{"id":"https://openalex.org/W4226487411","doi":"https://doi.org/10.1109/icme52920.2022.9859946","title":"Unsupervised Quantized Prosody Representation for Controllable Speech Synthesis","display_name":"Unsupervised Quantized Prosody Representation for Controllable Speech Synthesis","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4226487411","doi":"https://doi.org/10.1109/icme52920.2022.9859946"},"language":"en","primary_location":{"id":"doi:10.1109/icme52920.2022.9859946","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859946","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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/A5100741276","display_name":"Yutian Wang","orcid":"https://orcid.org/0009-0008-8451-600X"},"institutions":[{"id":"https://openalex.org/I4391768176","display_name":"State Key Laboratory of Media Convergence and Communication","ror":"https://ror.org/0595ys057","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391768176","https://openalex.org/I75689368"]},{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutian Wang","raw_affiliation_strings":["Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing,China","State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing,China","institution_ids":["https://openalex.org/I75689368","https://openalex.org/I4391768176"]},{"raw_affiliation_string":"State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044573835","display_name":"Yuankun Xie","orcid":"https://orcid.org/0000-0002-8366-9011"},"institutions":[{"id":"https://openalex.org/I4391768176","display_name":"State Key Laboratory of Media Convergence and Communication","ror":"https://ror.org/0595ys057","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391768176","https://openalex.org/I75689368"]},{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuankun Xie","raw_affiliation_strings":["Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing,China","State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing,China","institution_ids":["https://openalex.org/I75689368","https://openalex.org/I4391768176"]},{"raw_affiliation_string":"State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100675365","display_name":"Kun Zhao","orcid":"https://orcid.org/0000-0002-2293-9209"},"institutions":[{"id":"https://openalex.org/I4391768176","display_name":"State Key Laboratory of Media Convergence and Communication","ror":"https://ror.org/0595ys057","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391768176","https://openalex.org/I75689368"]},{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Zhao","raw_affiliation_strings":["Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing,China","State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing,China","institution_ids":["https://openalex.org/I75689368","https://openalex.org/I4391768176"]},{"raw_affiliation_string":"State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460850","display_name":"Hui Wang","orcid":"https://orcid.org/0000-0002-8814-1988"},"institutions":[{"id":"https://openalex.org/I4391768176","display_name":"State Key Laboratory of Media Convergence and Communication","ror":"https://ror.org/0595ys057","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391768176","https://openalex.org/I75689368"]},{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Wang","raw_affiliation_strings":["Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing,China","State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing,China","institution_ids":["https://openalex.org/I75689368","https://openalex.org/I4391768176"]},{"raw_affiliation_string":"State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114378014","display_name":"Qin Zhang","orcid":"https://orcid.org/0009-0001-0205-6986"},"institutions":[{"id":"https://openalex.org/I4391768176","display_name":"State Key Laboratory of Media Convergence and Communication","ror":"https://ror.org/0595ys057","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391768176","https://openalex.org/I75689368"]},{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qin Zhang","raw_affiliation_strings":["Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing,China","State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing,China","institution_ids":["https://openalex.org/I75689368","https://openalex.org/I4391768176"]},{"raw_affiliation_string":"State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9990000128746033,"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":0.9975000023841858,"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":0.8930266499519348},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6400983929634094},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6248856782913208},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.6227641105651855},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.5270352959632874},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5269057154655457},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5121634006500244},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48328307271003723},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4429226219654083},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.42264634370803833},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4206072688102722},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35715752840042114},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33419954776763916},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10015267133712769}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8930266499519348},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6400983929634094},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6248856782913208},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.6227641105651855},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.5270352959632874},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5269057154655457},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5121634006500244},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48328307271003723},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4429226219654083},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.42264634370803833},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4206072688102722},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35715752840042114},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33419954776763916},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10015267133712769},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme52920.2022.9859946","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859946","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.41999998688697815}],"awards":[{"id":"https://openalex.org/G7299993058","display_name":"\u5386\u53f2\u5f71\u97f3\u8d44\u6599\u97f3\u9891\u4fee\u590d\u65b9\u6cd5\u4e0e\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"61631016","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"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":34,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W2025722797","https://openalex.org/W2091425152","https://openalex.org/W2107740512","https://openalex.org/W2107860279","https://openalex.org/W2130086727","https://openalex.org/W2591927543","https://openalex.org/W2752796333","https://openalex.org/W2794490148","https://openalex.org/W2904459034","https://openalex.org/W2946200149","https://openalex.org/W2962691331","https://openalex.org/W2963609956","https://openalex.org/W2963799213","https://openalex.org/W2964243274","https://openalex.org/W2966387353","https://openalex.org/W2971074500","https://openalex.org/W2972394484","https://openalex.org/W3007067948","https://openalex.org/W3010916717","https://openalex.org/W3016021263","https://openalex.org/W3033411150","https://openalex.org/W3096524539","https://openalex.org/W4289383906","https://openalex.org/W4298580827","https://openalex.org/W6623517193","https://openalex.org/W6675938391","https://openalex.org/W6736996214","https://openalex.org/W6748409065","https://openalex.org/W6750489868","https://openalex.org/W6755300632","https://openalex.org/W6762931180","https://openalex.org/W6763832098","https://openalex.org/W6778823374"],"related_works":["https://openalex.org/W1927421023","https://openalex.org/W10581632","https://openalex.org/W3149582125","https://openalex.org/W157238252","https://openalex.org/W2169632867","https://openalex.org/W2465421051","https://openalex.org/W152045069","https://openalex.org/W652196294","https://openalex.org/W2368700418","https://openalex.org/W1965141925"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,74],"novel":[6],"prosody":[7,25,31,86],"disentangle":[8,69],"method":[9,21],"for":[10],"prosodic":[11],"Text-to-Speech":[12],"(TTS)":[13],"model,":[14],"which":[15],"introduces":[16],"the":[17,23,29,41,57,64,95,104,117],"vector":[18],"quantization":[19],"(VQ)":[20],"to":[22,27],"auxiliary":[24],"encoder":[26],"obtain":[28],"decomposed":[30,54],"representations":[32],"in":[33],"an":[34],"unsupervised":[35],"manner.":[36],"Rely":[37],"on":[38],"its":[39],"advantages,":[40],"speaking":[42,47,96],"styles,":[43],"such":[44],"as":[45],"pitch,":[46],"velocity,":[48],"local":[49],"pitch":[50],"variance,":[51],"etc.,":[52],"are":[53],"automatically":[55],"into":[56],"latent":[58,75,105],"quantize":[59],"vectors.":[60],"We":[61],"also":[62],"investigate":[63],"internal":[65],"mechanism":[66],"of":[67,73,98],"VQ":[68],"process":[70],"by":[71,101],"means":[72],"variables":[76],"counter":[77],"and":[78,109],"find":[79],"that":[80,90,113],"higher":[81],"value":[82],"dimensions":[83],"usually":[84],"represent":[85],"information.":[87],"Experiments":[88],"show":[89],"our":[91,114],"model":[92,115],"can":[93],"control":[94],"styles":[97],"synthesis":[99],"results":[100],"directly":[102],"manipulating":[103],"variables.":[106],"The":[107],"objective":[108],"subjective":[110],"evaluations":[111],"illustrated":[112],"outperforms":[116],"popular":[118],"models.":[119]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}