{"id":"https://openalex.org/W3134921434","doi":"https://doi.org/10.1109/iscslp49672.2021.9362110","title":"Towards Fine-Grained Prosody Control for Voice Conversion","display_name":"Towards Fine-Grained Prosody Control for Voice Conversion","publication_year":2021,"publication_date":"2021-01-24","ids":{"openalex":"https://openalex.org/W3134921434","doi":"https://doi.org/10.1109/iscslp49672.2021.9362110","mag":"3134921434"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp49672.2021.9362110","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp49672.2021.9362110","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":"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/A5001973434","display_name":"Zheng Lian","orcid":"https://orcid.org/0000-0001-9477-0599"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Lian","raw_affiliation_strings":["National Laboratory of Pattern Recognition, CASIA, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, CASIA, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023256246","display_name":"Rongxiu Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongxiu Zhong","raw_affiliation_strings":["National Laboratory of Pattern Recognition, CASIA, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, CASIA, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111856667","display_name":"Zhengqi Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengqi Wen","raw_affiliation_strings":["National Laboratory of Pattern Recognition, CASIA, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, CASIA, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100395562","display_name":"Bin Liu","orcid":"https://orcid.org/0000-0003-1529-1552"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Liu","raw_affiliation_strings":["National Laboratory of Pattern Recognition, CASIA, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, CASIA, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112613657","display_name":"Jianhua Tao","orcid":"https://orcid.org/0000-0002-9344-6428"},"institutions":[{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Tao","raw_affiliation_strings":["CAS Center for Excellence in Brain Science and Intelligence Technology, Beijing, China","National Laboratory of Pattern Recognition, CASIA, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CAS Center for Excellence in Brain Science and Intelligence Technology, Beijing, China","institution_ids":["https://openalex.org/I4210097554"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition, CASIA, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]}],"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":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"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/prosody","display_name":"Prosody","score":0.9400397539138794},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7692645788192749},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7508693337440491},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.7310104370117188},{"id":"https://openalex.org/keywords/intonation","display_name":"Intonation (linguistics)","score":0.6715776324272156},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.5171412825584412},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5050593018531799},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.4686196446418762},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.45888951420783997},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.4543168246746063},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.44843900203704834},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4320671558380127},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42666053771972656},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4167505204677582},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41538697481155396},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.15923336148262024},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.15521582961082458},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09242105484008789},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07871124148368835},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07171565294265747}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.9400397539138794},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7692645788192749},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7508693337440491},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.7310104370117188},{"id":"https://openalex.org/C2781045179","wikidata":"https://www.wikidata.org/wiki/Q5576720","display_name":"Intonation (linguistics)","level":2,"score":0.6715776324272156},{"id":"https://openalex.org/C21036866","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.5171412825584412},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5050593018531799},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.4686196446418762},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.45888951420783997},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.4543168246746063},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.44843900203704834},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4320671558380127},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42666053771972656},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4167505204677582},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41538697481155396},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.15923336148262024},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.15521582961082458},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09242105484008789},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07871124148368835},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07171565294265747},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp49672.2021.9362110","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp49672.2021.9362110","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":[{"score":0.49000000953674316,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1973746598","https://openalex.org/W1974745215","https://openalex.org/W2013020033","https://openalex.org/W2049686551","https://openalex.org/W2098166503","https://openalex.org/W2142300631","https://openalex.org/W2156142001","https://openalex.org/W2157412983","https://openalex.org/W2161727827","https://openalex.org/W2191779130","https://openalex.org/W2471520273","https://openalex.org/W2518172956","https://openalex.org/W2519091744","https://openalex.org/W2532494225","https://openalex.org/W2794490148","https://openalex.org/W2795109282","https://openalex.org/W2889061305","https://openalex.org/W2902070858","https://openalex.org/W2938583109","https://openalex.org/W2938836228","https://openalex.org/W2963091184","https://openalex.org/W2963609956","https://openalex.org/W2963623257","https://openalex.org/W2964138190","https://openalex.org/W2964307104","https://openalex.org/W2972313557","https://openalex.org/W2972970915","https://openalex.org/W3015707856","https://openalex.org/W3015719316","https://openalex.org/W3016007107","https://openalex.org/W3016243847","https://openalex.org/W3102628737","https://openalex.org/W4295731579","https://openalex.org/W4298580827","https://openalex.org/W6631362777","https://openalex.org/W6674835290","https://openalex.org/W6726528559","https://openalex.org/W6748409065","https://openalex.org/W6750489868","https://openalex.org/W6753441378","https://openalex.org/W6755811826","https://openalex.org/W6756328725","https://openalex.org/W6761155646","https://openalex.org/W6761278089","https://openalex.org/W6770351630","https://openalex.org/W6772037278","https://openalex.org/W6772199901","https://openalex.org/W6775933407"],"related_works":["https://openalex.org/W1965454423","https://openalex.org/W2028501571","https://openalex.org/W2052542215","https://openalex.org/W2036564641","https://openalex.org/W1927421023","https://openalex.org/W10581632","https://openalex.org/W3149582125","https://openalex.org/W1984347656","https://openalex.org/W1965141925","https://openalex.org/W2465421051"],"abstract_inverted_index":{"In":[0],"a":[1,47],"typical":[2],"voice":[3],"conversion":[4],"system,":[5],"previous":[6],"works":[7],"utilized":[8],"various":[9],"acoustic":[10,56],"features":[11],"(such":[12],"as":[13,39],"the":[14,21,26,40,76,85,107,114],"pitch,":[15],"voiced/unvoiced":[16],"flag":[17],"and":[18,43,110],"aperiodicity)":[19],"of":[20,28,87,113],"source":[22,77],"speech":[23,78,108],"to":[24,50,64,68],"control":[25],"prosody":[27,32,53,66],"converted":[29,115],"speech.":[30,116],"However,":[31],"is":[33,46],"related":[34],"with":[35],"many":[36],"factors,":[37],"such":[38],"intonation,":[41],"stress":[42],"rhythm.":[44],"It":[45],"challenging":[48],"task":[49],"perfectly":[51],"describe":[52,69],"through":[54],"hand-crafted":[55],"features.":[57],"To":[58,83],"address":[59],"these":[60],"difficulties,":[61],"we":[62,91,119],"propose":[63],"use":[65],"embeddings":[67,72],"prosody.":[70],"These":[71],"are":[73],"learned":[74],"from":[75],"in":[79,129],"an":[80],"unsupervised":[81],"manner.":[82],"verify":[84],"effectiveness":[86],"our":[88,95,102,122],"proposed":[89,103],"method,":[90],"conduct":[92],"experiments":[93],"on":[94],"Mandarin":[96],"corpus.":[97],"Experimental":[98],"results":[99,128],"show":[100],"that":[101,121],"method":[104,123],"can":[105,124],"improve":[106],"quality":[109],"speaker":[111],"similarity":[112],"What's":[117],"more,":[118],"observe":[120],"even":[125],"achieve":[126],"promising":[127],"singing":[130],"conditions.":[131]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
