{"id":"https://openalex.org/W4417073290","doi":"https://doi.org/10.1145/3743093.3771038","title":"FabasedVC: Enhancing Voice Conversion with Text Modality Fusion and Phoneme-Level SSL Features","display_name":"FabasedVC: Enhancing Voice Conversion with Text Modality Fusion and Phoneme-Level SSL Features","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W4417073290","doi":"https://doi.org/10.1145/3743093.3771038"},"language":null,"primary_location":{"id":"doi:10.1145/3743093.3771038","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3771038","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3771038","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3771038","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Wenyu Wang","orcid":"https://orcid.org/0009-0005-4849-5035"},"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":["School of Software Engineering, Xi'an Jiaotong University, Xi'an, China and SYKI-SPEECH Team, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0005-4849-5035","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, China and SYKI-SPEECH Team, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhetao Hu","orcid":"https://orcid.org/0009-0008-1453-0949"},"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":"Zhetao Hu","raw_affiliation_strings":["School of Software Engineering, Xi'an Jiaotong University, Xi'an, China and SYKI-SPEECH Team, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0008-1453-0949","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, China and SYKI-SPEECH Team, 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":["School of Software Engineering, Xi'an Jiaotong University, Xi'an, China; SYKI-SPEECH Team, Xi'an, China and AI Platform Department, bilibili, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0002-1453-3820","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, China; SYKI-SPEECH Team, Xi'an, China and AI Platform Department, bilibili, Shanghai, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113695728","display_name":"Jiacheng Xu","orcid":"https://orcid.org/0009-0004-2755-1256"},"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":["School of Software Engineering, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0004-2755-1256","affiliations":[{"raw_affiliation_string":"School of Software Engineering, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhiyu Wu","orcid":"https://orcid.org/0009-0001-0075-6380"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyu Wu","raw_affiliation_strings":["School of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0001-0075-6380","affiliations":[{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chen Li","orcid":"https://orcid.org/0000-0003-2523-9141"},"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":"Chen Li","raw_affiliation_strings":["School of Software Engineering, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0003-2523-9141","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":null,"display_name":"Shihao Li","orcid":"https://orcid.org/0009-0008-1989-2842"},"institutions":[{"id":"https://openalex.org/I2799285397","display_name":"Sichuan Conservatory of Music","ror":"https://ror.org/01khb1c27","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799285397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shihao Li","raw_affiliation_strings":["Division of Music and Audio, Union Wheatland Culture and Media Ltd., Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0008-1989-2842","affiliations":[{"raw_affiliation_string":"Division of Music and Audio, Union Wheatland Culture and Media Ltd., Chengdu, China","institution_ids":["https://openalex.org/I2799285397"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7678999900817871,"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":0.7678999900817871,"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":0.12020000070333481,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.020999999716877937,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.6468999981880188},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.6333000063896179},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6126000285148621},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5968999862670898},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5889999866485596},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5178999900817871},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48559999465942383},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.42890000343322754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7932000160217285},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6743000149726868},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.6468999981880188},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6333000063896179},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6126000285148621},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5968999862670898},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5889999866485596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5557000041007996},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5178999900817871},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48559999465942383},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.42890000343322754},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4196999967098236},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41510000824928284},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.3808000087738037},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3361000120639801},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.33559998869895935},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3743093.3771038","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3771038","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3771038","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3743093.3771038","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3771038","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3771038","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320336350","display_name":"Key Research and Development Projects of Shaanxi Province","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417073290.pdf","grobid_xml":"https://content.openalex.org/works/W4417073290.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W2017425464","https://openalex.org/W2121387787","https://openalex.org/W2156142001","https://openalex.org/W2576309025","https://openalex.org/W2952370363","https://openalex.org/W2963609956","https://openalex.org/W3016137096","https://openalex.org/W3083423753","https://openalex.org/W3158374895","https://openalex.org/W3162512456","https://openalex.org/W3196667132","https://openalex.org/W3197659778","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/W4283067311","https://openalex.org/W4372260053","https://openalex.org/W4372337821","https://openalex.org/W4381786045","https://openalex.org/W4385823163","https://openalex.org/W4385823416","https://openalex.org/W4386158910"],"related_works":[],"abstract_inverted_index":{"In":[0],"voice":[1],"conversion":[2],"(VC),":[3],"it":[4],"is":[5,47,113],"crucial":[6],"to":[7,25,36,75,115,150],"preserve":[8],"complete":[9],"semantic":[10],"information":[11],"while":[12],"accurately":[13],"modeling":[14],"the":[15,37,89,118,124],"target":[16,38,125],"speaker\u2019s":[17],"timbre":[18],"and":[19,34,64,83,101,121,141],"prosody.":[20],"This":[21],"paper":[22],"proposes":[23],"FabasedVC":[24],"achieve":[26],"VC":[27,51],"with":[28],"enhanced":[29],"similarity":[30],"in":[31,136],"timbre,":[32],"prosody,":[33],"duration":[35,66,111],"speaker,":[39],"as":[40,42,79],"well":[41],"improved":[43],"content":[44,142],"integrity.":[45,143],"It":[46],"an":[48],"end-to-end":[49],"VITS-based":[50],"system":[52],"that":[53,130,147],"integrates":[54],"relevant":[55],"textual":[56],"modality":[57],"information,":[58],"phoneme-level":[59,94],"self-supervised":[60],"learning":[61],"(SSL)":[62],"features,":[63],"a":[65,71,110],"predictor.":[67],"Specifically,":[68],"we":[69],"employ":[70],"text":[72],"feature":[73],"encoder":[74],"encode":[76],"attributes":[77],"such":[78],"text,":[80],"phonemes,":[81],"tones":[82],"BERT":[84],"features.":[85],"We":[86,144],"then":[87],"process":[88],"frame-level":[90],"SSL":[91],"features":[92,95],"into":[93],"using":[96],"two":[97],"methods:":[98],"average":[99],"pooling":[100],"attention":[102],"mechanism":[103],"based":[104],"on":[105],"each":[106],"phoneme\u2019s":[107],"duration.":[108],"Moreover,":[109],"predictor":[112],"incorporated":[114],"better":[116],"align":[117],"speech":[119],"rate":[120],"prosody":[122],"of":[123,138],"speaker.":[126],"Experimental":[127],"results":[128],"demonstrate":[129],"our":[131,151],"method":[132],"outperforms":[133],"competing":[134],"systems":[135],"terms":[137],"naturalness,":[139],"similarity,":[140],"strongly":[145],"recommend":[146],"readers":[148],"listen":[149],"samples.1":[152]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-12-06T00:00:00"}