{"id":"https://openalex.org/W4372337821","doi":"https://doi.org/10.1109/icassp49357.2023.10096057","title":"Expressive-VC: Highly Expressive Voice Conversion with Attention Fusion of Bottleneck and Perturbation Features","display_name":"Expressive-VC: Highly Expressive Voice Conversion with Attention Fusion of Bottleneck and Perturbation Features","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372337821","doi":"https://doi.org/10.1109/icassp49357.2023.10096057"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096057","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096057","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5081164682","display_name":"Ziqian Ning","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]},{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziqian Ning","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China","Fuxi AI Lab, NetEase Inc., Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Fuxi AI Lab, NetEase Inc., Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049213273","display_name":"Qicong Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qicong Xie","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046479703","display_name":"Pengcheng Zhu","orcid":"https://orcid.org/0000-0001-8145-6023"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengcheng Zhu","raw_affiliation_strings":["NetEase Inc.,Fuxi AI Lab,Hangzhou,China","Fuxi AI Lab, NetEase Inc., Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Inc.,Fuxi AI Lab,Hangzhou,China","institution_ids":["https://openalex.org/I4210091137"]},{"raw_affiliation_string":"Fuxi AI Lab, NetEase Inc., Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106698700","display_name":"Zhichao Wang","orcid":"https://orcid.org/0000-0001-8075-1784"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhichao Wang","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009337933","display_name":"Liumeng Xue","orcid":"https://orcid.org/0000-0003-2815-8494"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liumeng Xue","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015560758","display_name":"Jixun Yao","orcid":"https://orcid.org/0000-0002-5324-7360"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jixun Yao","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036369578","display_name":"Mengxiao Bi","orcid":"https://orcid.org/0009-0007-6680-481X"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengxiao Bi","raw_affiliation_strings":["NetEase Inc.,Fuxi AI Lab,Hangzhou,China","Fuxi AI Lab, NetEase Inc., Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Inc.,Fuxi AI Lab,Hangzhou,China","institution_ids":["https://openalex.org/I4210091137"]},{"raw_affiliation_string":"Fuxi AI Lab, NetEase Inc., Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6106,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.91572821,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9972000122070312,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.7531599998474121},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7396335005760193},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7231905460357666},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5625247955322266},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.48558348417282104},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4102744162082672},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3444301187992096}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7531599998474121},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7396335005760193},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7231905460357666},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5625247955322266},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.48558348417282104},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4102744162082672},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3444301187992096},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096057","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096057","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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","score":0.5099999904632568,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1985709747","https://openalex.org/W2518172956","https://openalex.org/W2945478979","https://openalex.org/W2963373786","https://openalex.org/W2964041258","https://openalex.org/W2972313557","https://openalex.org/W2972849140","https://openalex.org/W3002433751","https://openalex.org/W3092028330","https://openalex.org/W3094635600","https://openalex.org/W3098557217","https://openalex.org/W3100378519","https://openalex.org/W3128910262","https://openalex.org/W3134921434","https://openalex.org/W3163475957","https://openalex.org/W3163568691","https://openalex.org/W3197478142","https://openalex.org/W3197659778","https://openalex.org/W3197943112","https://openalex.org/W3203407300","https://openalex.org/W4210970267","https://openalex.org/W4225322394","https://openalex.org/W4294311176","https://openalex.org/W4296068587","https://openalex.org/W4301371414","https://openalex.org/W4319586549","https://openalex.org/W4385245566","https://openalex.org/W6718379498","https://openalex.org/W6739901393","https://openalex.org/W6762533536","https://openalex.org/W6768192883","https://openalex.org/W6783867762","https://openalex.org/W6790220310","https://openalex.org/W6803547063"],"related_works":["https://openalex.org/W3130133758","https://openalex.org/W1927421023","https://openalex.org/W10581632","https://openalex.org/W3149582125","https://openalex.org/W1984347656","https://openalex.org/W1965141925","https://openalex.org/W2465421051","https://openalex.org/W652196294","https://openalex.org/W2127461790","https://openalex.org/W2069324367"],"abstract_inverted_index":{"Voice":[0],"conversion":[1,31],"for":[2],"highly":[3],"expressive":[4],"speech":[5,128,166],"is":[6,152,177],"challenging.":[7],"Current":[8],"approaches":[9],"struggle":[10],"with":[11,117,171],"the":[12,38,45,81,92,108,132,135,139,145,164,172],"balance":[13],"between":[14],"speaker":[15,119,169],"similarity,":[16],"intelligibility,":[17],"and":[18,44,55,67,80,94,121,124,138,167],"expressiveness.":[19],"To":[20],"address":[21],"this":[22],"problem,":[23],"we":[24,50],"propose":[25],"Expressive-VC,":[26],"a":[27,52,56,61,75,114],"novel":[28],"end-to-end":[29],"voice":[30],"framework":[32],"that":[33,150],"leverages":[34],"advantages":[35],"from":[36,74,113,163],"both":[37,159],"neural":[39],"bottleneck":[40],"feature":[41,142],"(BNF)":[42],"approach":[43],"information":[46],"perturbation":[47],"approach.":[48],"Specifically,":[49],"use":[51],"BNF":[53],"encoder":[54,58,116],"Perturbed-Wav":[57],"to":[59,64,143,154],"form":[60],"content":[62],"extractor":[63],"learn":[65],"linguistic":[66,93],"para-linguistic":[68,95],"features":[69,96,104,137],"respectively,":[70],"where":[71,101],"BNFs":[72],"come":[73],"robust":[76],"pre-trained":[77],"ASR":[78],"model":[79],"perturbed":[82],"wave":[83],"becomes":[84],"speaker-irrelevant":[85],"after":[86],"signal":[87],"perturbation.":[88],"We":[89],"further":[90],"fuse":[91],"through":[97],"an":[98],"attention":[99,109],"mechanism,":[100],"speaker-dependent":[102,140],"prosody":[103,115,141],"are":[105],"used":[106],"as":[107,129],"query,":[110],"which":[111],"results":[112],"target":[118,173],"embedding":[120],"normalized":[122],"pitch":[123],"energy":[125],"of":[126],"source":[127,165],"input.":[130],"Finally,":[131],"decoder":[133],"consumes":[134],"integrated":[136],"generate":[144],"converted":[146],"speech.":[147],"Experiments":[148],"show":[149],"Expressive-VC":[151],"superior":[153],"several":[155],"popular":[156],"systems,":[157],"achieving":[158],"high":[160,168],"expressiveness":[161],"captured":[162],"similarity":[170],"speaker;":[174],"meanwhile":[175],"intelligibility":[176],"well":[178],"maintained.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
