{"id":"https://openalex.org/W3198609073","doi":"https://doi.org/10.21437/interspeech.2021-660","title":"A Universal Multi-Speaker Multi-Style Text-to-Speech via Disentangled Representation Learning Based on R&amp;#233;nyi Divergence Minimization","display_name":"A Universal Multi-Speaker Multi-Style Text-to-Speech via Disentangled Representation Learning Based on R&amp;#233;nyi Divergence Minimization","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3198609073","doi":"https://doi.org/10.21437/interspeech.2021-660","mag":"3198609073"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-660","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5041343074","display_name":"Dipjyoti Paul","orcid":"https://orcid.org/0000-0002-5320-1602"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dipjyoti Paul","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102910914","display_name":"Sankar Mukherjee","orcid":"https://orcid.org/0000-0002-0515-0804"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sankar Mukherjee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010084334","display_name":"Yannis Pantazis","orcid":"https://orcid.org/0000-0002-2009-7562"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yannis Pantazis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5035745788","display_name":"Yannis Stylianou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yannis Stylianou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5597,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.73655313,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3625","last_page":"3629"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9983999729156494,"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":0.9955999851226807,"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/style","display_name":"Style (visual arts)","score":0.6786061525344849},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.6116055846214294},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6037842035293579},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5917384624481201},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.535869836807251},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.49875450134277344},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3621801733970642},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3556186556816101},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2085147500038147},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.0716366171836853},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.059383898973464966}],"concepts":[{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.6786061525344849},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.6116055846214294},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6037842035293579},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5917384624481201},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.535869836807251},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.49875450134277344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3621801733970642},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3556186556816101},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2085147500038147},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0716366171836853},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.059383898973464966},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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:10.21437/interspeech.2021-660","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2136144249","https://openalex.org/W2527729766","https://openalex.org/W2794490148","https://openalex.org/W2803832867","https://openalex.org/W2900148439","https://openalex.org/W2903739847","https://openalex.org/W2949382160","https://openalex.org/W2963403868","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2994658979","https://openalex.org/W3015212100","https://openalex.org/W3048423403","https://openalex.org/W3135644023"],"related_works":["https://openalex.org/W2356229341","https://openalex.org/W3208095355","https://openalex.org/W2177370417","https://openalex.org/W2052507016","https://openalex.org/W2180461068","https://openalex.org/W2349768204","https://openalex.org/W2051816080","https://openalex.org/W4313326281","https://openalex.org/W4310813911","https://openalex.org/W574867512"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
