{"id":"https://openalex.org/W3203633372","doi":"https://doi.org/10.1109/icassp43922.2022.9746409","title":"Multi-Task Voice Activated Framework Using Self-Supervised Learning","display_name":"Multi-Task Voice Activated Framework Using Self-Supervised Learning","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3203633372","doi":"https://doi.org/10.1109/icassp43922.2022.9746409","mag":"3203633372"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746409","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746409","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015232966","display_name":"Shehzeen Hussain","orcid":"https://orcid.org/0000-0003-4693-2113"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shehzeen Hussain","raw_affiliation_strings":["University of California,San Diego","University of California, San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,San Diego","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"University of California, San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100695012","display_name":"Van Huan Nguyen","orcid":"https://orcid.org/0000-0001-9394-3371"},"institutions":[{"id":"https://openalex.org/I4210087596","display_name":"Qualcomm (United States)","ror":"https://ror.org/002zrf773","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087596"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Van Nguyen","raw_affiliation_strings":["Qualcomm Technologies, Inc.,San Diego,California","Qualcomm Technologies, Inc., San Diego, California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qualcomm Technologies, Inc.,San Diego,California","institution_ids":["https://openalex.org/I4210087596"]},{"raw_affiliation_string":"Qualcomm Technologies, Inc., San Diego, California","institution_ids":["https://openalex.org/I4210087596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100394780","display_name":"Shuhua Zhang","orcid":"https://orcid.org/0000-0001-8635-9214"},"institutions":[{"id":"https://openalex.org/I4210087596","display_name":"Qualcomm (United States)","ror":"https://ror.org/002zrf773","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087596"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuhua Zhang","raw_affiliation_strings":["Qualcomm Technologies, Inc.,San Diego,California","Qualcomm Technologies, Inc., San Diego, California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qualcomm Technologies, Inc.,San Diego,California","institution_ids":["https://openalex.org/I4210087596"]},{"raw_affiliation_string":"Qualcomm Technologies, Inc., San Diego, California","institution_ids":["https://openalex.org/I4210087596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009801065","display_name":"Erik Visser","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087596","display_name":"Qualcomm (United States)","ror":"https://ror.org/002zrf773","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087596"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erik Visser","raw_affiliation_strings":["Qualcomm Technologies, Inc.,San Diego,California","Qualcomm Technologies, Inc., San Diego, California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qualcomm Technologies, Inc.,San Diego,California","institution_ids":["https://openalex.org/I4210087596"]},{"raw_affiliation_string":"Qualcomm Technologies, Inc., San Diego, California","institution_ids":["https://openalex.org/I4210087596"]}]}],"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":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6137","last_page":"6141"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9976999759674072,"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/T10860","display_name":"Speech and Audio Processing","score":0.9962000250816345,"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/computer-science","display_name":"Computer science","score":0.8527838587760925},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6453268527984619},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6439653635025024},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6026324033737183},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.588436484336853},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5086963772773743},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.49960899353027344},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.487930029630661},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4483698904514313},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3821711838245392},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37908363342285156}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8527838587760925},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6453268527984619},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6439653635025024},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6026324033737183},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.588436484336853},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5086963772773743},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.49960899353027344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.487930029630661},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4483698904514313},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3821711838245392},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37908363342285156},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746409","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746409","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2726515241","https://openalex.org/W2769905613","https://openalex.org/W2794506738","https://openalex.org/W2797583228","https://openalex.org/W2916104401","https://openalex.org/W2963351448","https://openalex.org/W2963371159","https://openalex.org/W2963466847","https://openalex.org/W2972706975","https://openalex.org/W2981087920","https://openalex.org/W3010925296","https://openalex.org/W3020953549","https://openalex.org/W3034552680","https://openalex.org/W3036601975","https://openalex.org/W3082010634","https://openalex.org/W3088922629","https://openalex.org/W3099782249","https://openalex.org/W3144073776","https://openalex.org/W3162426298","https://openalex.org/W3163571828","https://openalex.org/W3166571445","https://openalex.org/W3196496149","https://openalex.org/W3197642003","https://openalex.org/W3198275944","https://openalex.org/W6736780073","https://openalex.org/W6750665317","https://openalex.org/W6780218876","https://openalex.org/W6787335539"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W3119978414","https://openalex.org/W2114097550","https://openalex.org/W2516975559","https://openalex.org/W2545741539","https://openalex.org/W3206647229","https://openalex.org/W4286904253","https://openalex.org/W2000885660","https://openalex.org/W1969408022","https://openalex.org/W2117995638"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1,12,107],"methods":[2],"such":[3],"as":[4],"wav2vec":[5,67,88],"2.0":[6,68,89],"have":[7],"shown":[8],"promising":[9],"results":[10,133],"in":[11,134],"speech":[13,19,25,85],"representations":[14,29,86,93],"from":[15],"unlabelled":[16],"and":[17,128,137,147,158,161],"untranscribed":[18],"data":[20],"that":[21,80],"are":[22,30],"useful":[23,40],"for":[24,41,63,70,94],"recognition.":[26],"Since":[27],"these":[28],"learned":[31],"without":[32],"any":[33],"task-specific":[34],"supervision,":[35],"they":[36],"can":[37],"also":[38],"be":[39],"other":[42],"voice":[43,72,116],"activated":[44,73,117],"tasks":[45,118],"like":[46],"speaker":[47,135],"verification,":[48],"keyword":[49,138,169],"spotting,":[50],"emotion":[51],"classification":[52],"etc.":[53],"In":[54],"our":[55,102,126],"work,":[56],"we":[57,100],"propose":[58],"a":[59,65,96,120],"general":[60],"purpose":[61],"framework":[62,103],"adapting":[64],"pre-trained":[66],"model":[69],"different":[71],"tasks.":[74],"We":[75],"develop":[76],"downstream":[77],"network":[78,112],"architectures":[79],"operate":[81],"on":[82,114,150,156,164],"the":[83,92,111],"contextualized":[84],"of":[87,125],"to":[90,104],"adapt":[91],"solving":[95],"given":[97],"task.":[98],"Finally,":[99],"extend":[101],"perform":[105],"multi-task":[106,129],"by":[108],"jointly":[109],"optimizing":[110],"parameters":[113],"multiple":[115],"using":[119],"shared":[121],"transformer":[122],"backbone.":[123],"Both":[124],"single":[127],"frameworks":[130],"achieve":[131,145],"state-of-the-art":[132],"verification":[136],"spotting":[139,170],"benchmarks.":[140],"Our":[141],"best":[142],"performing":[143],"models":[144],"1.98%":[146],"3.15%":[148],"EER":[149],"VoxCeleb1":[151,159],"test":[152],"set":[153],"when":[154],"trained":[155],"Vox-Celeb2":[157],"respectively,":[160],"98.23%":[162],"accuracy":[163],"Google":[165],"Speech":[166],"Commands":[167],"v1.0":[168],"dataset.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}
