{"id":"https://openalex.org/W3135654121","doi":"https://doi.org/10.1109/iscslp49672.2021.9362120","title":"Accent and Speaker Disentanglement in Many-to-many Voice Conversion","display_name":"Accent and Speaker Disentanglement in Many-to-many Voice Conversion","publication_year":2021,"publication_date":"2021-01-24","ids":{"openalex":"https://openalex.org/W3135654121","doi":"https://doi.org/10.1109/iscslp49672.2021.9362120","mag":"3135654121"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp49672.2021.9362120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp49672.2021.9362120","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-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":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091846895","display_name":"Wenshuo Ge","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":"Wenshuo Ge","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100359238","display_name":"Xiong Wang","orcid":"https://orcid.org/0000-0002-1343-0339"},"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":"Xiong Wang","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101736420","display_name":"Shan Yang","orcid":"https://orcid.org/0000-0003-4464-146X"},"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":"Shan Yang","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020922543","display_name":"Wendong Gan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115040","display_name":"iQIYI (China)","ror":"https://ror.org/026xvz038","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210115040"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wendong Gan","raw_affiliation_strings":["iQIYI Inc, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iQIYI Inc, China","institution_ids":["https://openalex.org/I4210115040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100737752","display_name":"Haitao Chen","orcid":"https://orcid.org/0000-0003-2262-4781"},"institutions":[{"id":"https://openalex.org/I4210115040","display_name":"iQIYI (China)","ror":"https://ror.org/026xvz038","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210115040"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haitao Chen","raw_affiliation_strings":["iQIYI Inc, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iQIYI Inc, China","institution_ids":["https://openalex.org/I4210115040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100429403","display_name":"Hai Li","orcid":"https://orcid.org/0000-0003-3228-6544"},"institutions":[{"id":"https://openalex.org/I4210115040","display_name":"iQIYI (China)","ror":"https://ror.org/026xvz038","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210115040"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hai Li","raw_affiliation_strings":["iQIYI Inc, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iQIYI Inc, China","institution_ids":["https://openalex.org/I4210115040"]}]},{"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":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101562197","display_name":"Xiulin Li","orcid":"https://orcid.org/0000-0003-3581-2968"},"institutions":[{"id":"https://openalex.org/I4210162623","display_name":"Datang Telecom Group (China)","ror":"https://ror.org/050rf2257","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210162623"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiulin Li","raw_affiliation_strings":["Databaker (Beijing) Technology Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Databaker (Beijing) Technology Co., Ltd","institution_ids":["https://openalex.org/I4210162623"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0785,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.92692587,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"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":0.9961000084877014,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9943000078201294,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8016160130500793},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7974240183830261},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.517948567867279},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.5144398808479309},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4940033555030823},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.48552751541137695},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.46660444140434265},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4429016709327698},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4165314733982086},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.391006201505661}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8016160130500793},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7974240183830261},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.517948567867279},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.5144398808479309},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4940033555030823},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.48552751541137695},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.46660444140434265},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4429016709327698},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4165314733982086},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.391006201505661},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp49672.2021.9362120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp49672.2021.9362120","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1509691205","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1599112982","https://openalex.org/W1731081199","https://openalex.org/W1977362459","https://openalex.org/W1991682319","https://openalex.org/W2017425464","https://openalex.org/W2120605154","https://openalex.org/W2121387787","https://openalex.org/W2126143605","https://openalex.org/W2156142001","https://openalex.org/W2156477760","https://openalex.org/W2187089797","https://openalex.org/W2518172956","https://openalex.org/W2784163702","https://openalex.org/W2890402938","https://openalex.org/W2897353073","https://openalex.org/W2936832667","https://openalex.org/W2946809691","https://openalex.org/W2962896155","https://openalex.org/W2963091184","https://openalex.org/W2963609956","https://openalex.org/W2964121744","https://openalex.org/W2972313557","https://openalex.org/W2972659941","https://openalex.org/W2973142754","https://openalex.org/W2996414377","https://openalex.org/W3007502375","https://openalex.org/W3015430779","https://openalex.org/W3022057435","https://openalex.org/W3097728852","https://openalex.org/W3099078140","https://openalex.org/W3101689408","https://openalex.org/W3103152812","https://openalex.org/W3104309246","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6635678660","https://openalex.org/W6637618735","https://openalex.org/W6726528559","https://openalex.org/W6762987126"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1493012537","https://openalex.org/W1521299571","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W2175373321","https://openalex.org/W3141593045","https://openalex.org/W2134501921","https://openalex.org/W1521049138","https://openalex.org/W2144470400"],"abstract_inverted_index":{"This":[0,26,91],"paper":[1],"proposes":[2],"an":[3,14,134,143],"interesting":[4],"voice":[5,18],"and":[6,41,47,55,122,174,177],"accent":[7,40,46,123],"joint":[8],"conversion":[9,52,60,65,107,129],"approach,":[10],"which":[11],"can":[12],"convert":[13],"arbitrary":[15],"source":[16],"speaker\u2019s":[17],"to":[19,44,69,83,93,113,117,138,146,162],"a":[20],"target":[21,32],"speaker":[22,33,48,121,136,149,178],"with":[23,142],"non-native":[24],"accent.":[25],"problem":[27,72],"is":[28,160],"challenging":[29],"as":[30],"each":[31],"only":[34],"has":[35],"training":[36,54,116],"data":[37],"in":[38,50,58,102,125,171],"native":[39],"we":[42,67,78,111,132],"need":[43],"disentangle":[45,119],"information":[49,101,124,150],"the":[51,59,99,103,120,139,152,163],"model":[53,108],"re-combine":[56],"them":[57],"stage.":[61],"In":[62],"our":[63,126,158],"recognition-synthesis":[64],"framework,":[66],"manage":[68],"solve":[70],"this":[71],"by":[73],"two":[74],"proposed":[75,166],"tricks.":[76],"First,":[77],"use":[79,114],"accent-dependent":[80],"speech":[81],"recognizers":[82],"obtain":[84],"bottleneck":[85],"features":[86,105],"for":[87,106],"different":[88],"accented":[89],"speakers.":[90],"aims":[92],"wipe":[94,147],"out":[95,148],"other":[96],"factors":[97],"beyond":[98],"linguistic":[100],"BN":[104],"training.":[109],"Second,":[110],"propose":[112],"adversarial":[115,144],"better":[118],"encoder-decoder":[127],"based":[128],"model.":[130],"Specifically,":[131],"plug":[133],"auxiliary":[135],"classifier":[137],"encoder,":[140],"trained":[141],"loss":[145],"from":[151],"encoder":[153],"output.":[154],"Experiments":[155],"show":[156],"that":[157],"approach":[159],"superior":[161],"baseline.":[164],"The":[165],"tricks":[167],"are":[168,180],"quite":[169],"effective":[170],"improving":[172],"accentedness":[173],"audio":[175],"quality":[176],"similarity":[179],"well":[181],"maintained.":[182]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}