{"id":"https://openalex.org/W4372260402","doi":"https://doi.org/10.1109/icassp49357.2023.10095840","title":"Improving Prosody for Cross-Speaker Style Transfer by Semi-Supervised Style Extractor and Hierarchical Modeling in Speech Synthesis","display_name":"Improving Prosody for Cross-Speaker Style Transfer by Semi-Supervised Style Extractor and Hierarchical Modeling in Speech Synthesis","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260402","doi":"https://doi.org/10.1109/icassp49357.2023.10095840"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095840","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095840","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":"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/A5028353824","display_name":"Chunyu Qiang","orcid":"https://orcid.org/0009-0007-2290-3074"},"institutions":[{"id":"https://openalex.org/I2801745840","display_name":"Kwai Chung Hospital","ror":"https://ror.org/05kz7bw59","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I1294586568","https://openalex.org/I2801745840"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunyu Qiang","raw_affiliation_strings":["Kwai,Beijing,P.R. China","Kwai, Beijing, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kwai,Beijing,P.R. China","institution_ids":["https://openalex.org/I2801745840"]},{"raw_affiliation_string":"Kwai, Beijing, P.R. China","institution_ids":["https://openalex.org/I2801745840"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101863403","display_name":"Peng Yang","orcid":"https://orcid.org/0009-0005-3449-5843"},"institutions":[{"id":"https://openalex.org/I2801745840","display_name":"Kwai Chung Hospital","ror":"https://ror.org/05kz7bw59","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I1294586568","https://openalex.org/I2801745840"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Yang","raw_affiliation_strings":["Kwai,Beijing,P.R. China","Kwai, Beijing, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kwai,Beijing,P.R. China","institution_ids":["https://openalex.org/I2801745840"]},{"raw_affiliation_string":"Kwai, Beijing, P.R. China","institution_ids":["https://openalex.org/I2801745840"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112489758","display_name":"Hao Che","orcid":"https://orcid.org/0009-0001-9852-320X"},"institutions":[{"id":"https://openalex.org/I2801745840","display_name":"Kwai Chung Hospital","ror":"https://ror.org/05kz7bw59","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I1294586568","https://openalex.org/I2801745840"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Che","raw_affiliation_strings":["Kwai,Beijing,P.R. China","Kwai, Beijing, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kwai,Beijing,P.R. China","institution_ids":["https://openalex.org/I2801745840"]},{"raw_affiliation_string":"Kwai, Beijing, P.R. China","institution_ids":["https://openalex.org/I2801745840"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100386277","display_name":"Ying Zhang","orcid":"https://orcid.org/0009-0000-9627-8768"},"institutions":[{"id":"https://openalex.org/I2801745840","display_name":"Kwai Chung Hospital","ror":"https://ror.org/05kz7bw59","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I1294586568","https://openalex.org/I2801745840"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Zhang","raw_affiliation_strings":["Kwai,Beijing,P.R. China","Kwai, Beijing, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kwai,Beijing,P.R. China","institution_ids":["https://openalex.org/I2801745840"]},{"raw_affiliation_string":"Kwai, Beijing, P.R. China","institution_ids":["https://openalex.org/I2801745840"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100658019","display_name":"Xiaorui Wang","orcid":"https://orcid.org/0000-0001-9633-1418"},"institutions":[{"id":"https://openalex.org/I2801745840","display_name":"Kwai Chung Hospital","ror":"https://ror.org/05kz7bw59","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I1294586568","https://openalex.org/I2801745840"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaorui Wang","raw_affiliation_strings":["Kwai,Beijing,P.R. China","Kwai, Beijing, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kwai,Beijing,P.R. China","institution_ids":["https://openalex.org/I2801745840"]},{"raw_affiliation_string":"Kwai, Beijing, P.R. China","institution_ids":["https://openalex.org/I2801745840"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100741750","display_name":"Zhongyuan Wang","orcid":"https://orcid.org/0000-0002-9796-488X"},"institutions":[{"id":"https://openalex.org/I2801745840","display_name":"Kwai Chung Hospital","ror":"https://ror.org/05kz7bw59","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I1294586568","https://openalex.org/I2801745840"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongyuan