi Arabia","Innovative Technologies Laboratories (ITL), King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology (KAUST),Innovative Technologies Laboratories (ITL),Thuwal,Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]},{"raw_affiliation_string":"Innovative Technologies Laboratories (ITL), King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057380866","display_name":"Yehia Massoud","orcid":"https://orcid.org/0000-0002-6701-0639"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Yehia Massoud","raw_affiliation_strings":["King Abdullah University of Science and Technology (KAUST),Innovative Technologies Laboratories (ITL),Thuwal,Saudi Arabia","Innovative Technologies Laboratories (ITL), King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology (KAUST),Innovative Technologies Laboratories (ITL),Thuwal,Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]},{"raw_affiliation_string":"Innovative Technologies Laboratories (ITL), King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3631,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.49795404,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"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":0.9994999766349792,"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":0.9976999759674072,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.857553243637085},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7746412754058838},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.7529804110527039},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7159260511398315},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5790901184082031},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5225743055343628},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.46213120222091675},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42573603987693787},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3590627610683441},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2368711531162262}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.857553243637085},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7746412754058838},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.7529804110527039},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7159260511398315},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5790901184082031},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5225743055343628},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.46213120222091675},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42573603987693787},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3590627610683441},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2368711531162262},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/mwscas54063.2022.9859533","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mwscas54063.2022.9859533","pdf_url":null,"source":{"id":"https://openalex.org/S4363606568","display_name":"2022 IEEE 65th International Midwest Symposium on Circuits and Systems (MWSCAS)","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":"2022 IEEE 65th International Midwest Symposium on Circuits and Systems (MWSCAS)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.kaust.edu.sa:10754/680550","is_oa":false,"landing_page_url":"http://hdl.handle.net/10754/680550","pdf_url":null,"source":{"id":"https://openalex.org/S4306401596","display_name":"King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I71920554","host_organization_name":"King Abdullah University of Science and Technology","host_organization_lineage":["https://openalex.org/I71920554"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320326537","display_name":"University of Thessaly","ror":"https://ror.org/04v4g9h31"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1533861849","https://openalex.org/W1562651896","https://openalex.org/W1686810756","https://openalex.org/W1771384906","https://openalex.org/W1817277359","https://openalex.org/W2035890032","https://openalex.org/W2084827375","https://openalex.org/W2115175902","https://openalex.org/W2125336414","https://openalex.org/W2181871477","https://openalex.org/W2191779130","https://openalex.org/W2194775991","https://openalex.org/W2604379605","https://openalex.org/W2963173190","https://openalex.org/W2963307811","https://openalex.org/W2963566548","https://openalex.org/W2964052309","https://openalex.org/W2972729214","https://openalex.org/W2981728176","https://openalex.org/W3206008172","https://openalex.org/W4286378963","https://openalex.org/W6631943919","https://openalex.org/W6637373629","https://openalex.org/W6638480814","https://openalex.org/W6677400965","https://openalex.org/W6679388247","https://openalex.org/W6686050157","https://openalex.org/W6735927292","https://openalex.org/W6743555153","https://openalex.org/W6768882765","https://openalex.org/W6804225560"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"Speaker":[0],"diarization":[1,27,61,71,122],"is":[2],"a":[3,52,125],"task":[4],"to":[5,56,80,99,132],"identify":[6],"\u201cwho":[7],"spoke":[8],"when\u201d.":[9],"Moreover,":[10],"nowadays,":[11],"speakers\u2019":[12],"audio":[13,43,106],"clips":[14,44],"usually":[15],"are":[16],"accompanied":[17],"by":[18,34],"visual":[19,39],"information.":[20],"Thus,":[21],"in":[22,45,90,137],"the":[23,38,84,87,105,112,118,133,140],"latest":[24],"works,":[25],"speaker":[26,60,70,121],"systems":[28,72],"performance":[29],"has":[30],"been":[31],"improved":[32],"substantially":[33],"taking":[35],"advantage":[36],"of":[37],"information":[40],"synchronized":[41],"with":[42],"Audio-Visual":[46],"(AV)":[47],"content.":[48],"This":[49],"paper":[50],"presents":[51],"deep":[53],"learning":[54],"architecture":[55],"implement":[57],"an":[58],"AV":[59,69],"system":[62,93,123],"emphasizing":[63],"Voice":[64],"Activity":[65],"Detection":[66],"(VAD).":[67],"Traditional":[68],"use":[73],"hand-crafted":[74],"features,":[75],"like":[76],"Mel-frequency":[77],"cepstral":[78],"coefficients,":[79],"perform":[81],"VAD.":[82],"On":[83],"other":[85],"hand,":[86],"VAD":[88,127],"module":[89],"our":[91],"proposed":[92,119],"employs":[94],"Convolutional":[95],"Neural":[96],"Networks":[97],"(CNN)":[98],"learn":[100],"and":[101],"extract":[102],"features":[103],"from":[104],"waveforms":[107],"directly.":[108],"Experimental":[109],"results":[110],"on":[111],"AMI":[113],"Meeting":[114],"Corpus":[115],"indicated":[116],"that":[117],"multimodal":[120],"reaches":[124],"state-of-the-art":[126],"False":[128],"Alarm":[129],"rate":[130],"due":[131],"CNN-based":[134],"VAD,":[135],"which":[136],"turn":[138],"boosts":[139],"whole":[141],"system's":[142],"performance.":[143]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
