{"id":"https://openalex.org/W4392981515","doi":"https://doi.org/10.1109/icaiic60209.2024.10463204","title":"Advancing AI Voice Synthesis: Integrating Emotional Expression in Multi-Speaker Voice Generation","display_name":"Advancing AI Voice Synthesis: Integrating Emotional Expression in Multi-Speaker Voice Generation","publication_year":2024,"publication_date":"2024-02-19","ids":{"openalex":"https://openalex.org/W4392981515","doi":"https://doi.org/10.1109/icaiic60209.2024.10463204"},"language":"en","primary_location":{"id":"doi:10.1109/icaiic60209.2024.10463204","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaiic60209.2024.10463204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","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/A5051639604","display_name":"Shivani Sanjay Kolekar","orcid":"https://orcid.org/0000-0001-8422-6071"},"institutions":[{"id":"https://openalex.org/I111277659","display_name":"Chonnam National University","ror":"https://ror.org/05kzjxq56","country_code":"KR","type":"education","lineage":["https://openalex.org/I111277659"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Shivani Sanjay Kolekar","raw_affiliation_strings":["Chonnam National University,Department of Artificial Intelligence Convergence,Gwangju,South Korea","Department of Artificial Intelligence Convergence, Chonnam National University, Gwangju, South Korea"],"affiliations":[{"raw_affiliation_string":"Chonnam National University,Department of Artificial Intelligence Convergence,Gwangju,South Korea","institution_ids":["https://openalex.org/I111277659"]},{"raw_affiliation_string":"Department of Artificial Intelligence Convergence, Chonnam National University, Gwangju, South Korea","institution_ids":["https://openalex.org/I111277659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009794289","display_name":"David J. Richter","orcid":"https://orcid.org/0000-0001-5413-6710"},"institutions":[{"id":"https://openalex.org/I111277659","display_name":"Chonnam National University","ror":"https://ror.org/05kzjxq56","country_code":"KR","type":"education","lineage":["https://openalex.org/I111277659"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"David J. Richter","raw_affiliation_strings":["Chonnam National University,Department of Artificial Intelligence Convergence,Gwangju,South Korea","Department of Artificial Intelligence Convergence, Chonnam National University, Gwangju, South Korea"],"affiliations":[{"raw_affiliation_string":"Chonnam National University,Department of Artificial Intelligence Convergence,Gwangju,South Korea","institution_ids":["https://openalex.org/I111277659"]},{"raw_affiliation_string":"Department of Artificial Intelligence Convergence, Chonnam National University, Gwangju, South Korea","institution_ids":["https://openalex.org/I111277659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094198699","display_name":"MD Ilias Bappi","orcid":null},"institutions":[{"id":"https://openalex.org/I111277659","display_name":"Chonnam National University","ror":"https://ror.org/05kzjxq56","country_code":"KR","type":"education","lineage":["https://openalex.org/I111277659"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Md Ilias Bappi","raw_affiliation_strings":["Chonnam National University,Department of Artificial Intelligence Convergence,Gwangju,South Korea","Department of Artificial Intelligence Convergence, Chonnam National University, Gwangju, South Korea"],"affiliations":[{"raw_affiliation_string":"Chonnam National University,Department of Artificial Intelligence Convergence,Gwangju,South Korea","institution_ids":["https://openalex.org/I111277659"]},{"raw_affiliation_string":"Department of Artificial Intelligence Convergence, Chonnam National University, Gwangju, South Korea","institution_ids":["https://openalex.org/I111277659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015500546","display_name":"Kyungbaek Kim","orcid":"https://orcid.org/0000-0001-9985-3051"},"institutions":[{"id":"https://openalex.org/I111277659","display_name":"Chonnam National University","ror":"https://ror.org/05kzjxq56","country_code":"KR","type":"education","lineage":["https://openalex.org/I111277659"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyungbaek Kim","raw_affiliation_strings":["Chonnam National University,Department of Artificial Intelligence Convergence,Gwangju,South Korea","Department of Artificial Intelligence Convergence, Chonnam National University, Gwangju, South Korea"],"affiliations":[{"raw_affiliation_string":"Chonnam National University,Department of Artificial Intelligence Convergence,Gwangju,South Korea","institution_ids":["https://openalex.org/I111277659"]},{"raw_affiliation_string":"Department of Artificial Intelligence Convergence, Chonnam National University, Gwangju, South Korea","institution_ids":["https://openalex.org/I111277659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5051639604"],"corresponding_institution_ids":["https://openalex.org/I111277659"],"apc_list":null,"apc_paid":null,"fwci":2.0726,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.88063302,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"193","last_page":"198"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.896399974822998,"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/T12031","display_name":"Speech and dialogue systems","score":0.896399974822998,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.8220000267028809,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.8181999921798706,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7225000858306885},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7112799286842346},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6055184006690979},{"id":"https://openalex.org/keywords/voice-analysis","display_name":"Voice