{"id":"https://openalex.org/W3198452307","doi":"https://doi.org/10.21437/interspeech.2021-2161","title":"An Integrated Framework for Two-Pass Personalized Voice Trigger","display_name":"An Integrated Framework for Two-Pass Personalized Voice Trigger","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3198452307","doi":"https://doi.org/10.21437/interspeech.2021-2161","mag":"3198452307"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-2161","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-2161","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5039844745","display_name":"Dexin Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dexin Liao","raw_affiliation_strings":["School of Informatics, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100336919","display_name":"Jing Li","orcid":"https://orcid.org/0000-0002-3626-5815"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032683415","display_name":"Yiming Zhi","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Zhi","raw_affiliation_strings":["School of Informatics, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100448204","display_name":"Song Li","orcid":"https://orcid.org/0000-0002-6797-143X"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]},{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song Li","raw_affiliation_strings":["School of Informatics, Xiamen University, China","School of Electronic Science and Engineering, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Electronic Science and Engineering, Xiamen University, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011997254","display_name":"Qingyang Hong","orcid":"https://orcid.org/0000-0001-7380-8690"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyang Hong","raw_affiliation_strings":["School of Informatics, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103050255","display_name":"Lin Li","orcid":"https://orcid.org/0000-0002-5021-2648"},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Li","raw_affiliation_strings":["School of Electronic Science and Engineering, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Science and Engineering, Xiamen University, China","institution_ids":["https://openalex.org/I75867142"]}]}],"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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4633","last_page":"4637"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9997000098228455,"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":0.9993000030517578,"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":0.8219974637031555},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7101385593414307},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5935536026954651},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5838835835456848},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5475708842277527},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.5419891476631165},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49571311473846436},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4716170132160187},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.23716488480567932}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8219974637031555},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7101385593414307},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5935536026954651},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5838835835456848},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5475708842277527},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.5419891476631165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49571311473846436},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4716170132160187},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.23716488480567932},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-2161","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-2161","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6600000262260437}],"awards":[{"id":"https://openalex.org/G2299475589","display_name":null,"funder_award_id":"62001405","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3698338998","display_name":null,"funder_award_id":"61876160","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W2034940213","https://openalex.org/W2219249508","https://openalex.org/W2514741789","https://openalex.org/W2526425061","https://openalex.org/W2696967604","https://openalex.org/W2748488820","https://openalex.org/W2936774411","https://openalex.org/W2963628261","https://openalex.org/W2964187693","https://openalex.org/W2964247977","https://openalex.org/W2969985801","https://openalex.org/W2972389417","https://openalex.org/W2972743990","https://openalex.org/W2973226577","https://openalex.org/W3003903817","https://openalex.org/W3010983946","https://openalex.org/W3019293601","https://openalex.org/W3095012737","https://openalex.org/W3095949666","https://openalex.org/W3096831963","https://openalex.org/W3096976027","https://openalex.org/W3097018422","https://openalex.org/W3118331024","https://openalex.org/W3133600743","https://openalex.org/W3163421828","https://openalex.org/W4283014282","https://openalex.org/W4285789737","https://openalex.org/W4288265053","https://openalex.org/W4297775537","https://openalex.org/W4309845474"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W2144208207","https://openalex.org/W4389984014","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,50,68],"present":[4],"the":[5,47,62,65,80,84,92,95],"XMUSPEECH":[6],"system":[7,33,119],"for":[8,113],"Task":[9],"1":[10,18],"of":[11,35,83,94],"2020":[12],"Personalized":[13],"Voice":[14],"Trigger":[15],"Challenge":[16],"(PVTC2020).Task":[17],"is":[19,77,89,98,107],"a":[20,36,42,52,70],"joint":[21],"wake-up":[22],"word":[23],"detection":[24],"with":[25,79,91,100,124],"speaker":[26,43,87,114],"verification":[27,44],"on":[28],"close":[29],"talking":[30],"data.The":[31],"whole":[32],"consists":[34],"keyword":[37],"spotting":[38],"(KWS)":[39],"sub-system":[40],"and":[41,86],"(SV)":[45],"sub-system.For":[46],"KWS":[48],"system,":[49,67],"applied":[51],"Temporal":[53],"Depthwise":[54],"Separable":[55],"Convolution":[56],"Residual":[57],"Network":[58],"(TDSC-ResNet)":[59],"to":[60],"improve":[61],"system's":[63],"performance.For":[64],"SV":[66],"proposed":[69],"multi-task":[71],"learning":[72],"network,":[73],"where":[74],"phonetic":[75],"branch":[76,88,97],"trained":[78,90],"character":[81],"label":[82,93],"utterance,":[85],"speaker.Phonetic":[96],"optimized":[99],"connectionist":[101],"temporal":[102],"classification":[103],"(CTC)":[104],"loss,":[105],"which":[106],"treated":[108],"as":[109],"an":[110],"auxiliary":[111],"module":[112],"branch.Experiments":[115],"show":[116],"that":[117],"our":[118],"gets":[120],"significant":[121],"improvements":[122],"compared":[123],"baseline":[125],"system.":[126]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
