{"id":"https://openalex.org/W4386536200","doi":"https://doi.org/10.1109/taslp.2023.3313414","title":"MSM-VC: High-Fidelity Source Style Transfer for Non-Parallel Voice Conversion by Multi-Scale Style Modeling","display_name":"MSM-VC: High-Fidelity Source Style Transfer for Non-Parallel Voice Conversion by Multi-Scale Style Modeling","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386536200","doi":"https://doi.org/10.1109/taslp.2023.3313414"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3313414","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/taslp.2023.3313414","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/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":["ASLP Lab, School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-8075-1784","affiliations":[{"raw_affiliation_string":"ASLP Lab, School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021472684","display_name":"Xinsheng Wang","orcid":"https://orcid.org/0000-0003-1826-7419"},"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":"Xinsheng Wang","raw_affiliation_strings":["School of Software Engineering, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0003-1826-7419","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"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":["ASLP Lab, School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASLP Lab, School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055592507","display_name":"Tao Li","orcid":"https://orcid.org/0000-0001-5578-3960"},"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":"Tao Li","raw_affiliation_strings":["ASLP Lab, School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-5578-3960","affiliations":[{"raw_affiliation_string":"ASLP Lab, School of Computer Science, Northwestern Polytechnical University, Xi'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":["ASLP Lab, School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-8234-0823","affiliations":[{"raw_affiliation_string":"ASLP Lab, School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103162279","display_name":"Qiao Tian","orcid":"https://orcid.org/0000-0002-4078-1273"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiao Tian","raw_affiliation_strings":["ByteDance SAMI Group, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance SAMI Group, Shanghai, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100339106","display_name":"Yu\u2010Ping Wang","orcid":"https://orcid.org/0000-0001-9340-5864"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuping Wang","raw_affiliation_strings":["ByteDance SAMI Group, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance SAMI Group, Shanghai, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2345,"currency":"USD","value_usd":2345},"apc_paid":null,"fwci":0.6568,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.75630259,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":97},"biblio":{"volume":"31","issue":null,"first_page":"3883","last_page":"3895"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9973999857902527,"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":0.9973999857902527,"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":0.9661999940872192,"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":0.965499997138977,"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":0.7303961515426636},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6733907461166382},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.6426856517791748},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.4586593508720398},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3819001019001007},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3204893469810486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7303961515426636},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6733907461166382},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.6426856517791748},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.4586593508720398},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3819001019001007},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3204893469810486},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"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/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3313414","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/taslp.2023.3313414","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.44999998807907104,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1977362459","https://openalex.org/W2091318760","https://openalex.org/W2120605154","https://openalex.org/W2141340689","https://openalex.org/W2156477760","https://openalex.org/W2518172956","https://openalex.org/W2532494225","https://openalex.org/W2759925408","https://openalex.org/W2885800352","https://openalex.org/W2896457183","https://openalex.org/W2902070858","https://openalex.org/W2904459034","https://openalex.org/W2963091184","https://openalex.org/W2963539064","https://openalex.org/W2964135678","https://openalex.org/W2964243274","https://openalex.org/W2972659941","https://openalex.org/W2973158936","https://openalex.org/W3007067948","https://openalex.org/W3010916717","https://openalex