{"id":"https://openalex.org/W3163654539","doi":"https://doi.org/10.1109/icassp39728.2021.9414081","title":"One-Shot Voice Conversion Based on Speaker Aware Module","display_name":"One-Shot Voice Conversion Based on Speaker Aware Module","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163654539","doi":"https://doi.org/10.1109/icassp39728.2021.9414081","mag":"3163654539"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414081","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/A5100386104","display_name":"Ying Zhang","orcid":"https://orcid.org/0000-0002-2674-1638"},"institutions":[{"id":"https://openalex.org/I2801745840","display_name":"Kwai Chung Hospital","ror":"https://ror.org/05kz7bw59","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I1294586568","https://openalex.org/I2801745840"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Zhang","raw_affiliation_strings":["Kwai, Beijing, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kwai, Beijing, P.R. China","institution_ids":["https://openalex.org/I2801745840"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112489758","display_name":"Hao Che","orcid":"https://orcid.org/0009-0001-9852-320X"},"institutions":[{"id":"https://openalex.org/I2801745840","display_name":"Kwai Chung Hospital","ror":"https://ror.org/05kz7bw59","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I1294586568","https://openalex.org/I2801745840"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Che","raw_affiliation_strings":["Kwai, Beijing, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kwai, Beijing, P.R. China","institution_ids":["https://openalex.org/I2801745840"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100428285","display_name":"Jie Li","orcid":"https://orcid.org/0000-0002-7561-7043"},"institutions":[{"id":"https://openalex.org/I2801745840","display_name":"Kwai Chung Hospital","ror":"https://ror.org/05kz7bw59","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I1294586568","https://openalex.org/I2801745840"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Li","raw_affiliation_strings":["Kwai, Beijing, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kwai, Beijing, P.R. China","institution_ids":["https://openalex.org/I2801745840"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101744663","display_name":"Chenxing Li","orcid":"https://orcid.org/0009-0001-4226-7825"},"institutions":[{"id":"https://openalex.org/I2801745840","display_name":"Kwai Chung Hospital","ror":"https://ror.org/05kz7bw59","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I1294586568","https://openalex.org/I2801745840"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenxing Li","raw_affiliation_strings":["Kwai, Beijing, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kwai, Beijing, P.R. China","institution_ids":["https://openalex.org/I2801745840"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100658019","display_name":"Xiaorui Wang","orcid":"https://orcid.org/0000-0001-9633-1418"},"institutions":[{"id":"https://openalex.org/I2801745840","display_name":"Kwai Chung Hospital","ror":"https://ror.org/05kz7bw59","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I1294586568","https://openalex.org/I2801745840"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaorui Wang","raw_affiliation_strings":["Kwai, Beijing, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kwai, Beijing, P.R. China","institution_ids":["https://openalex.org/I2801745840"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100741750","display_name":"Zhongyuan Wang","orcid":"https://orcid.org/0000-0002-9796-488X"},"institutions":[{"id":"https://openalex.org/I2801745840","display_name":"Kwai Chung Hospital","ror":"https://ror.org/05kz7bw59","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I1294586568","https://openalex.org/I2801745840"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongyuan Wang","raw_affiliation_strings":["Kwai, Beijing, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kwai, Beijing, P.R. China","institution_ids":["https://openalex.org/I2801745840"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2801745840"],"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":"5959","last_page":"5963"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9965999722480774,"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":0.9962000250816345,"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":0.8261432647705078},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7215548753738403},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6428083181381226},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5858396887779236},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5390903353691101},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.48161715269088745},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4596739411354065},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4586184024810791},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45086416602134705},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3299681544303894}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8261432647705078},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7215548753738403},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6428083181381226},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5858396887779236},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5390903353691101},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.48161715269088745},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4596739411354065},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4586184024810791},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45086416602134705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3299681544303894},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414081","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":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1483144309","https://openalex.org/W1517202054","https://openalex.org/W2120847449","https://openalex.org/W2294351487","https://openalex.org/W2518172956","https://openalex.org/W2794490148","https://openalex.org/W2802935216","https://openalex.org/W2887264325","https://openalex.org/W2888922217","https://openalex.org/W2889048668","https://openalex.org/W2890964092","https://openalex.org/W2903538854","https://openalex.org/W2937579788","https://openalex.org/W2950662112","https://openalex.org/W2963091184","https://openalex.org/W2963242190","https://openalex.org/W2972659941","https://openalex.org/W2973154337","https://openalex.org/W3007550212","https://openalex.org/W6630905448","https://openalex.org/W6696767757","https://openalex.org/W6750489868","https://openalex.org/W6754095682","https://openalex.org/W6754473786","https://openalex.org/W6755811826","https://openalex.org/W6756663807"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1950940422","https://openalex.org/W4283822356","https://openalex.org/W2129146436","https://openalex.org/W2032507829","https://openalex.org/W2147282173","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162"],"abstract_inverted_index":{"Voice":[0],"conversion":[1,55,61],"(VC)":[2],"is":[3,30,99,112,123],"a":[4,38,52,69,81,85,92,103,107],"task":[5],"to":[6,23,33,74,101,106,125,146],"convert":[7],"the":[8,35,110,119,147,157,162],"voice":[9,36,54,60],"of":[10,41,115],"speech":[11,172],"while":[12],"preserving":[13],"its":[14],"linguistic":[15],"content.":[16],"Although":[17],"several":[18],"methods":[19],"have":[20],"been":[21],"proposed":[22,163],"enable":[24],"VC":[25],"with":[26,141],"non-parallel":[27],"data,":[28],"it":[29],"still":[31],"difficult":[32],"model":[34],"without":[37,62],"great":[39],"number":[40],"data":[42],"or":[43],"an":[44,63],"adaptive":[45],"process.":[46],"In":[47],"this":[48],"paper,":[49],"we":[50],"propose":[51],"speaker-aware":[53],"(SAVC)":[56],"system":[57],"realizing":[58],"one-shot":[59],"adaptation":[64],"stage.":[65],"The":[66,78,96],"SAVC":[67],"utilizes":[68],"speaker":[70,76,87,129,142,167],"aware":[71],"module":[72,149],"(SAM)":[73],"disentangle":[75],"embeddings.":[77,130],"SAM":[79],"comprises":[80],"dynamic":[82],"reference":[83,97],"encoder,":[84],"static":[86],"knowledge":[88],"block":[89],"(SKB),":[90],"and":[91,118,144,169],"multi-head":[93,120],"attention":[94,121],"layer.":[95],"encoder":[98],"used":[100],"compress":[102],"variable-length":[104],"utterance":[105],"fixed-length":[108],"vector,":[109],"SKB":[111],"made":[113],"up":[114],"pre-extraction":[116],"x-vectors,":[117],"layer":[122],"designed":[124],"generate":[126],"weighted":[127],"combined":[128],"Subsequently,":[131],"phonetic":[132],"pos-":[133],"teriorgrams":[134],"(PPGs)":[135],"as":[136],"context":[137],"encoding":[138],"are":[139],"concatenated":[140],"embeddings":[143],"sent":[145],"decoder":[148],"for":[150],"generating":[151],"acoustic":[152],"features.":[153],"Experimental":[154],"results":[155],"on":[156],"Aishell-1":[158],"corpus":[159],"show":[160],"that":[161],"method":[164],"can":[165],"improve":[166],"similarity":[168],"converted":[170],"utterances'":[171],"quality.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