analysis","score":0.5476235151290894},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.514609694480896},{"id":"https://openalex.org/keywords/voice-command-device","display_name":"Voice command device","score":0.4996635913848877},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.4971063435077667},{"id":"https://openalex.org/keywords/s-voice","display_name":"S Voice","score":0.4377436935901642},{"id":"https://openalex.org/keywords/voice-communication","display_name":"Voice communication","score":0.4291975796222687},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4252203702926636},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.31458723545074463},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.11121034622192383}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7225000858306885},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7112799286842346},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6055184006690979},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.5476235151290894},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.514609694480896},{"id":"https://openalex.org/C178718744","wikidata":"https://www.wikidata.org/wiki/Q2350070","display_name":"Voice command device","level":2,"score":0.4996635913848877},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.4971063435077667},{"id":"https://openalex.org/C81696912","wikidata":"https://www.wikidata.org/wiki/Q718502","display_name":"S Voice","level":2,"score":0.4377436935901642},{"id":"https://openalex.org/C2983306500","wikidata":"https://www.wikidata.org/wiki/Q52946","display_name":"Voice communication","level":2,"score":0.4291975796222687},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4252203702926636},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.31458723545074463},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.11121034622192383},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icaiic60209.2024.10463204","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaiic60209.2024.10463204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2085662862","https://openalex.org/W2326830712","https://openalex.org/W2519091744","https://openalex.org/W2747874407","https://openalex.org/W2946200149","https://openalex.org/W2963163163","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W3033411150","https://openalex.org/W3097828251","https://openalex.org/W3163573274","https://openalex.org/W3196308991","https://openalex.org/W3196475561","https://openalex.org/W4221152438","https://openalex.org/W4221165968","https://openalex.org/W4224928632","https://openalex.org/W4225746985","https://openalex.org/W4310447808","https://openalex.org/W4323896824","https://openalex.org/W4385993826","https://openalex.org/W6734815144","https://openalex.org/W6763832098"],"related_works":["https://openalex.org/W1481470095","https://openalex.org/W2974139573","https://openalex.org/W2603738923","https://openalex.org/W2398516981","https://openalex.org/W1915283592","https://openalex.org/W2946335951","https://openalex.org/W2801338149","https://openalex.org/W2417199973","https://openalex.org/W3143398958","https://openalex.org/W4392981515"],"abstract_inverted_index":{"Advancements":[0],"in":[1,26,34,72],"text-to-speech":[2],"(TTS)":[3],"synthesis":[4],"have":[5],"primarily":[6],"focused":[7],"on":[8],"natural":[9],"speech":[10,12,36,145],"and":[11,19,33,70,112,123,147,163,177,182],"intelligibility,":[13],"but":[14],"integrating":[15],"nuanced":[16],"emotional":[17,84,114,181],"expressiveness":[18,85],"speaker":[20,110,167,183],"variability":[21],"remains":[22],"a":[23,41,93,154],"challenge,":[24],"especially":[25],"dynamic":[27],"environments":[28],"such":[29,50],"as":[30,51],"customer":[31],"service":[32],"assistive":[35],"technologies.":[37],"This":[38],"paper":[39,170],"introduces":[40],"direct":[42],"text":[43],"input":[44,104],"approach":[45],"over":[46],"conventional":[47],"phoneme-first":[48],"methods,":[49],"FastSpeech,":[52],"enhancing":[53],"user":[54],"experience.":[55],"We":[56,143],"integrate":[57,135],"the":[58,73,77,83,129,150],"extended":[59],"Geneva":[60],"Minimalistic":[61],"Acoustic":[62],"Parameter":[63],"Set":[64],"(eGeMAPS)":[65],"along":[66],"with":[67,149],"pitch,":[68],"energy,":[69],"duration":[71],"variance":[74],"adaptor":[75],"of":[76,86],"FastSpeech":[78],"2":[79],"model":[80],"to":[81,103,119,126,134,175],"deepen":[82],"speech.":[87],"In":[88],"this":[89],"paper,":[90],"we":[91],"propose":[92],"Multi-speaker":[94],"Emotional":[95],"Text-to-speech":[96],"Synthesis":[97],"System":[98],"(METTS)":[99],"which":[100],"allows":[101,132],"users":[102,133],"desired":[105],"text,":[106],"select":[107],"from":[108,117],"various":[109],"voices,":[111],"choose":[113],"tones":[115],"ranging":[116],"happiness":[118],"sadness,":[120],"surprise,":[121],"neutrality,":[122],"anger.":[124],"Unique":[125],"METTS":[127],"is":[128],"feature":[130],"that":[131],"personal":[136],"voice":[137],"datasets,":[138],"making":[139],"it":[140],"highly":[141],"customizable.":[142],"assess":[144],"quality":[146],"naturalness":[148],"NISQA":[151],"model,":[152],"achieving":[153],"3.72":[155],"\u00b1":[156],"0.78":[157],"MOS":[158],"score":[159],"for":[160,165,179],"multi-speaker":[161],"evaluation":[162],"4.09\u00b10.65":[164],"individual":[166],"voices.":[168],"The":[169],"details":[171],"METTS's":[172],"architecture,":[173],"enhancements":[174],"FastSpeech2,":[176],"methods":[178],"embedding":[180],"variations.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}