{"id":"https://openalex.org/W3163929126","doi":"https://doi.org/10.1109/icassp39728.2021.9413396","title":"Investigation of Fast and Efficient Methods for Multi-Speaker Modeling and Speaker Adaptation","display_name":"Investigation of Fast and Efficient Methods for Multi-Speaker Modeling and Speaker Adaptation","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163929126","doi":"https://doi.org/10.1109/icassp39728.2021.9413396","mag":"3163929126"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413396","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413396","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5101398585","display_name":"Yibin Zheng","orcid":"https://orcid.org/0000-0001-9158-1813"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yibin Zheng","raw_affiliation_strings":["Tencent Inc,China","Tencent Inc, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Inc,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Inc, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100701662","display_name":"Xinhui Li","orcid":"https://orcid.org/0000-0002-8398-8741"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinhui Li","raw_affiliation_strings":["Tencent Inc,China","Tencent Inc, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Inc,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Inc, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100658678","display_name":"Li L\u00fc","orcid":"https://orcid.org/0000-0001-5230-3749"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Lu","raw_affiliation_strings":["Tencent Inc,China","Tencent Inc, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Inc,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Inc, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":0.2931,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.49915093,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"650","issue":null,"first_page":"6618","last_page":"6622"},"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":0.9973000288009644,"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":0.9966999888420105,"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":0.7850233316421509},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7166492938995361},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5877647399902344},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5447179079055786},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.5370188355445862},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4889568090438843},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4439636468887329},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.43835875391960144},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4183824360370636},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3371824622154236}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7850233316421509},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7166492938995361},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5877647399902344},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5447179079055786},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.5370188355445862},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4889568090438843},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4439636468887329},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.43835875391960144},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4183824360370636},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3371824622154236}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413396","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413396","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1731081199","https://openalex.org/W2612434969","https://openalex.org/W2619368999","https://openalex.org/W2766406951","https://openalex.org/W2767052532","https://openalex.org/W2788357188","https://openalex.org/W2794490148","https://openalex.org/W2795109282","https://openalex.org/W2808706139","https://openalex.org/W2892620417","https://openalex.org/W2903853691","https://openalex.org/W2942807473","https://openalex.org/W2962739369","https://openalex.org/W2963091184","https://openalex.org/W2963192573","https://openalex.org/W2963272440","https://openalex.org/W2963432880","https://openalex.org/W2963609956","https://openalex.org/W2963691546","https://openalex.org/W2963927338","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2969521066","https://openalex.org/W2972473628","https://openalex.org/W2972574864","https://openalex.org/W3008008574","https://openalex.org/W3015826515","https://openalex.org/W3025942077","https://openalex.org/W3096702751","https://openalex.org/W4295731579","https://openalex.org/W4298174729","https://openalex.org/W6637618735","https://openalex.org/W6737575990","https://openalex.org/W6745232783","https://openalex.org/W6748573829","https://openalex.org/W6748588790","https://openalex.org/W6749489859","https://openalex.org/W6750489868","https://openalex.org/W6752888775","https://openalex.org/W6755135894","https://openalex.org/W6757322325","https://openalex.org/W6765987481","https://openalex.org/W6769900187"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W66821593","https://openalex.org/W2149220986","https://openalex.org/W1521299571","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W4235705411","https://openalex.org/W1493012537","https://openalex.org/W2144470400","https://openalex.org/W2911612049"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,87,156],"propose":[4,101],"a":[5,51,55,60,102,159,164,169],"novel":[6],"method":[7,117],"for":[8,82,163],"fast":[9],"and":[10,21,59,78,84,97,100,125,135,153],"efficient":[11,85],"few-shot":[12],"TTS":[13],"task,":[14],"which":[15,167],"is":[16,29],"able":[17],"to":[18,32,64,106,142],"disentangle":[19],"linguistic":[20,39],"speaker":[22,35,43,52,61,66,126,171],"representations.":[23,40],"Specifically,":[24],"an":[25,129],"adversarial":[26],"training":[27],"strategy":[28],"firstly":[30],"employed":[31],"wipe":[33],"out":[34],"information":[36,74],"from":[37,47],"the":[38,42,90,95,108,115],"Then":[41],"representations":[44],"are":[45,70],"extracted":[46],"audio":[48,98],"signals":[49],"by":[50],"encoder":[53],"with":[54,128,145],"random":[56],"sampling":[57],"mechanism":[58],"classifier,":[62],"aiming":[63],"extract":[65],"embedding":[67],"features":[68],"that":[69],"independent":[71],"of":[72,133,161,173],"content":[73],"(such":[75],"as":[76],"prosody":[77],"style":[79],"etc).":[80],"Meanwhile,":[81],"faster":[83,152],"adaptation,":[86],"further":[88],"introduce":[89],"prior":[91],"alignment":[92],"knowledge":[93],"between":[94],"text":[96],"pairs":[99],"multi-alignment":[103],"guided":[104],"attention":[105,109],"help":[107],"learning.":[110],"The":[111],"Experimental":[112],"results":[113],"show":[114],"proposed":[116],"not":[118],"only":[119],"could":[120],"generate":[121],"higher":[122],"speech":[123],"quality":[124],"similarity":[127],"average":[130],"absolute":[131],"improvement":[132],"0.26":[134],"0.30":[136],"in":[137],"MOS":[138,160],"respectively,":[139],"when":[140],"adapting":[141],"new":[143],"speakers":[144],"20":[146],"utterances,":[147],"but":[148],"also":[149],"converge":[150],"much":[151],"efficient.":[154],"More-over,":[155],"can":[157],"achieve":[158],"4.45":[162],"premium":[165],"voice,":[166],"outperforms":[168],"single":[170],"model":[172],"4.23.1":[174]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}