{"id":"https://openalex.org/W3213984348","doi":"https://doi.org/10.1109/lsp.2021.3125259","title":"A Controllable Multi-Lingual Multi-Speaker Multi-Style Text-to-Speech Synthesis With Multivariate Information Minimization","display_name":"A Controllable Multi-Lingual Multi-Speaker Multi-Style Text-to-Speech Synthesis With Multivariate Information Minimization","publication_year":2021,"publication_date":"2021-11-04","ids":{"openalex":"https://openalex.org/W3213984348","doi":"https://doi.org/10.1109/lsp.2021.3125259","mag":"3213984348"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2021.3125259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2021.3125259","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5005088101","display_name":"Sung Jun Cheon","orcid":"https://orcid.org/0000-0002-7293-6997"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Sung Jun Cheon","raw_affiliation_strings":["Department of Electrical and Computer Engineering and with the Institute of New Media and Communications, Seoul National University, Gwanak-gu, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-7293-6997","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and with the Institute of New Media and Communications, Seoul National University, Gwanak-gu, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101424423","display_name":"Byoung Jin Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byoung Jin Choi","raw_affiliation_strings":["Department of Electrical and Computer Engineering and with the Institute of New Media and Communications, Seoul National University, Gwanak-gu, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-1319-8215","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and with the Institute of New Media and Communications, Seoul National University, Gwanak-gu, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027616639","display_name":"Minchan Kim","orcid":"https://orcid.org/0000-0002-8150-765X"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minchan Kim","raw_affiliation_strings":["Department of Electrical and Computer Engineering and with the Institute of New Media and Communications, Seoul National University, Gwanak-gu, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-8150-765X","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and with the Institute of New Media and Communications, Seoul National University, Gwanak-gu, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103052875","display_name":"Hyeonseung Lee","orcid":"https://orcid.org/0000-0001-6997-205X"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyeonseung Lee","raw_affiliation_strings":["Department of Electrical and Computer Engineering and with the Institute of New Media and Communications, Seoul National University, Gwanak-gu, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0001-6997-205X","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and with the Institute of New Media and Communications, Seoul National University, Gwanak-gu, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051356511","display_name":"Nam Soo Kim","orcid":"https://orcid.org/0000-0002-0568-4902"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nam Soo Kim","raw_affiliation_strings":["Department of Electrical and Computer Engineering and with the Institute of New Media and Communications, Seoul National University, Gwanak-gu, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-0568-4902","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and with the Institute of New Media and Communications, Seoul National University, Gwanak-gu, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5005088101"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.14,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57894074,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"29","issue":null,"first_page":"55","last_page":"59"},"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":0.9994000196456909,"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":0.9976000189781189,"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":0.7662806510925293},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.7637491822242737},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6819940805435181},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.6306171417236328},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.60548335313797},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5657678842544556},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.5615374445915222},{"id":"https://openalex.org/keywords/multivariate-statistics","display_name":"Multivariate statistics","score":0.5087147355079651},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46308785676956177},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.43674543499946594},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.4328542947769165},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4233183264732361},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35037821531295776},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34780293703079224},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.24918684363365173},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14888527989387512}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7662806510925293},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.7637491822242737},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6819940805435181},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.6306171417236328},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.60548335313797},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5657678842544556},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.5615374445915222},{"id":"https://openalex.org/C161584116","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate statistics","level":2,"score":0.5087147355079651},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46308785676956177},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.43674543499946594},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.4328542947769165},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4233183264732361},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35037821531295776},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34780293703079224},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24918684363365173},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14888527989387512},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2021.3125259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2021.3125259","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1613249581","https://openalex.org/W1995875735","https://openalex.org/W2095439994","https://openalex.org/W2157331557","https://openalex.org/W2556467266","https://openalex.org/W2902476877","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2972473628","https://openalex.org/W2972921407","https://openalex.org/W2998115938","https://openalex.org/W3015212100","https://openalex.org/W3015338123","https://openalex.org/W3047443559","https://openalex.org/W3198123658","https://openalex.org/W3198869563","https://openalex.org/W4210631502","https://openalex.org/W6631190155","https://openalex.org/W6730333270","https://openalex.org/W6745117592","https://openalex.org/W6749555683","https://openalex.org/W6750489868","https://openalex.org/W6752051073","https://openalex.org/W6752888775","https://openalex.org/W6755300632","https://openalex.org/W6756824971","https://openalex.org/W6762796984","https://openalex.org/W6762931180","https://openalex.org/W6763832098","https://openalex.org/W6778823374","https://openalex.org/W6779459370","https://openalex.org/W6783867762","https://openalex.org/W6785754695","https://openalex.org/W6795949861"],"related_works":["https://openalex.org/W2036697162","https://openalex.org/W2332386680","https://openalex.org/W2248621902","https://openalex.org/W2003779889","https://openalex.org/W2561315646","https://openalex.org/W4205698120","https://openalex.org/W4239246781","https://openalex.org/W2542825942","https://openalex.org/W3201620972","https://openalex.org/W1496421768"],"abstract_inverted_index":{"In":[0],"this":[1],"letter,":[2],"we":[3],"propose":[4],"a":[5,34,69],"multivariate":[6],"information":[7,38],"minimization":[8],"method":[9,85],"that":[10,19,82],"disentangles":[11],"three":[12],"or":[13],"more":[14],"latent":[15],"representations.":[16],"We":[17],"show":[18],"control":[20],"factors":[21],"can":[22,30,86],"be":[23,31],"disentangled":[24],"by":[25],"minimizing":[26],"interactive":[27],"dependency,":[28],"which":[29],"expressed":[32],"as":[33,94,96],"sum":[35],"of":[36,92],"mutual":[37],"upper":[39,44],"bound":[40,45],"terms.":[41],"Since":[42],"the":[43,49,83,88],"estimate":[46],"converges":[47],"from":[48],"early":[50],"training":[51],"stage,":[52],"there":[53],"is":[54,65],"little":[55],"performance":[56],"degradation":[57],"due":[58],"to":[59,67],"auxiliary":[60],"loss.":[61],"The":[62],"proposed":[63,84],"technique":[64],"applied":[66],"train":[68],"text-to-speech":[70],"synthesizer":[71,89],"with":[72],"multi-lingual,":[73],"multi-speaker,":[74],"and":[75],"multi-style":[76],"corpora.":[77],"Subjective":[78],"listening":[79],"tests":[80],"validate":[81],"improve":[87],"in":[90],"terms":[91],"quality":[93],"well":[95],"controllability.":[97]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}