.org/W3015598461","https://openalex.org/W3016159759","https://openalex.org/W3024869864","https://openalex.org/W3094635600","https://openalex.org/W3097777922","https://openalex.org/W3097892637","https://openalex.org/W3146550708","https://openalex.org/W3152136404","https://openalex.org/W3158374895","https://openalex.org/W3160329778","https://openalex.org/W3161695192","https://openalex.org/W3163568691","https://openalex.org/W3163573274","https://openalex.org/W3168542456","https://openalex.org/W3194143312","https://openalex.org/W3194347141","https://openalex.org/W3197659778","https://openalex.org/W3197704090","https://openalex.org/W3197943112","https://openalex.org/W3198082505","https://openalex.org/W3198104520","https://openalex.org/W3203407300","https://openalex.org/W3205154814","https://openalex.org/W3207354624","https://openalex.org/W3210530853","https://openalex.org/W3216296943","https://openalex.org/W4210774711","https://openalex.org/W4226225516","https://openalex.org/W4226421465","https://openalex.org/W4226474318","https://openalex.org/W4244543785","https://openalex.org/W4286747238","https://openalex.org/W4294311176","https://openalex.org/W4319586674","https://openalex.org/W4390912371","https://openalex.org/W6631362777","https://openalex.org/W6746238782","https://openalex.org/W6749555683","https://openalex.org/W6750489868","https://openalex.org/W6755300632","https://openalex.org/W6762533536","https://openalex.org/W6769196770","https://openalex.org/W6769299913","https://openalex.org/W6776390925","https://openalex.org/W6778823374","https://openalex.org/W6785629321","https://openalex.org/W6790220310","https://openalex.org/W6795952400","https://openalex.org/W6810681921","https://openalex.org/W6936113694"],"related_works":["https://openalex.org/W2406877384","https://openalex.org/W2595839522","https://openalex.org/W3109975354","https://openalex.org/W2124576126","https://openalex.org/W1984264321","https://openalex.org/W2357614930","https://openalex.org/W2008642382","https://openalex.org/W1541822869","https://openalex.org/W2037604299","https://openalex.org/W3204019825"],"abstract_inverted_index":{"In":[0],"addition":[1],"to":[2,10,63,74,103,142,174,184,215,225,235,261],"conveying":[3],"the":[4,14,26,65,86,99,113,131,176,186,227,233,237,242,251,262,283,291],"linguistic":[5],"content":[6],"from":[7,60,119,139],"source":[8,18,40,61,69,117,140,189,268],"speech":[9,19,62,118,141,205,254,269,274],"converted":[11,143],"speech,":[12,41,70,92,144],"maintaining":[13,272],"speaking":[15,66,114,132],"style":[16,57,67,77,95,115,133,147,190,228,270,287],"of":[17,68,90,116,188,202,285,293],"also":[20,221],"plays":[21],"an":[22,197],"important":[23],"role":[24],"in":[25,34,108],"voice":[27],"conversion":[28],"(VC)":[29],"task,":[30,101],"which":[31,71],"is":[32,72,106,148,213,259],"essential":[33],"many":[35],"scenarios":[36],"with":[37,168],"highly":[38,252],"expressive":[39,253],"such":[42],"as":[43,104],"dubbing":[44],"and":[45,79,125,134,161,179,192,209,240,246,276,290],"data":[46],"augmentation.":[47],"Previous":[48],"work":[49],"generally":[50],"took":[51],"explicit":[52,198,218],"prosodic":[53,154],"features":[54,162],"or":[55],"fixed-length":[56],"embedding":[58],"extracted":[59,163],"model":[64,166,175,208],"insufficient":[73],"achieve":[75],"comprehensive":[76],"modeling":[78,96,191,267,289],"target":[80,193],"speaker":[81,194,211,277],"timbre":[82,137,195],"preservation.":[83],"Inspired":[84],"by":[85,150,164],"style's":[87],"multi-scale":[88,94],"nature":[89],"human":[91],"a":[93,165,169,203,210],"method":[97],"for":[98,266],"VC":[100,264],"referred":[102],"MSM-VC,":[105],"proposed":[107],"this":[109],"article.":[110],"MSM-VC":[111,258],"models":[112],"different":[120],"levels,":[121],"i.e.,":[122],"global,":[123],"local,":[124,178],"frame":[126],"levels.":[127],"To":[128],"effectively":[129],"convey":[130],"meanwhile":[135],"prevent":[136],"leakage":[138],"each":[145,294],"level's":[146,288],"modeled":[149],"specific":[151],"representation.":[152],"Specifically,":[153],"features,":[155,160],"pre-trained":[156,204],"ASR":[157],"model's":[158],"bottleneck":[159],"trained":[167],"self-supervised":[170],"strategy":[171],"are":[172],"adopted":[173],"frame,":[177],"global-level":[180],"styles,":[181],"respectively.":[182],"Besides,":[183],"balance":[185],"performance":[187],"preservation,":[196],"constraint":[199,219],"module":[200,220],"consisting":[201],"emotion":[206],"recognition":[207],"classifier":[212],"introduced":[214],"MSM-VC.":[216],"This":[217],"makes":[222],"it":[223],"possible":[224],"simulate":[226],"transfer":[229],"inference":[230],"process":[231],"during":[232],"training":[234,245],"improve":[236],"disentanglement":[238],"ability":[239],"alleviate":[241],"mismatch":[243],"between":[244],"inference.":[247],"Experiments":[248],"performed":[249],"on":[250],"corpus":[255],"demonstrate":[256],"that":[257],"superior":[260],"state-of-the-art":[263],"methods":[265],"while":[271],"good":[273],"quality":[275],"similarity.":[278],"Furthermore,":[279],"ablation":[280],"analysis":[281],"indicates":[282],"indispensable":[284],"every":[286],"effectiveness":[292],"module.":[295]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}