{"id":"https://openalex.org/W4408355973","doi":"https://doi.org/10.1109/icassp49660.2025.10889652","title":"Voice Conversion via Structural Entropy","display_name":"Voice Conversion via Structural Entropy","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355973","doi":"https://doi.org/10.1109/icassp49660.2025.10889652"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889652","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889652","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5076315968","display_name":"Linqin Wang","orcid":"https://orcid.org/0000-0001-6293-6742"},"institutions":[{"id":"https://openalex.org/I146071755","display_name":"Kunming University","ror":"https://ror.org/035rhx828","country_code":"CN","type":"education","lineage":["https://openalex.org/I146071755"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linqin Wang","raw_affiliation_strings":["Kunming University of Tech. and Sci.,Info. Engineering and Automation Yunnan Key Lab. of AI,Kunming,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunming University of Tech. and Sci.,Info. Engineering and Automation Yunnan Key Lab. of AI,Kunming,China","institution_ids":["https://openalex.org/I146071755"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100619287","display_name":"Zhengtao Yu","orcid":"https://orcid.org/0000-0002-4012-461X"},"institutions":[{"id":"https://openalex.org/I146071755","display_name":"Kunming University","ror":"https://ror.org/035rhx828","country_code":"CN","type":"education","lineage":["https://openalex.org/I146071755"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengtao Yu","raw_affiliation_strings":["Kunming University of Tech. and Sci.,Info. Engineering and Automation Yunnan Key Lab. of AI,Kunming,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunming University of Tech. and Sci.,Info. Engineering and Automation Yunnan Key Lab. of AI,Kunming,China","institution_ids":["https://openalex.org/I146071755"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017471172","display_name":"Shengxiang Gao","orcid":"https://orcid.org/0000-0002-2980-8420"},"institutions":[{"id":"https://openalex.org/I146071755","display_name":"Kunming University","ror":"https://ror.org/035rhx828","country_code":"CN","type":"education","lineage":["https://openalex.org/I146071755"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengxiang Gao","raw_affiliation_strings":["Kunming University of Tech. and Sci.,Info. Engineering and Automation Yunnan Key Lab. of AI,Kunming,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunming University of Tech. and Sci.,Info. Engineering and Automation Yunnan Key Lab. of AI,Kunming,China","institution_ids":["https://openalex.org/I146071755"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053889923","display_name":"Cunli Mao","orcid":null},"institutions":[{"id":"https://openalex.org/I146071755","display_name":"Kunming University","ror":"https://ror.org/035rhx828","country_code":"CN","type":"education","lineage":["https://openalex.org/I146071755"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cunli Mao","raw_affiliation_strings":["Kunming University of Tech. and Sci.,Info. Engineering and Automation Yunnan Key Lab. of AI,Kunming,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunming University of Tech. and Sci.,Info. Engineering and Automation Yunnan Key Lab. of AI,Kunming,China","institution_ids":["https://openalex.org/I146071755"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068973438","display_name":"Ling Dong","orcid":"https://orcid.org/0000-0003-1612-6671"},"institutions":[{"id":"https://openalex.org/I146071755","display_name":"Kunming University","ror":"https://ror.org/035rhx828","country_code":"CN","type":"education","lineage":["https://openalex.org/I146071755"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ling Dong","raw_affiliation_strings":["Kunming University of Tech. and Sci.,Info. Engineering and Automation Yunnan Key Lab. of AI,Kunming,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunming University of Tech. and Sci.,Info. Engineering and Automation Yunnan Key Lab. of AI,Kunming,China","institution_ids":["https://openalex.org/I146071755"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102000309","display_name":"Yuxin Huang","orcid":"https://orcid.org/0000-0003-4212-0644"},"institutions":[{"id":"https://openalex.org/I146071755","display_name":"Kunming University","ror":"https://ror.org/035rhx828","country_code":"CN","type":"education","lineage":["https://openalex.org/I146071755"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxin Huang","raw_affiliation_strings":["Kunming University of Tech. and