{"id":"https://openalex.org/W4205087900","doi":"https://doi.org/10.1109/ialp54817.2021.9675192","title":"Mongolian emotional speech synthesis based on transfer learning and emotional embedding","display_name":"Mongolian emotional speech synthesis based on transfer learning and emotional embedding","publication_year":2021,"publication_date":"2021-12-11","ids":{"openalex":"https://openalex.org/W4205087900","doi":"https://doi.org/10.1109/ialp54817.2021.9675192"},"language":"en","primary_location":{"id":"doi:10.1109/ialp54817.2021.9675192","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp54817.2021.9675192","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Conference on Asian Language Processing (IALP)","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/A5046211928","display_name":"Aihong Huang","orcid":"https://orcid.org/0000-0003-4609-173X"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aihong Huang","raw_affiliation_strings":["National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Provincial Key Laboratory of Mongolian Information Processing Technology, School of Computer Science, Inner Mongolia University, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Provincial Key Laboratory of Mongolian Information Processing Technology, School of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014372166","display_name":"Feilong Bao","orcid":"https://orcid.org/0000-0001-7312-1629"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feilong Bao","raw_affiliation_strings":["National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Provincial Key Laboratory of Mongolian Information Processing Technology, School of Computer Science, Inner Mongolia University, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Provincial Key Laboratory of Mongolian Information Processing Technology, School of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076174513","display_name":"Guanglai Gao","orcid":"https://orcid.org/0009-0005-5513-1192"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanglai Gao","raw_affiliation_strings":["National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Provincial Key Laboratory of Mongolian Information Processing Technology, School of Computer Science, Inner Mongolia University, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Provincial Key Laboratory of Mongolian Information Processing Technology, School of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088775444","display_name":"Shan Yu","orcid":"https://orcid.org/0000-0003-2253-9448"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Shan","raw_affiliation_strings":["National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Provincial Key Laboratory of Mongolian Information Processing Technology, School of Computer Science, Inner Mongolia University, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Provincial Key Laboratory of Mongolian Information Processing Technology, School of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082746577","display_name":"Rui Liu","orcid":"https://orcid.org/0000-0003-4524-7413"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Liu","raw_affiliation_strings":["National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Provincial Key Laboratory of Mongolian Information Processing Technology, School of Computer Science, Inner Mongolia University, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Provincial Key Laboratory of Mongolian Information Processing Technology, School of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2722730"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"80","issue":null,"first_page":"78","last_page":"83"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9858999848365784,"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":0.9380000233650208,"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/disgust","display_name":"Disgust","score":0.7539632320404053},{"id":"https://openalex.org/keywords/surprise","display_name":"Surprise","score":0.7310805320739746},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.7252309322357178},{"id":"https://openalex.org/keywords/sadness","display_name":"Sadness","score":0.6690160632133484},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6532446146011353},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6085762977600098},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5188649892807007},{"id":"https://openalex.org/keywords/boredom","display_name":"Boredom","score":0.5143269300460815},{"id":"https://openalex.org/keywords/anger","display_name":"Anger","score":0.424686461687088},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39313018321990967},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3842656910419464},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.25690513849258423},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.1326155662536621}],"concepts":[{"id":"https://openalex.org/C2777375102","wikidata":"https://www.wikidata.org/wiki/Q208351","display_name":"Disgust","level":3,"score":0.7539632320404053},{"id":"https://openalex.org/C2780343955","wikidata":"https://www.wikidata.org/wiki/Q333173","display_name":"Surprise","level":2,"score":0.7310805320739746},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7252309322357178},{"id":"https://openalex.org/C2779812673","wikidata":"https://www.wikidata.org/wiki/Q169251","display_name":"Sadness","level":3,"score":0.6690160632133484},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6532446146011353},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6085762977600098},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5188649892807007},{"id":"https://openalex.org/C2777589236","wikidata":"https://www.wikidata.org/wiki/Q34255","display_name":"Boredom","level":2,"score":0.5143269300460815},{"id":"https://openalex.org/C2779302386","wikidata":"https://www.wikidata.org/wiki/Q79871","display_name":"Anger","level":2,"score":0.424686461687088},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39313018321990967},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3842656910419464},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.25690513849258423},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.1326155662536621},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ialp54817.2021.9675192","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp54817.2021.9675192","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Conference on Asian Language Processing (IALP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5199999809265137}],"awards":[{"id":"https://openalex.org/G4177377619","display_name":null,"funder_award_id":"61773224,62066033","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5435010561","display_name":null,"funder_award_id":"2018YFE0122900","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2165698076","https://openalex.org/W2172247269","https://openalex.org/W2519091744","https://openalex.org/W2619368999","https://openalex.org/W2770743791","https://openalex.org/W2790783922","https://openalex.org/W2794490148","https://openalex.org/W2795109282","https://openalex.org/W2885952204","https://openalex.org/W2887280559","https://openalex.org/W2937870435","https://openalex.org/W2944622002","https://openalex.org/W2963091184","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2966387353","https://openalex.org/W2969658393","https://openalex.org/W2994396107","https://openalex.org/W3008691130","https://openalex.org/W3010916717","https://openalex.org/W3015841875","https://openalex.org/W3016151052","https://openalex.org/W3106690208","https://openalex.org/W3135644023","https://openalex.org/W3146550708","https://openalex.org/W4295731579","https://openalex.org/W6750489868","https://openalex.org/W6765987481"],"related_works":["https://openalex.org/W318616257","https://openalex.org/W3118254946","https://openalex.org/W2120267809","https://openalex.org/W4238520549","https://openalex.org/W3216173459","https://openalex.org/W2794357331","https://openalex.org/W4242611441","https://openalex.org/W4242034606","https://openalex.org/W4402346481","https://openalex.org/W2037174948"],"abstract_inverted_index":{"In":[0,50],"recent":[1],"years,":[2],"end-to-end":[3,22],"speech":[4,15,24,43,67,84],"synthesis":[5,16,25,44,68,85],"based":[6],"on":[7,40],"attention":[8],"has":[9,26,101],"achieved":[10],"better":[11],"performance":[12],"than":[13],"traditional":[14],"models,":[17],"and":[18,61,78,99],"the":[19,28,34,38,71,81,106,114,117,129,133,139],"technology":[20],"of":[21,90,116,132,152],"Mongolian":[23,41,58,66,82,164],"reached":[27],"application":[29],"standard.":[30],"However,":[31],"due":[32],"to":[33,52,121],"sparse":[35],"training":[36],"corpus,":[37],"research":[39],"emotional":[42,59,79,83,109,118,123,146,154,165],"is":[45],"still":[46],"far":[47],"from":[48],"perfect.":[49],"response":[51],"these":[53],"problems,":[54],"we":[55],"established":[56],"a":[57,150],"corpus":[60],"constructed":[62],"an":[63],"emotionally":[64],"controllable":[65],"system":[69,86],"for":[70],"first":[72],"time.":[73],"Through":[74],"combining":[75],"transfer":[76],"learning":[77],"embedding,":[80],"with":[87,128],"8":[88],"kinds":[89],"emotions":[91],"(happy,":[92],"angry,":[93],"sadness,":[94],"surprise,":[95],"fear,":[96],"disgust,":[97],"boredom":[98],"neutral)":[100],"been":[102],"achieved.":[103],"We":[104],"proposed":[105],"method":[107,160],"that":[108,138,158],"labels":[110],"are":[111,126],"used":[112],"as":[113],"input":[115],"embedding":[119],"layer":[120],"generate":[122],"vectors,":[124],"which":[125],"spliced":[127],"output":[130],"vectors":[131,142],"bidirectional":[134],"LSTM":[135],"layer,":[136],"so":[137],"text":[140],"representation":[141],"contain":[143],"information":[144],"about":[145],"category,":[147],"thereby":[148],"synthesize":[149,162],"variety":[151],"different":[153],"voices.":[155],"Experiments":[156],"show":[157],"our":[159],"can":[161],"high-quality":[163],"speech.":[166]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
