{"id":"https://openalex.org/W3197034238","doi":"https://doi.org/10.21437/interspeech.2021-1148","title":"EMOVIE: A Mandarin Emotion Speech Dataset with a Simple Emotional Text-to-Speech Model","display_name":"EMOVIE: A Mandarin Emotion Speech Dataset with a Simple Emotional Text-to-Speech Model","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3197034238","doi":"https://doi.org/10.21437/interspeech.2021-1148","mag":"3197034238"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1148","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5012657658","display_name":"Chenye Cui","orcid":"https://orcid.org/0009-0009-9083-1628"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenye Cui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088179161","display_name":"Yi Ren","orcid":"https://orcid.org/0000-0001-9889-5460"},"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/A5065126806","display_name":"Jinglin Liu","orcid":"https://orcid.org/0000-0002-9905-3887"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinglin Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060844215","display_name":"Feiyang Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feiyang Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011787904","display_name":"Rongjie Huang","orcid":"https://orcid.org/0000-0002-1695-9000"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rongjie Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058896884","display_name":"Ming Lei","orcid":"https://orcid.org/0000-0002-5712-3285"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3789,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.90623516,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2766","last_page":"2770"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9850999712944031,"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":0.9850999712944031,"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":0.9735000133514404,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9593999981880188,"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":0.805213451385498},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6824900507926941},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6385596990585327},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.6225449442863464},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5217707753181458},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5153012275695801},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4683949947357178},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4431854784488678},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43660539388656616},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0886971652507782}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.805213451385498},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6824900507926941},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6385596990585327},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.6225449442863464},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5217707753181458},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5153012275695801},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4683949947357178},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4431854784488678},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43660539388656616},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0886971652507782},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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:10.21437/interspeech.2021-1148","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2078713291","https://openalex.org/W2361574037","https://openalex.org/W2386292991","https://openalex.org/W2364440891","https://openalex.org/W2393726922","https://openalex.org/W2366752344"],"abstract_inverted_index":{"Recently,":[0],"there":[1],"has":[2],"been":[3],"an":[4,143],"increasing":[5],"interest":[6],"in":[7,20,169],"neural":[8,14],"speech":[9,33,48,71,95,124,172],"synthesis.":[10],"While":[11],"the":[12,17,43,51,117,127,131,137,153,170,178,181],"deep":[13],"network":[15],"achieves":[16],"state-of-the-art":[18],"result":[19],"text-to-speech":[21],"(TTS)":[22],"tasks,":[23],"how":[24],"to":[25,39,42],"generate":[26,121],"a":[27,36,68,88,158,166],"more":[28,31,122],"emotional":[29,55,94,171],"and":[30,50,65,79,120,156],"expressive":[32,123],"is":[34],"becoming":[35],"new":[37],"challenge":[38],"researchers":[40],"due":[41],"scarcity":[44],"of":[45,53,139,160,180],"high-quality":[46],"emotion":[47,70,81,113,128,144],"dataset":[49,72,141,155],"lack":[52],"advanced":[54],"TTS":[56],"model.":[57,183],"In":[58,130],"this":[59],"paper,":[60],"we":[61,86,134,148,175],"first":[62,135],"briefly":[63],"introduce":[64],"publicly":[66],"release":[67],"Mandarin":[69],"including":[73],"9,724":[74],"samples":[75],"with":[76],"audio":[77,106],"files":[78],"its":[80],"human-labeled":[82],"annotation.":[83],"After":[84],"that,":[85],"propose":[87],"simple":[89],"but":[90],"efficient":[91],"architecture":[92],"for":[93],"synthesis":[96,173],"called":[97],"EMSpeech.":[98],"Unlike":[99],"those":[100],"models":[101],"which":[102],"need":[103],"additional":[104],"reference":[105],"as":[107],"input,":[108],"our":[109,140,150],"model":[110,151],"could":[111],"predict":[112],"labels":[114],"just":[115],"from":[116],"input":[118],"text":[119],"conditioned":[125],"on":[126,152],"embedding.":[129],"experiment":[132],"phase,":[133],"validate":[136],"effectiveness":[138],"by":[142,164],"classification":[145],"task.":[146],"Then":[147],"train":[149],"proposed":[154,182],"conduct":[157],"series":[159],"subjective":[161],"evaluations.":[162],"Finally,":[163],"showing":[165],"comparable":[167],"performance":[168],"task,":[174],"successfully":[176],"demonstrate":[177],"ability":[179]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}