{"id":"https://openalex.org/W4415708378","doi":"https://doi.org/10.1109/icme59968.2025.11209204","title":"AVENet: Disentangling Features by Approximating Average Features for Voice Conversion","display_name":"AVENet: Disentangling Features by Approximating Average Features for Voice Conversion","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708378","doi":"https://doi.org/10.1109/icme59968.2025.11209204"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209204","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5067816529","display_name":"Wenyu Wang","orcid":"https://orcid.org/0000-0001-6772-1839"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenyu Wang","raw_affiliation_strings":["Xi’an Jiaotong University,School of Software Engineering,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,School of Software Engineering,Xi’an,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111363141","display_name":"Yiquan Zhou","orcid":"https://orcid.org/0009-0002-1453-3820"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiquan Zhou","raw_affiliation_strings":["Xi’an Jiaotong University,School of Software Engineering,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,School of Software Engineering,Xi’an,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068185614","display_name":"Jihua Zhu","orcid":"https://orcid.org/0000-0002-3081-8781"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jihua Zhu","raw_affiliation_strings":["Xi’an Jiaotong University,School of Software Engineering,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,School of Software Engineering,Xi’an,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113430879","display_name":"Hongwu Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongwu Ding","raw_affiliation_strings":["Anhui University,School of Computer Science and Technology,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui University,School of Computer Science and Technology,Hefei,China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100622261","display_name":"Jiacheng Xu","orcid":"https://orcid.org/0000-0002-9292-6999"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiacheng Xu","raw_affiliation_strings":["East China Normal University,School of Software Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University,School of Software Engineering,Shanghai,China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041766601","display_name":"Shihao Li","orcid":"https://orcid.org/0009-0005-0520-2319"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shihao Li","raw_affiliation_strings":["Union Wheatland Culture and Media Ltd.,Division of Music and Audio,Chengdu,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Union Wheatland Culture and Media Ltd.,Division of Music and Audio,Chengdu,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8652999997138977,"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":0.8652999997138977,"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/T10863","display_name":"Voice and Speech Disorders","score":0.0689999982714653,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.013000000268220901,"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/feature","display_name":"Feature (linguistics)","score":0.7484999895095825},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.6312000155448914},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5644999742507935},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4715000092983246},{"id":"https://openalex.org/keywords/feature-matching","display_name":"Feature matching","score":0.4431999921798706},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.40310001373291016},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.3765000104904175}],"concepts":[{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7484999895095825},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6507999897003174},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6353999972343445},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.6312000155448914},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5644999742507935},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4715000092983246},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.4431999921798706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43860000371932983},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.40310001373291016},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.3765000104904175},{"id":"https://openalex.org/C2776639384","wikidata":"https://www.wikidata.org/wiki/Q840396","display_name":"Ideal (ethics)","level":2,"score":0.3720000088214874},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.3249000012874603},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3237999975681305},{"id":"https://openalex.org/C89051679","wikidata":"https://www.wikidata.org/wiki/Q627770","display_name":"Voice-onset time","level":3,"score":0.2799000144004822},{"id":"https://openalex.org/C168031717","wikidata":"https://www.wikidata.org/wiki/Q1530280","display_name":"Balance (ability)","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2671999931335449}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209204","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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":25,"referenced_works":["https://openalex.org/W2518172956","https://openalex.org/W2576309025","https://openalex.org/W2747874407","https://openalex.org/W2902070858","https://openalex.org/W3002433751","https://openalex.org/W3083423753","https://openalex.org/W3094635600","https://openalex.org/W3097777922","https://openalex.org/W3140429000","https://openalex.org/W3163475957","https://openalex.org/W3196667132","https://openalex.org/W3197478142","https://openalex.org/W3197943112","https://openalex.org/W3198533616","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3210530853","https://openalex.org/W4225322394","https://openalex.org/W4280552695","https://openalex.org/W4319586549","https://openalex.org/W4372260053","https://openalex.org/W4375869253","https://openalex.org/W4385823163","https://openalex.org/W4386158910","https://openalex.org/W4402980879"],"related_works":[],"abstract_inverted_index":{"Voice":[0],"conversion":[1],"(VC)":[2],"has":[3],"made":[4],"progress":[5],"in":[6,29,84],"feature":[7,40,96,140],"disentanglement,":[8],"but":[9],"it":[10],"is":[11,57],"still":[12],"difficult":[13],"to":[14,51,106],"balance":[15],"timbre":[16],"and":[17,32,88,111],"content":[18,48],"information.":[19],"This":[20],"paper":[21],"evaluates":[22],"the":[23,53,61,81,94,104,121,146],"pre-trained":[24],"model":[25],"features":[26,62,108,125],"commonly":[27],"used":[28],"voice":[30],"conversion,":[31],"proposes":[33],"an":[34,46],"innovative":[35],"method":[36],"for":[37],"disentangling":[38,141],"speech":[39,67,139],"representations.":[41],"Specifically,":[42],"we":[43,74,101],"first":[44],"propose":[45],"ideal":[47],"feature,":[49,55],"referred":[50],"as":[52,109],"average":[54,95,115],"which":[56],"calculated":[58],"by":[59],"averaging":[60],"within":[63,126],"frame-level":[64],"aligned":[65],"parallel":[66],"(FAPS)":[68],"data.":[69],"For":[70],"generating":[71],"FAPS":[72],"data,":[73],"utilize":[75],"a":[76,85,127],"technique":[77],"that":[78],"involves":[79],"freezing":[80],"duration":[82],"predictor":[83],"Text-to-Speech":[86],"system":[87],"manipulating":[89],"speaker":[90],"embedding.":[91],"To":[92],"fit":[93],"on":[97,120],"traditional":[98],"VC":[99,128],"datasets,":[100],"then":[102],"design":[103],"AVENet":[105],"take":[107],"input":[110],"generate":[112],"closely":[113],"matching":[114],"features.":[116],"Experiments":[117],"are":[118],"conducted":[119],"performance":[122],"of":[123,148],"AVENet-extracted":[124],"system.":[129],"The":[130],"experimental":[131],"results":[132],"demonstrate":[133],"its":[134],"superiority":[135],"over":[136],"multiple":[137],"current":[138],"methods.":[142],"These":[143],"findings":[144],"affirm":[145],"effectiveness":[147],"our":[149],"disentanglement":[150],"approach.":[151]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}