{"id":"https://openalex.org/W4297841622","doi":"https://doi.org/10.21437/interspeech.2022-11160","title":"Improving Voice Trigger Detection with Metric Learning","display_name":"Improving Voice Trigger Detection with Metric Learning","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841622","doi":"https://doi.org/10.21437/interspeech.2022-11160"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-11160","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11160","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5021356938","display_name":"Prateeth Nayak","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prateeth Nayak","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101768343","display_name":"Takuya Higuchi","orcid":"https://orcid.org/0000-0002-0361-7132"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takuya Higuchi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014436016","display_name":"Anmol Gupta","orcid":"https://orcid.org/0000-0003-0159-8780"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Anmol Gupta","raw_affiliation_strings":["Department of Computer Science, The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069699960","display_name":"Shivesh Ranjan","orcid":"https://orcid.org/0000-0002-7365-0253"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shivesh Ranjan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021880697","display_name":"Stephen Shum","orcid":"https://orcid.org/0000-0001-7292-8121"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stephen Shum","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113798270","display_name":"Siddharth Sigtia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siddharth Sigtia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009327522","display_name":"Erik Marchi","orcid":"https://orcid.org/0000-0002-5335-6356"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Erik Marchi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076956117","display_name":"Varun Lakshminarasimhan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Varun Lakshminarasimhan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115076654","display_name":"Minsik Cho","orcid":"https://orcid.org/0000-0003-0481-2682"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minsik Cho","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068392026","display_name":"Saurabh Adya","orcid":"https://orcid.org/0009-0000-4533-6577"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saurabh Adya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110720542","display_name":"Chandra Dhir","orcid":null},"institutions":[{"id":"https://openalex.org/I1305429384","display_name":"JPMorgan Chase & Co (United States)","ror":"https://ror.org/01x3kkr08","country_code":"US","type":"company","lineage":["https://openalex.org/I1305429384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chandra Dhir","raw_affiliation_strings":["JPMorgan Chase & Co"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JPMorgan Chase & Co","institution_ids":["https://openalex.org/I1305429384"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089360428","display_name":"Ahmed H. Tewfik","orcid":"https://orcid.org/0000-0002-2384-4391"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahmed Tewfik","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":12,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0827825,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1896","last_page":"1900"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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":0.9988999962806702,"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":0.703694224357605},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.659961998462677},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5583664774894714},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4729211926460266},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.19311439990997314},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1305815875530243}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.703694224357605},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.659961998462677},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5583664774894714},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4729211926460266},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.19311439990997314},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1305815875530243},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-11160","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11160","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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":34,"referenced_works":["https://openalex.org/W114193738","https://openalex.org/W1496120315","https://openalex.org/W1553469512","https://openalex.org/W1974745151","https://openalex.org/W1985371235","https://openalex.org/W1993409002","https://openalex.org/W2040226630","https://openalex.org/W2079623482","https://openalex.org/W2126203737","https://openalex.org/W2171019095","https://openalex.org/W2407023693","https://openalex.org/W2507319753","https://openalex.org/W2510945575","https://openalex.org/W2697044473","https://openalex.org/W2937292033","https://openalex.org/W2953219395","https://openalex.org/W2962707338","https://openalex.org/W2964187693","https://openalex.org/W2964525587","https://openalex.org/W2973094925","https://openalex.org/W2973226577","https://openalex.org/W3001493895","https://openalex.org/W3003903817","https://openalex.org/W3007913012","https://openalex.org/W3095321517","https://openalex.org/W3097018422","https://openalex.org/W3098773154","https://openalex.org/W3118331024","https://openalex.org/W3133600743","https://openalex.org/W3196705076","https://openalex.org/W3198035615","https://openalex.org/W4226020322","https://openalex.org/W4226135414","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2131711534","https://openalex.org/W2559837139","https://openalex.org/W1151175420","https://openalex.org/W2407342067","https://openalex.org/W2166690696","https://openalex.org/W2541680182"],"abstract_inverted_index":{"Voice":[0],"trigger":[1,37,45,68,98,122,153,158,185],"detection":[2,38,84,159],"is":[3,22,107,124],"an":[4,89],"important":[5],"task,":[6],"which":[7],"enables":[8],"activating":[9],"a":[10,14,18,41,65,73,79,114,128,138,168,173,180],"voice":[11,36,44,67,97,121,152,157,184],"assistant":[12],"when":[13,149],"target":[15,80,146],"user":[16],"speaks":[17],"keyword":[19],"phrase.A":[20],"detector":[21,46,69],"typically":[23,47],"trained":[24,108],"on":[25,52],"speech":[26,53,148],"data":[27],"independent":[28,43,96,183],"of":[29,76,134],"speaker":[30,42,81,95,182],"information":[31],"and":[32,112,137],"used":[33],"for":[34,117],"the":[35,92,102,105,132,151,164],"task.However,":[39],"such":[40,57],"suffers":[48],"from":[49,54,78],"performance":[50],"degradation":[51],"underrepresented":[55],"groups,":[56],"as":[58,127],"accented":[59],"speakers.In":[60],"this":[61],"work,":[62],"we":[63],"propose":[64],"novel":[66],"that":[70,163],"can":[71],"use":[72],"small":[74],"number":[75],"utterances":[77,136],"to":[82,101,145,179],"improve":[83],"accuracy.Our":[85],"proposed":[86,165],"model":[87],"employs":[88],"encoder-decoder":[90],"architecture.While":[91],"encoder":[93],"performs":[94],"detection,":[99],"similar":[100],"conventional":[103],"detector,":[104],"decoder":[106],"with":[109],"metric":[110],"learning":[111],"predicts":[113],"personalized":[115,120,141],"embedding":[116,142],"each":[118],"utterance.A":[119],"score":[123,130],"then":[125],"obtained":[126],"similarity":[129],"between":[131],"embeddings":[133],"enrollment":[135],"test":[139],"utterance.The":[140],"allows":[143],"adapting":[144],"speaker's":[147],"computing":[150],"score,":[154],"hence":[155],"improving":[156],"accuracy.Experimental":[160],"results":[161],"show":[162],"approach":[166],"achieves":[167],"38%":[169],"relative":[170],"reduction":[171],"in":[172],"false":[174],"rejection":[175],"rate":[176],"(FRR)":[177],"compared":[178],"baseline":[181],"model.":[186]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}