{"id":"https://openalex.org/W3160950295","doi":"https://doi.org/10.1109/icassp39728.2021.9414975","title":"Zero-Shot Voice Conversion with Adjusted Speaker Embeddings and Simple Acoustic Features","display_name":"Zero-Shot Voice Conversion with Adjusted Speaker Embeddings and Simple Acoustic Features","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160950295","doi":"https://doi.org/10.1109/icassp39728.2021.9414975","mag":"3160950295"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414975","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414975","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":"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/A5032810766","display_name":"Zhiyuan Tan","orcid":"https://orcid.org/0009-0004-3876-1961"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhiyuan Tan","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,Tianjin,China","College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027428789","display_name":"Jianguo Wei","orcid":"https://orcid.org/0000-0002-8964-9759"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianguo Wei","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,Tianjin,China","College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006839468","display_name":"Junhai Xu","orcid":"https://orcid.org/0000-0002-4289-647X"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junhai Xu","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,Tianjin,China","College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100654741","display_name":"Yuqing He","orcid":"https://orcid.org/0000-0003-1666-4330"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqing He","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,Tianjin,China","College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082286929","display_name":"Wenhuan Lu","orcid":"https://orcid.org/0000-0002-7951-8907"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhuan Lu","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,Tianjin,China","College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5032810766"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":1.5489,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.85860657,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5964","last_page":"5968"},"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":0.9991000294685364,"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":0.9969000220298767,"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/spectrogram","display_name":"Spectrogram","score":0.7409100532531738},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7241745591163635},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7131261825561523},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6851283311843872},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5397033095359802},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5353257060050964},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4830108880996704},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.478799432516098},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.46789348125457764},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.421254426240921},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4017517566680908},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3611699938774109},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.271104097366333},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1343507468700409},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07939934730529785}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7409100532531738},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7241745591163635},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7131261825561523},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6851283311843872},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5397033095359802},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5353257060050964},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4830108880996704},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.478799432516098},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.46789348125457764},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.421254426240921},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4017517566680908},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3611699938774109},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.271104097366333},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1343507468700409},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07939934730529785},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414975","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414975","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1517202054","https://openalex.org/W2019849101","https://openalex.org/W2022125261","https://openalex.org/W2056852181","https://openalex.org/W2114659828","https://openalex.org/W2115747813","https://openalex.org/W2123771434","https://openalex.org/W2127520494","https://openalex.org/W2156142001","https://openalex.org/W2471520273","https://openalex.org/W2473388484","https://openalex.org/W2518312472","https://openalex.org/W2527729766","https://openalex.org/W2532494225","https://openalex.org/W2547364378","https://openalex.org/W2577042574","https://openalex.org/W2747744257","https://openalex.org/W2808706139","https://openalex.org/W2885820941","https://openalex.org/W2889061305","https://openalex.org/W2902070858","https://openalex.org/W2937579788","https://openalex.org/W2938983457","https://openalex.org/W2945478979","https://openalex.org/W2949281321","https://openalex.org/W2962788625","https://openalex.org/W2963035245","https://openalex.org/W2963432880","https://openalex.org/W2963539064","https://openalex.org/W2964135678","https://openalex.org/W2964544342","https://openalex.org/W3015209900","https://openalex.org/W3015434413","https://openalex.org/W3015805741","https://openalex.org/W3102628737","https://openalex.org/W6726442046","https://openalex.org/W6728445508","https://openalex.org/W6732251480","https://openalex.org/W6752888775","https://openalex.org/W6762533536","https://openalex.org/W6936113694"],"related_works":["https://openalex.org/W3119288895","https://openalex.org/W2185075503","https://openalex.org/W2104528589","https://openalex.org/W4229940372","https://openalex.org/W2186375278","https://openalex.org/W2749720872","https://openalex.org/W2793748347","https://openalex.org/W4250904811","https://openalex.org/W2155047054","https://openalex.org/W2379120504"],"abstract_inverted_index":{"Zero-shot":[0],"voice":[1],"conversion":[2],"(VC)":[3],"where":[4],"both":[5],"source":[6],"and":[7,98,137],"target":[8],"speakers":[9],"are":[10],"unseen":[11,43,61],"in":[12,112,116,133],"the":[13,57,80,117,128],"training":[14],"dataset":[15],"has":[16],"become":[17],"a":[18,34,48],"new":[19],"research":[20],"direction.":[21],"Using":[22],"speaker":[23,31,58,65],"embeddings":[24,59,66],"instead":[25],"of":[26,60,77,89,92,130,135],"one-hot":[27],"vectors":[28],"to":[29,55,67,83],"represent":[30],"identity":[32],"is":[33,79],"key":[35],"point,":[36],"which":[37],"makes":[38],"VC":[39,93],"models":[40],"work":[41],"on":[42,70],"speakers.":[44,62],"In":[45,73,87],"our":[46,124],"work,":[47],"newly":[49],"designed":[50],"neural":[51],"network":[52],"was":[53],"used":[54],"adjust":[56],"This":[63,108],"enables":[64],"perform":[68],"better":[69],"zero-shot":[71,85],"VC.":[72,86],"addition,":[74],"disentangled":[75],"representation":[76],"features":[78,91,103],"mainstream":[81],"method":[82],"achieve":[84],"terms":[88,134],"input":[90],"model,":[94],"we":[95],"use":[96],"Mel-cepstral":[97],"F0":[99,110],"as":[100],"simple":[101],"acoustic":[102],"(SAF)":[104],"rather":[105],"than":[106],"Mel-spectrograms.":[107],"avoids":[109],"conflicts":[111],"decoder":[113],"that":[114,123],"existed":[115],"previous":[118],"methods.":[119],"The":[120],"evaluations":[121],"demonstrate":[122],"proposed":[125],"methods":[126],"improve":[127],"quality":[129],"converted":[131],"speech":[132],"naturalness":[136],"similarity.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}