{"id":"https://openalex.org/W4392902857","doi":"https://doi.org/10.1109/icassp48485.2024.10446160","title":"SEF-VC: Speaker Embedding Free Zero-Shot Voice Conversion with Cross Attention","display_name":"SEF-VC: Speaker Embedding Free Zero-Shot Voice Conversion with Cross Attention","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902857","doi":"https://doi.org/10.1109/icassp48485.2024.10446160"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446160","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446160","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5011373660","display_name":"Junjie Li","orcid":"https://orcid.org/0000-0002-0249-9293"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junjie Li","raw_affiliation_strings":["AI Institute Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,X-LANCE Lab, Department of Computer Science and Engineering,Shanghai,China","X-LANCE Lab, Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"AI Institute Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,X-LANCE Lab, Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"X-LANCE Lab, Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101579214","display_name":"Yiwei Guo","orcid":"https://orcid.org/0009-0003-8114-2085"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiwei Guo","raw_affiliation_strings":["AI Institute Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,X-LANCE Lab, Department of Computer Science and Engineering,Shanghai,China","X-LANCE Lab, Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"AI Institute Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,X-LANCE Lab, Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"X-LANCE Lab, Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101293966","display_name":"Xie Chen","orcid":"https://orcid.org/0009-0004-4458-0753"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xie Chen","raw_affiliation_strings":["AI Institute Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,X-LANCE Lab, Department of Computer Science and Engineering,Shanghai,China","X-LANCE Lab, Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"AI Institute Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,X-LANCE Lab, Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"X-LANCE Lab, Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":["AI Institute Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,X-LANCE Lab, Department of Computer Science and Engineering,Shanghai,China","X-LANCE Lab, Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"AI Institute Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,X-LANCE Lab, Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"X-LANCE Lab, Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5011373660"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":5.5125,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.96189719,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"12296","last_page":"12300"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/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":0.9876999855041504,"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":0.7406899333000183},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.697577953338623},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.5934330224990845},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.546995997428894},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5332443714141846},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4802184998989105},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.46099498867988586},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.4525167942047119},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.4441388249397278},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4133874177932739},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3748888373374939},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0818694531917572},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06694215536117554}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7406899333000183},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.697577953338623},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.5934330224990845},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.546995997428894},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5332443714141846},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4802184998989105},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.46099498867988586},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.4525167942047119},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.4441388249397278},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4133874177932739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3748888373374939},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0818694531917572},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06694215536117554},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446160","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446160","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2532494225","https://openalex.org/W2804998325","https://openalex.org/W2890964092","https://openalex.org/W2972359262","https://openalex.org/W2972659941","https://openalex.org/W3097777922","https://openalex.org/W3140429000","https://openalex.org/W3154134465","https://openalex.org/W3160950295","https://openalex.org/W3161695192","https://openalex.org/W3196584150","https://openalex.org/W3197763626","https://openalex.org/W3209059054","https://openalex.org/W4221146610","https://openalex.org/W4224916404","https://openalex.org/W4224916568","https://openalex.org/W4225329057","https://openalex.org/W4280552695","https://openalex.org/W4375869015","https://openalex.org/W4378945745","https://openalex.org/W4381786045","https://openalex.org/W4386132131","https://openalex.org/W4386133927","https://openalex.org/W4393147067","https://openalex.org/W6631362777","https://openalex.org/W6752910514","https://openalex.org/W6762533536","https://openalex.org/W6769196770","https://openalex.org/W6776390925","https://openalex.org/W6783867762","https://openalex.org/W6805710207","https://openalex.org/W6810585344"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2696990509"],"abstract_inverted_index":{"Zero-shot":[0],"voice":[1,25,61,104],"conversion":[2,62,105],"(VC)":[3],"aims":[4],"to":[5,11,67,116,123],"transfer":[6],"the":[7,19,24,34,38,41,47,112],"source":[8],"speaker":[9,15,35,42,58,71],"timbre":[10,72],"arbitrary":[12],"unseen":[13],"target":[14,39,124],"timbre,":[16],"while":[17],"keeping":[18],"linguistic":[20],"content":[21],"unchanged.":[22],"Although":[23],"of":[26,37,97,114],"generated":[27],"speech":[28,75,119],"can":[29],"be":[30],"controlled":[31],"by":[32],"providing":[33],"embedding":[36,59],"speaker,":[40],"similarity":[43,122],"still":[44],"lags":[45],"behind":[46],"ground":[48],"truth":[49],"recordings.":[50],"In":[51],"this":[52],"paper,":[53],"we":[54],"propose":[55],"SEF-VC,":[56],"a":[57,77,91],"free":[60],"model,":[63],"which":[64],"is":[65],"designed":[66],"learn":[68],"and":[69,82,103,108],"incorporate":[70],"from":[73,86],"reference":[74,125,135],"via":[76],"powerful":[78],"position-agnostic":[79],"cross-attention":[80],"mechanism,":[81],"then":[83],"reconstruct":[84],"waveform":[85],"HuBERT":[87],"semantic":[88],"tokens":[89],"in":[90],"non-autoregressive":[92],"manner.":[93],"The":[94],"concise":[95],"design":[96],"SEF-VC":[98,115],"enhances":[99],"its":[100],"training":[101],"stability":[102],"performance.":[106],"Objective":[107],"subjective":[109],"evaluations":[110],"demonstrate":[111],"superiority":[113],"generate":[117],"high-quality":[118],"with":[120],"better":[121],"than":[126],"strong":[127],"zero-shot":[128],"VC":[129],"baselines,":[130],"even":[131],"for":[132],"very":[133],"short":[134],"speeches.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
