{"id":"https://openalex.org/W4413079894","doi":"https://doi.org/10.1145/3749102","title":"Mongolian Emotional Speech Synthesis Based on CGAN and Improved FastSpeech2","display_name":"Mongolian Emotional Speech Synthesis Based on CGAN and Improved FastSpeech2","publication_year":2025,"publication_date":"2025-07-17","ids":{"openalex":"https://openalex.org/W4413079894","doi":"https://doi.org/10.1145/3749102"},"language":"en","primary_location":{"id":"doi:10.1145/3749102","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3749102","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","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/A5029995116","display_name":"Qing-Dao-Er-Ji Ren","orcid":"https://orcid.org/0000-0003-3079-764X"},"institutions":[{"id":"https://openalex.org/I144917393","display_name":"Mongolian University of Science and Technology","ror":"https://ror.org/02shmve39","country_code":"MN","type":"education","lineage":["https://openalex.org/I144917393"]}],"countries":["MN"],"is_corresponding":false,"raw_author_name":"Ren Qingdaoerji","raw_affiliation_strings":["Inner Mongolia University of Technology"],"raw_orcid":"https://orcid.org/0000-0003-3079-764X","affiliations":[{"raw_affiliation_string":"Inner Mongolia University of Technology","institution_ids":["https://openalex.org/I144917393"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yang Yang","orcid":"https://orcid.org/0009-0002-6654-4150"},"institutions":[{"id":"https://openalex.org/I144917393","display_name":"Mongolian University of Science and Technology","ror":"https://ror.org/02shmve39","country_code":"MN","type":"education","lineage":["https://openalex.org/I144917393"]}],"countries":["MN"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["Inner Mongolia University of Technology"],"raw_orcid":"https://orcid.org/0009-0002-6654-4150","affiliations":[{"raw_affiliation_string":"Inner Mongolia University of Technology","institution_ids":["https://openalex.org/I144917393"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041377957","display_name":"Lele Wang","orcid":"https://orcid.org/0009-0008-2974-9898"},"institutions":[{"id":"https://openalex.org/I144917393","display_name":"Mongolian University of Science and Technology","ror":"https://ror.org/02shmve39","country_code":"MN","type":"education","lineage":["https://openalex.org/I144917393"]}],"countries":["MN"],"is_corresponding":false,"raw_author_name":"Wang Lele","raw_affiliation_strings":["Inner Mongolia University of Technology"],"raw_orcid":"https://orcid.org/0009-0008-2974-9898","affiliations":[{"raw_affiliation_string":"Inner Mongolia University of Technology","institution_ids":["https://openalex.org/I144917393"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I144917393"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09853308,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"24","issue":"9","first_page":"1","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9919000267982483,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.989300012588501,"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/computer-science","display_name":"Computer science","score":0.7180139422416687},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6569476127624512},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6562926173210144},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.556327760219574},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4493900537490845},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4408813416957855},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43920278549194336},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4103807806968689},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17293885350227356}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7180139422416687},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6569476127624512},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6562926173210144},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.556327760219574},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4493900537490845},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4408813416957855},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43920278549194336},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4103807806968689},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17293885350227356},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3749102","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3749102","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1975163393","https://openalex.org/W2262393948","https://openalex.org/W2519091744","https://openalex.org/W2899575547","https://openalex.org/W2903739847","https://openalex.org/W2904459034","https://openalex.org/W2964243274","https://openalex.org/W4210777104","https://openalex.org/W4387575377","https://openalex.org/W6600339963"],"related_works":["https://openalex.org/W231741463","https://openalex.org/W4200068392","https://openalex.org/W2772686614","https://openalex.org/W2152945827","https://openalex.org/W114226241","https://openalex.org/W2015513221","https://openalex.org/W301864623","https://openalex.org/W2757826346","https://openalex.org/W2184371793","https://openalex.org/W2349468610"],"abstract_inverted_index":{"Mongolian":[0,8,11,29,47,60,102,130,141],"speech":[1,54,62,95,104,126,132,143],"synthesis":[2,96,105],"is":[3,134],"a":[4,27,43,59,101],"technology":[5],"that":[6,119],"converts":[7],"text":[9],"into":[10],"speech.":[12],"In":[13],"order":[14],"to":[15],"improve":[16],"the":[17,76,94,120,128,137],"emotional":[18,53,61,103,125,131,142],"expressiveness":[19],"of":[20,124],"synthesized":[21],"speech,":[22],"this":[23,57,98],"article":[24,99],"first":[25],"proposed":[26],"lightweight":[28],"phoneme":[30],"pre-training":[31],"model":[32,79,106,138],"WFST-MnG2P":[33],"based":[34,107],"on":[35,108,127],"weighted":[36],"finite":[37],"state":[38],"transition":[39],"machine.":[40],"Secondly,":[41],"as":[42],"representative":[44],"low-resource":[45],"language,":[46],"currently":[48],"has":[49],"no":[50],"open":[51],"source":[52],"corpus.":[55],"For":[56],"reason,":[58],"corpus":[63,133],"containing":[64],"seven":[65],"discrete":[66],"emotions":[67,147],"was":[68],"constructed,":[69],"totaling":[70],"about":[71],"2.25":[72],"hours.":[73],"Finally,":[74],"since":[75],"non-autoregressive":[77],"acoustic":[78],"can":[80,139],"reduce":[81],"word":[82,84],"skipping,":[83],"missing,":[85],"repeated":[86],"pronunciation,":[87],"and":[88,91,113,136,148],"so":[89],"on,":[90],"speed":[92],"up":[93],"speed,":[97],"proposes":[100],"conditional":[109],"generative":[110],"adversarial":[111],"network":[112],"improved":[114],"FastSpeech2.":[115],"Experimental":[116],"results":[117],"show":[118],"average":[121],"MOS":[122],"score":[123],"self-built":[129],"3.69,":[135],"synthesize":[140],"with":[144],"rich":[145],"multi-dimensional":[146],"more":[149],"robustness.":[150]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