Sci.,Info. Engineering and Automation Yunnan Key Lab. of AI,Kunming,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunming University of Tech. and Sci.,Info. Engineering and Automation Yunnan Key Lab. of AI,Kunming,China","institution_ids":["https://openalex.org/I146071755"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I146071755"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10860","display_name":"Speech and Audio Processing","score":0.9660999774932861,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9660999774932861,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9657999873161316,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5504199862480164},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4410858750343323},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32943806052207947},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08736827969551086},{"id":"https://openalex.org/keywords/thermodynamics","display_name":"Thermodynamics","score":0.062409400939941406}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5504199862480164},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4410858750343323},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32943806052207947},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08736827969551086},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.062409400939941406}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889652","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889652","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2338678442","https://openalex.org/W2576309025","https://openalex.org/W2890964092","https://openalex.org/W3098557217","https://openalex.org/W3163829335","https://openalex.org/W3197659778","https://openalex.org/W3209984917","https://openalex.org/W4372260053","https://openalex.org/W4372267192","https://openalex.org/W4372337821","https://openalex.org/W4385823432","https://openalex.org/W4392367760","https://openalex.org/W4393148023","https://openalex.org/W4395097571","https://openalex.org/W4401594478","https://openalex.org/W4401863527","https://openalex.org/W4403758858","https://openalex.org/W4404795636","https://openalex.org/W4409347088","https://openalex.org/W4409365180","https://openalex.org/W6762533536","https://openalex.org/W6783867762","https://openalex.org/W6805710207","https://openalex.org/W6847363464","https://openalex.org/W6866385851"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Voice":[0],"conversion":[1,89],"(VC)":[2],"aims":[3],"to":[4,9,163,183],"transform":[5],"a":[6,44,72,100,139],"person\u2019s":[7],"voice":[8],"resemble":[10],"that":[11,153,170],"of":[12,27,33,65,93,118,129],"another":[13],"person":[14],"while":[15,158],"maintaining":[16,159],"the":[17,25,31,58,66,87,94,104,119,126,135,145,177,181,187],"original":[18],"linguistic":[19],"content.":[20,189],"Existing":[21],"methods":[22],"suffer":[23],"from":[24,56,134,144,176],"blurring":[26],"speech":[28,68,96],"representations":[29,55,64,82],"and":[30,60,103,149],"leakage":[32],"prosody":[34],"information.":[35],"To":[36],"address":[37],"this":[38,40],"issue,":[39],"study":[41],"introduces":[42],"SEVC,":[43],"novel":[45],"neural":[46],"structural":[47,77],"entropy-based":[48],"VC":[49],"framework.":[50],"First,":[51],"we":[52],"extract":[53],"self-supervised":[54],"both":[57],"source":[59,95,120],"reference":[61,67,136,178],"speech.":[62,137],"The":[63],"are":[69,83],"structured":[70],"as":[71,99],"graph.":[73],"Using":[74],"two-dimensional":[75],"(2D)":[76],"entropy":[78],"(SE),":[79],"semantically":[80],"similar":[81],"clustered":[84],"together.":[85],"For":[86],"speaker":[88,156],"process,":[90],"each":[91,110],"frame":[92,117],"is":[97,112,122],"treated":[98],"new":[101],"node,":[102],"most":[105],"appropriate":[106],"semantic":[107,132,188],"cluster":[108,133],"for":[109],"node":[111],"identified":[113],"using":[114],"SE.":[115],"Each":[116],"representation":[121,128],"then":[123],"replaced":[124],"by":[125],"center":[127],"its":[130],"corresponding":[131],"Finally,":[138],"pretrained":[140],"vocoder":[141],"synthesizes":[142],"audio":[143],"transformed":[146],"representations.":[147],"Quantitative":[148],"qualitative":[150],"evaluations":[151],"demonstrate":[152],"SEVC":[154,171],"improves":[155],"similarity":[157],"intelligibility":[160],"scores":[161],"comparable":[162],"existing":[164],"methods.":[165],"Additionally,":[166],"experimental":[167],"results":[168],"indicate":[169],"effectively":[172],"disentangles":[173],"paralinguistic":[174],"features":[175],"speech,":[179],"allowing":[180],"model":[182],"better":[184],"focus":[185],"on":[186]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}