{"id":"https://openalex.org/W4375869253","doi":"https://doi.org/10.1109/icassp49357.2023.10096471","title":"Delivering Speaking Style in Low-Resource Voice Conversion with Multi-Factor Constraints","display_name":"Delivering Speaking Style in Low-Resource Voice Conversion with Multi-Factor Constraints","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869253","doi":"https://doi.org/10.1109/icassp49357.2023.10096471"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096471","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096471","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":"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/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’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’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115547209","display_name":"Xinsheng Wang","orcid":"https://orcid.org/0000-0002-7528-4621"},"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":"Xinsheng Wang","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’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’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’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’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055175414","display_name":"Yuanzhe Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuanzhe Chen","raw_affiliation_strings":["ByteDance,Speech, Audio & Music Intelligence (SAMI)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance,Speech, Audio & Music Intelligence (SAMI)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018710096","display_name":"Qiao Tian","orcid":"https://orcid.org/0000-0001-8177-7724"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiao Tian","raw_affiliation_strings":["ByteDance,Speech, Audio & Music Intelligence (SAMI)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance,Speech, Audio & Music Intelligence (SAMI)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100339104","display_name":"Yuping Wang","orcid":"https://orcid.org/0000-0001-6868-0004"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuping Wang","raw_affiliation_strings":["ByteDance,Speech, Audio & Music Intelligence (SAMI)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance,Speech, Audio & Music Intelligence (SAMI)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8712,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.73156688,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"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":0.9979000091552734,"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/T11309","display_name":"Music and Audio Processing","score":0.98580002784729,"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":0.7595697045326233},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7427353858947754},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.7299162149429321},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5824620723724365},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5613120198249817},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5269884467124939},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5016052722930908},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.48246294260025024},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.461161345243454},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.41074472665786743},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39072418212890625},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33218324184417725}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7595697045326233},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7427353858947754},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.7299162149429321},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5824620723724365},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5613120198249817},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5269884467124939},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5016052722930908},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.48246294260025024},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.461161345243454},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.41074472665786743},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39072418212890625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33218324184417725},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/icassp49357.2023.10096471","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096471","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":[{"display_name":"Quality Education","score":0.6399999856948853,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2404839462","https://openalex.org/W2518172956","https://openalex.org/W2532494225","https://openalex.org/W2795109282","https://openalex.org/W2808631503","https://openalex.org/W2944378183","https://openalex.org/W2945478979","https://openalex.org/W2962788625","https://openalex.org/W2962896155","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2972659941","https://openalex.org/W3024869864","https://openalex.org/W3034218934","https://openalex.org/W3094635600","https://openalex.org/W3097892637","https://openalex.org/W3109064156","https://openalex.org/W3134921434","https://openalex.org/W3163573274","https://openalex.org/W3168527213","https://openalex.org/W3168542456","https://openalex.org/W3179060760","https://openalex.org/W3196616101","https://openalex.org/W3197659778","https://openalex.org/W3197704090","https://openalex.org/W3197943112","https://openalex.org/W3198533616","https://openalex.org/W3203407300","https://openalex.org/W3216296943","https://openalex.org/W4221160837","https://openalex.org/W4226225516","https://openalex.org/W4226474318","https://openalex.org/W4295731579","https://openalex.org/W6736996214","https://openalex.org/W6737196085","https://openalex.org/W6762533536","https://openalex.org/W6762744983","https://openalex.org/W6786325012","https://openalex.org/W6795807602","https://openalex.org/W6796719098","https://openalex.org/W6802061202","https://openalex.org/W6810447587","https://openalex.org/W6810681921"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"Conveying":[0],"the":[1,6,32,48,66,95,126,131,145,148],"linguistic":[2,113],"content":[3],"and":[4,14,46,115,135],"maintaining":[5],"source":[7],"speech\u2019s":[8],"speaking":[9,111],"style,":[10,112],"such":[11],"as":[12,61],"intonation":[13],"emotion,":[15],"is":[16,63,78,122],"essential":[17],"in":[18,23,87,151],"voice":[19],"conversion":[20],"(VC).":[21],"However,":[22],"a":[24,55,119],"low-resource":[25,67,152],"situation,":[26],"where":[27],"only":[28],"limited":[29,98],"utterances":[30],"from":[31],"target":[33,49,83,96],"speaker":[34,71,84],"are":[35,40],"accessible,":[36],"existing":[37],"VC":[38,57,68],"methods":[39],"hard":[41],"to":[42,60,81,91,94,124,129],"meet":[43],"this":[44,53],"requirement":[45],"capture":[47],"speaker\u2019s":[50,97],"timber.":[51],"In":[52],"work,":[54],"novel":[56],"model,":[58],"referred":[59],"MFC-StyleVC,":[62],"proposed":[64,80,149],"for":[65],"task.":[69],"Specifically,":[70],"timbre":[72,85],"constraint":[73],"generated":[74],"by":[75],"clustering":[76],"method":[77,150],"newly":[79],"guide":[82],"learning":[86],"different":[88],"stages.":[89],"Meanwhile,":[90],"prevent":[92],"over-fitting":[93],"data,":[99],"perceptual":[100],"regularization":[101],"constraints":[102],"explicitly":[103],"maintain":[104],"model":[105],"performance":[106],"on":[107,140],"specific":[108],"aspects,":[109],"including":[110],"content,":[114],"speech":[116,143],"quality.":[117],"Besides,":[118],"simulation":[120],"mode":[121],"introduced":[123],"simulate":[125],"inference":[127],"process":[128],"alleviate":[130],"mis-match":[132],"between":[133],"training":[134],"inference.":[136],"Extensive":[137],"experiments":[138],"performed":[139],"highly":[141],"expressive":[142],"demonstrate":[144],"superiority":[146],"of":[147],"VC.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}