{"id":"https://openalex.org/W2973084242","doi":"https://doi.org/10.21437/interspeech.2019-1632","title":"Cross-Lingual, Multi-Speaker Text-To-Speech Synthesis Using Neural Speaker Embedding","display_name":"Cross-Lingual, Multi-Speaker Text-To-Speech Synthesis Using Neural Speaker Embedding","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2973084242","doi":"https://doi.org/10.21437/interspeech.2019-1632","mag":"2973084242"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1632","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","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/A5019092473","display_name":"Mengnan Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mengnan Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059638789","display_name":"Minchuan Chen","orcid":"https://orcid.org/0009-0001-1512-6672"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minchuan Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033522290","display_name":"Shuang Liang","orcid":"https://orcid.org/0000-0001-7003-3906"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuang Liang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100643103","display_name":"Jun Ma","orcid":"https://orcid.org/0009-0003-8713-0667"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100755955","display_name":"Lei Chen","orcid":"https://orcid.org/0000-0003-3068-1583"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100702017","display_name":"Shaojun Wang","orcid":"https://orcid.org/0009-0001-8955-8566"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shaojun Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101623806","display_name":"Jing Xiao","orcid":"https://orcid.org/0009-0002-6516-1916"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":63,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2105","last_page":"2109"},"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":0.9980000257492065,"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":0.9970999956130981,"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":0.7635070085525513},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7583454847335815},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5816916227340698},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4423280656337738},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44171345233917236},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4387889504432678},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4268280565738678},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41867485642433167},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.40805238485336304}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7635070085525513},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7583454847335815},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5816916227340698},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4423280656337738},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44171345233917236},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4387889504432678},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4268280565738678},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41867485642433167},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.40805238485336304}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2019-1632","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W36870606","https://openalex.org/W1562777581","https://openalex.org/W2114010348","https://openalex.org/W2123808477","https://openalex.org/W2398071208","https://openalex.org/W2805993470","https://openalex.org/W2901997113","https://openalex.org/W2962739369","https://openalex.org/W2963192573","https://openalex.org/W2963432880","https://openalex.org/W2963712897","https://openalex.org/W2963975282","https://openalex.org/W2964243274","https://openalex.org/W3099206234"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W4313854686","https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}