Wang","raw_affiliation_strings":["Kwai,Beijing,P.R. China","Kwai, Beijing, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kwai,Beijing,P.R. China","institution_ids":["https://openalex.org/I2801745840"]},{"raw_affiliation_string":"Kwai, Beijing, P.R. China","institution_ids":["https://openalex.org/I2801745840"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2801745840"],"apc_list":null,"apc_paid":null,"fwci":1.4517,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.85137603,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9991000294685364,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9977999925613403,"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":0.9125655293464661},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.736655592918396},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6829991936683655},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6283773183822632},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.5674097537994385},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4555280804634094},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45428064465522766},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.4503898322582245},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4483165740966797},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.442058265209198},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.07969948649406433}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.9125655293464661},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.736655592918396},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6829991936683655},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6283773183822632},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.5674097537994385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4555280804634094},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45428064465522766},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.4503898322582245},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4483165740966797},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.442058265209198},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.07969948649406433},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095840","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095840","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":0.6899999976158142,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W2752782242","https://openalex.org/W2794490148","https://openalex.org/W2795109282","https://openalex.org/W2903739847","https://openalex.org/W2904459034","https://openalex.org/W2952269766","https://openalex.org/W2963091184","https://openalex.org/W2963609956","https://openalex.org/W2996573371","https://openalex.org/W3083565479","https://openalex.org/W3139170550","https://openalex.org/W3161296985","https://openalex.org/W3163573274","https://openalex.org/W3163906773","https://openalex.org/W3194613004","https://openalex.org/W3195366750","https://openalex.org/W3198104520","https://openalex.org/W3205631867","https://openalex.org/W3206725777","https://openalex.org/W4225303561","https://openalex.org/W4226421465","https://openalex.org/W4295731579","https://openalex.org/W4312069022","https://openalex.org/W4319779739","https://openalex.org/W6640963894","https://openalex.org/W6736996214","https://openalex.org/W6750489868","https://openalex.org/W6762643587","https://openalex.org/W6768443183","https://openalex.org/W6802591955"],"related_works":["https://openalex.org/W1927421023","https://openalex.org/W10581632","https://openalex.org/W3149582125","https://openalex.org/W1984347656","https://openalex.org/W1965141925","https://openalex.org/W2465421051","https://openalex.org/W652196294","https://openalex.org/W2368700418","https://openalex.org/W2587342322","https://openalex.org/W2540115864"],"abstract_inverted_index":{"Cross-speaker":[0],"style":[1,10,59,66,79,108],"transfer":[2,109],"in":[3,91,136],"speech":[4,16],"synthesis":[5],"aims":[6],"at":[7],"transferring":[8],"a":[9,18,56,125,156],"from":[11,67],"source":[12,34,116],"speaker":[13],"to":[14,39,47,53,63,100,132],"synthesized":[15,27],"of":[17,76],"target":[19],"speaker\u2019s":[20,35,117],"timbre.":[21],"In":[22,51],"most":[23],"previous":[24],"methods,":[25],"the":[26,33,40,48,65,72,77,84,115,134,142,149,152],"fine-grained":[28],"prosody":[29,44,92,96,102,118],"features":[30,119],"often":[31],"represent":[32],"average":[36],"style,":[37],"similar":[38],"one-to-many":[41,85],"problem(i.e.,":[42],"multiple":[43],"variations":[45],"correspond":[46],"same":[49],"text).":[50],"response":[52],"this":[54],"problem,":[55],"strength-controlled":[57],"semi-supervised":[58],"extractor":[60],"is":[61,98,130],"proposed":[62,99,131],"disentangle":[64],"content":[68],"and":[69,74,87],"timbre,":[70],"improving":[71],"representation":[73],"interpretability":[75],"global":[78],"embedding,":[80],"which":[81],"can":[82,110],"alleviate":[83],"mapping":[86],"data":[88],"imbalance":[89],"problems":[90],"prediction.":[93],"A":[94],"hierarchical":[95],"predictor":[97],"improve":[101],"modeling.":[103],"We":[104,154],"find":[105],"that":[106,120,148],"better":[107],"be":[111],"achieved":[112],"by":[113],"using":[114],"are":[121],"easily":[122],"predicted.":[123],"Additionally,":[124],"speaker-transfer-wise":[126],"cycle":[127],"consistency":[128],"loss":[129],"assist":[133],"model":[135],"learning":[137],"unseen":[138],"style-timbre":[139],"combinations":[140],"during":[141],"training":[143],"phase.":[144],"Experimental":[145],"results":[146],"show":[147],"method":[150],"outperforms":[151],"baseline.":[153],"provide":[155],"website":[157],"with":[158],"audio":[159],"samples":[160],"<sup":[161],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[162],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[163],".":[164]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}