{"id":"https://openalex.org/W7131239881","doi":"https://doi.org/10.1016/j.csl.2026.101956","title":"Cro-MTVITS: An end-to-end cross-lingual speech synthesis model for Mandarin and multi-dialect Tibetan based on VITS","display_name":"Cro-MTVITS: An end-to-end cross-lingual speech synthesis model for Mandarin and multi-dialect Tibetan based on VITS","publication_year":2026,"publication_date":"2026-02-24","ids":{"openalex":"https://openalex.org/W7131239881","doi":"https://doi.org/10.1016/j.csl.2026.101956"},"language":"en","primary_location":{"id":"doi:10.1016/j.csl.2026.101956","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.csl.2026.101956","pdf_url":null,"source":{"id":"https://openalex.org/S91252481","display_name":"Computer Speech & Language","issn_l":"0885-2308","issn":["0885-2308","1095-8363"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Speech &amp; Language","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/A5126700697","display_name":"Weizhao Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I68986083","display_name":"Northwest Normal University","ror":"https://ror.org/00gx3j908","country_code":"CN","type":"education","lineage":["https://openalex.org/I68986083"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weizhao Zhang","raw_affiliation_strings":["College of Physics and Electronic Engineering, Northwest Normal University, China"],"raw_orcid":"https://orcid.org/0000-0002-3692-4921","affiliations":[{"raw_affiliation_string":"College of Physics and Electronic Engineering, Northwest Normal University, China","institution_ids":["https://openalex.org/I68986083"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121832315","display_name":"Mengjuan Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I68986083","display_name":"Northwest Normal University","ror":"https://ror.org/00gx3j908","country_code":"CN","type":"education","lineage":["https://openalex.org/I68986083"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengjuan Wang","raw_affiliation_strings":["College of Physics and Electronic Engineering, Northwest Normal University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Physics and Electronic Engineering, Northwest Normal University, China","institution_ids":["https://openalex.org/I68986083"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126694426","display_name":"Junzhi Li","orcid":null},"institutions":[{"id":"https://openalex.org/I68986083","display_name":"Northwest Normal University","ror":"https://ror.org/00gx3j908","country_code":"CN","type":"education","lineage":["https://openalex.org/I68986083"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junzhi Li","raw_affiliation_strings":["College of Physics and Electronic Engineering, Northwest Normal University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Physics and Electronic Engineering, Northwest Normal University, China","institution_ids":["https://openalex.org/I68986083"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126663131","display_name":"Hongwu Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I68986083","display_name":"Northwest Normal University","ror":"https://ror.org/00gx3j908","country_code":"CN","type":"education","lineage":["https://openalex.org/I68986083"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongwu Yang","raw_affiliation_strings":["School of Educational Technology, Northwest Normal University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Educational Technology, Northwest Normal University, China","institution_ids":["https://openalex.org/I68986083"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5126700697"],"corresponding_institution_ids":["https://openalex.org/I68986083"],"apc_list":{"value":3400,"currency":"USD","value_usd":3400},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18336726,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"100","issue":null,"first_page":"101956","last_page":"101956"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8234000205993652,"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":0.8234000205993652,"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/T10028","display_name":"Topic Modeling","score":0.04439999908208847,"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":0.014600000344216824,"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/mandarin-chinese","display_name":"Mandarin Chinese","score":0.8986999988555908},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.8080999851226807},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.5842000246047974},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5328999757766724},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5023999810218811},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.46880000829696655},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4490000009536743},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.4278999865055084}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.8986999988555908},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8352000117301941},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.8080999851226807},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6310999989509583},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.5842000246047974},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5328999757766724},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5303000211715698},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5023999810218811},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.46880000829696655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44999998807907104},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4490000009536743},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.4278999865055084},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.4068000018596649},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.375900000333786},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.37130001187324524},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.31380000710487366},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.25589999556541443}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.csl.2026.101956","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.csl.2026.101956","pdf_url":null,"source":{"id":"https://openalex.org/S91252481","display_name":"Computer Speech & Language","issn_l":"0885-2308","issn":["0885-2308","1095-8363"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Speech &amp; Language","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6678627133369446,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2451584550","display_name":null,"funder_award_id":"NWNU-LKQN2024-11","funder_id":"https://openalex.org/F4320312274","funder_display_name":"Northwest Normal University"},{"id":"https://openalex.org/G6664317164","display_name":"\u85cf\u65cf\u5730\u533a\u513f\u7ae5\u56fd\u5bb6\u901a\u7528\u8bed\u8a00\u53e3\u8bed\u667a\u80fd\u5b66\u4e60\u7684\u7814\u7a76","funder_award_id":"62067008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320312274","display_name":"Northwest Normal University","ror":"https://ror.org/00gx3j908"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W127087823","https://openalex.org/W1576227399","https://openalex.org/W2025638820","https://openalex.org/W2031768607","https://openalex.org/W2081254602","https://openalex.org/W2102003408","https://openalex.org/W2111284386","https://openalex.org/W2134973740","https://openalex.org/W2294797155","https://openalex.org/W2400517318","https://openalex.org/W2401698713","https://openalex.org/W2747874407","https://openalex.org/W2922185715","https://openalex.org/W2936832667","https://openalex.org/W2963964591","https://openalex.org/W2964002616","https://openalex.org/W2964243274","https://openalex.org/W2972473628","https://openalex.org/W2972730416","https://openalex.org/W3016139610","https://openalex.org/W3016428274","https://openalex.org/W3140429000","https://openalex.org/W3197186640","https://openalex.org/W3198533616","https://openalex.org/W3209059054","https://openalex.org/W4297798717","https://openalex.org/W4310191190","https://openalex.org/W4385809948","https://openalex.org/W4391020683","https://openalex.org/W4401322334","https://openalex.org/W4406417959","https://openalex.org/W4406461669"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-06-15T08:34:33.830935","created_date":"2026-02-25T00:00:00"}
