{"id":"https://openalex.org/W4385823116","doi":"https://doi.org/10.21437/interspeech.2023-1727","title":"GenerTTS: Pronunciation Disentanglement for Timbre and Style Generalization in Cross-Lingual Text-to-Speech","display_name":"GenerTTS: Pronunciation Disentanglement for Timbre and Style Generalization in Cross-Lingual Text-to-Speech","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823116","doi":"https://doi.org/10.21437/interspeech.2023-1727"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-1727","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1727","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/A5006210168","display_name":"Yahuan Cong","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yahuan Cong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100425887","display_name":"Haoyu Zhang","orcid":"https://orcid.org/0000-0002-3896-170X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoyu Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102741130","display_name":"Haopeng Lin","orcid":"https://orcid.org/0009-0005-8447-2797"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haopeng Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100682515","display_name":"Shichao Liu","orcid":"https://orcid.org/0000-0002-3163-161X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shichao Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100601920","display_name":"Chunfeng Wang","orcid":"https://orcid.org/0000-0001-9676-8425"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chunfeng Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101499461","display_name":"Yi Ren","orcid":"https://orcid.org/0000-0001-9360-8653"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Ren","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101874107","display_name":"Xiang Yin","orcid":"https://orcid.org/0000-0003-0741-4831"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Yin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5110851569","display_name":"Zejun Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zejun Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5006210168"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3302,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64920653,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5486","last_page":"5490"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9950000047683716,"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":0.9950000047683716,"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":0.9919000267982483,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9733999967575073,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.8019181489944458},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7335802912712097},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.681856095790863},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6167857050895691},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5963764190673828},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.5823518633842468},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34652531147003174},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.24912795424461365},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1976284384727478},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.09479159116744995},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.04122909903526306}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.8019181489944458},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7335802912712097},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.681856095790863},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6167857050895691},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5963764190673828},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.5823518633842468},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34652531147003174},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24912795424461365},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1976284384727478},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.09479159116744995},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.04122909903526306},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-1727","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1727","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2406877384","https://openalex.org/W2595839522","https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2124576126","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W2000075989","https://openalex.org/W2138455584"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-28T09:10:13.091523","created_date":"2025-10-10T00:00:00"}
