{"id":"https://openalex.org/W4297841883","doi":"https://doi.org/10.21437/interspeech.2022-831","title":"Decoupled Pronunciation and Prosody Modeling in Meta-Learning-based Multilingual Speech Synthesis","display_name":"Decoupled Pronunciation and Prosody Modeling in Meta-Learning-based Multilingual Speech Synthesis","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841883","doi":"https://doi.org/10.21437/interspeech.2022-831"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-831","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-831","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5013398130","display_name":"Yukun Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yukun Peng","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhenhua Ling","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5059767940"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4257","last_page":"4261"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.98089998960495,"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":0.98089998960495,"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/T12031","display_name":"Speech and dialogue systems","score":0.9469000101089478,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.7874281406402588},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7526013255119324},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.732641339302063},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5830127596855164},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5660977363586426},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5381428003311157},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4983370304107666},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.24806714057922363}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7874281406402588},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7526013255119324},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.732641339302063},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5830127596855164},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5660977363586426},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5381428003311157},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4983370304107666},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24806714057922363},{"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:10.21437/interspeech.2022-831","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-831","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G8663906801","display_name":"\u9762\u5411\u8bed\u97f3\u5408\u6210\u7684\u795e\u7ecf\u7f51\u7edc\u58f0\u7801\u5668\u7814\u7a76","funder_award_id":"61871358","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1731081199","https://openalex.org/W2049686551","https://openalex.org/W2494654097","https://openalex.org/W2525997790","https://openalex.org/W2767052532","https://openalex.org/W2808706139","https://openalex.org/W2888456631","https://openalex.org/W2936832667","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2972473628","https://openalex.org/W2972802841","https://openalex.org/W2973084242","https://openalex.org/W2973177731","https://openalex.org/W3030437843","https://openalex.org/W3092028330","https://openalex.org/W3095012670","https://openalex.org/W3097674564","https://openalex.org/W3197186640"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W2579204149","https://openalex.org/W2037482962","https://openalex.org/W2395605663","https://openalex.org/W2465421051","https://openalex.org/W2005104111","https://openalex.org/W1866214668","https://openalex.org/W3140955690","https://openalex.org/W2364136279","https://openalex.org/W2090830255"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,25,30,38,52],"method":[4,23,50,90],"of":[5,15,97],"decoupled":[6],"pronunciation":[7,64,72],"and":[8,37,60,65,74,95],"prosody":[9,66,76],"modeling":[10],"to":[11,41],"improve":[12],"the":[13,71,75,93,103],"performance":[14],"meta-learning-based":[16],"multilingual":[17,98],"speech":[18,99],"synthesis.The":[19],"baseline":[20,104],"meta-learning":[21,105],"synthesis":[22,100,106],"adopts":[24],"single":[26,39],"text":[27],"encoder":[28],"with":[29,102],"parameter":[31],"generator":[32],"conditioned":[33],"on":[34],"language":[35],"embeddings":[36],"decoder":[40],"predict":[42],"mel-spectrograms":[43],"for":[44,63],"all":[45],"languages.In":[46,85],"contrast,":[47],"our":[48,86,88],"proposed":[49,89],"designs":[51],"two-stream":[53],"model":[54],"structure":[55],"that":[56,70],"contains":[57],"two":[58,61],"encoders":[59],"decoders":[62],"modeling,":[67],"respectively,":[68],"considering":[69],"knowledge":[73,77],"should":[78],"be":[79],"shared":[80],"in":[81],"different":[82],"ways":[83],"among":[84],"experiments,":[87],"effectively":[91],"improved":[92],"intelligibility":[94],"naturalness":[96],"comparing":[101],"method.":[107]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}