{"id":"https://openalex.org/W3024085360","doi":"https://doi.org/10.21437/odyssey.2020-62","title":"Personal VAD: Speaker-Conditioned Voice Activity Detection","display_name":"Personal VAD: Speaker-Conditioned Voice Activity Detection","publication_year":2020,"publication_date":"2020-05-15","ids":{"openalex":"https://openalex.org/W3024085360","doi":"https://doi.org/10.21437/odyssey.2020-62","mag":"3024085360"},"language":"en","primary_location":{"id":"doi:10.21437/odyssey.2020-62","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2020-62","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2020)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5058886181","display_name":"Shaojin Ding","orcid":"https://orcid.org/0000-0002-2108-3111"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaojin Ding","raw_affiliation_strings":["Texas A&M University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas A&M University, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418245","display_name":"Quan Wang","orcid":"https://orcid.org/0000-0001-6102-3407"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Quan Wang","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001306222","display_name":"Shuo-Yiin Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuo-Yiin Chang","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100688627","display_name":"Li Wan","orcid":"https://orcid.org/0000-0001-9775-405X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Wan","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050898122","display_name":"Ignacio L\u00f3pez Moreno","orcid":"https://orcid.org/0000-0002-0900-3473"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ignacio Lopez Moreno","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"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":false,"cited_by_count":89,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"433","last_page":"439"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"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":0.9972000122070312,"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":0.6663575172424316},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.553231418132782},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5167945623397827},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.46845412254333496},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.17526814341545105}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6663575172424316},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.553231418132782},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5167945623397827},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.46845412254333496},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.17526814341545105}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/odyssey.2020-62","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2020-62","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2020)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.49000000953674316,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1536583098","https://openalex.org/W1821462560","https://openalex.org/W1999454387","https://openalex.org/W2023582935","https://openalex.org/W2034940213","https://openalex.org/W2062335243","https://openalex.org/W2136439176","https://openalex.org/W2240641835","https://openalex.org/W2295098554","https://openalex.org/W2497335382","https://openalex.org/W2612434969","https://openalex.org/W2617258110","https://openalex.org/W2625979394","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2742061524","https://openalex.org/W2775336875","https://openalex.org/W2787752687","https://openalex.org/W2808706139","https://openalex.org/W2890964092","https://openalex.org/W2892300106","https://openalex.org/W2892620417","https://openalex.org/W2896538040","https://openalex.org/W2902094805","https://openalex.org/W2962760690","https://openalex.org/W2962788625","https://openalex.org/W2963470929","https://openalex.org/W2972495969","https://openalex.org/W2973062255"],"related_works":["https://openalex.org/W3087422378","https://openalex.org/W3162054169","https://openalex.org/W2368779261","https://openalex.org/W2029134149","https://openalex.org/W3135230428","https://openalex.org/W4319663602","https://openalex.org/W2044038981","https://openalex.org/W2556771176","https://openalex.org/W1971797761","https://openalex.org/W2778699561"],"abstract_inverted_index":{"In":[0],"this":[1,64],"paper,":[2],"we":[3,105],"propose":[4],"\"personal":[5],"VAD\",":[6],"a":[7,15,30,58,67,110,118],"system":[8,22,120],"to":[9,29,108,132],"detect":[10],"the":[11,19,27,42,48,75,80,89,134],"voice":[12],"activity":[13],"of":[14],"target":[16,43,76,95],"speaker":[17,77,81,96,100,127],"at":[18],"frame":[20],"level.This":[21],"is":[23,61,72],"useful":[24],"for":[25,41,91],"gating":[26],"inputs":[28],"streaming":[31],"on-device":[32],"speech":[33],"recognition":[34,128],"system,":[35],"such":[36],"that":[37,71,116],"it":[38],"only":[39,113],"triggers":[40],"user,":[44],"which":[45],"helps":[46],"reduce":[47],"computational":[49],"cost":[50],"and":[51,98,126],"battery":[52],"consumption,":[53],"especially":[54],"in":[55],"scenarios":[56],"where":[57,121],"keyword":[59],"detector":[60],"unpreferable.We":[62],"achieve":[63],"by":[65],"training":[66],"VAD-alike":[68],"neural":[69],"network":[70],"conditioned":[73],"on":[74],"embedding":[78],"or":[79],"verification":[82],"score.For":[83],"each":[84],"frame,":[85],"personal":[86],"VAD":[87,125],"outputs":[88],"probabilities":[90],"three":[92],"classes:":[93],"non-speech,":[94],"speech,":[97],"non-target":[99],"speech.Under":[101],"our":[102],"optimal":[103],"setup,":[104],"are":[106,130],"able":[107],"train":[109],"model":[111],"with":[112],"130K":[114],"parameters":[115],"outperforms":[117],"baseline":[119],"individually":[122],"trained":[123],"standard":[124],"networks":[129],"combined":[131],"perform":[133],"same":[135],"task.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":23},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}