{"id":"https://openalex.org/W4414231467","doi":"https://doi.org/10.1109/ialp68296.2024.11156902","title":"Emotional Speech Synthesis Based on Valence-Arousal-Dominance Model and Multi-Feature Codebook","display_name":"Emotional Speech Synthesis Based on Valence-Arousal-Dominance Model and Multi-Feature Codebook","publication_year":2025,"publication_date":"2025-08-03","ids":{"openalex":"https://openalex.org/W4414231467","doi":"https://doi.org/10.1109/ialp68296.2024.11156902"},"language":"en","primary_location":{"id":"doi:10.1109/ialp68296.2024.11156902","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp68296.2024.11156902","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Asian Language Processing (IALP)","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/A5100330608","display_name":"Ying Liu","orcid":"https://orcid.org/0000-0003-1065-1811"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ying Liu","raw_affiliation_strings":["School of Information Science and Engineering, Yunnan University,Kunming,China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Yunnan University,Kunming,China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076764073","display_name":"Jian Yang","orcid":"https://orcid.org/0000-0003-0488-1514"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Yang","raw_affiliation_strings":["School of Information Science and Engineering, Yunnan University,Kunming,China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Yunnan University,Kunming,China","institution_ids":["https://openalex.org/I189210763"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100330608"],"corresponding_institution_ids":["https://openalex.org/I189210763"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13572062,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"255","last_page":"259"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8133999705314636,"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":0.8133999705314636,"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/T10860","display_name":"Speech and Audio Processing","score":0.8068000078201294,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.9014000296592712},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7221999764442444},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5688999891281128},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5333999991416931},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4975999891757965},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.49079999327659607},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48019999265670776},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4715000092983246}],"concepts":[{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.9014000296592712},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.744700014591217},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7221999764442444},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6948000192642212},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5688999891281128},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5333999991416931},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4975999891757965},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49410000443458557},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.49079999327659607},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48019999265670776},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4715000092983246},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3937999904155731},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.3917999863624573},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3776000142097473},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3596999943256378},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3237999975681305},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31690001487731934},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.26080000400543213}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ialp68296.2024.11156902","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp68296.2024.11156902","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Asian Language Processing (IALP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1600722501","https://openalex.org/W1902237438","https://openalex.org/W2066064791","https://openalex.org/W2149628368","https://openalex.org/W2151626637","https://openalex.org/W2966651628","https://openalex.org/W2969658393","https://openalex.org/W3198123658","https://openalex.org/W4205742757","https://openalex.org/W4372259784","https://openalex.org/W4385823160","https://openalex.org/W4392931276","https://openalex.org/W4402115961","https://openalex.org/W4402669711"],"related_works":[],"abstract_inverted_index":{"Despite":[0],"significant":[1],"advancements":[2],"in":[3,14],"emotional":[4,17,40,64,119],"speech":[5,31,123],"synthesis":[6,9,32],"technology,":[7],"existing":[8],"systems":[10],"still":[11],"face":[12],"challenges":[13],"achieving":[15],"fine-grained":[16],"expressiveness":[18,120],"while":[19,124],"maintaining":[20,125],"computational":[21,126],"efficiency.":[22,127],"To":[23],"address":[24],"these":[25],"limitations,":[26],"we":[27,54],"propose":[28],"a":[29,57,84],"novel":[30],"framework":[33,115],"based":[34],"on":[35],"the":[36,92,113,118],"Valence-Arousal-Dominance":[37],"(VAD)":[38],"three-dimensional":[39],"model,":[41],"which":[42],"integrates":[43],"continuous":[44],"emotion":[45],"feature":[46,89],"extraction":[47],"with":[48],"multi-feature":[49],"codebook.":[50],"Within":[51],"this":[52],"framework,":[53],"first":[55],"construct":[56],"multi-dimensional":[58],"codebook":[59,85],"encompassing":[60],"both":[61],"acoustic":[62],"and":[63,105],"features":[65],"by":[66,97],"extracting":[67],"VAD":[68],"characteristics":[69],"from":[70],"training":[71],"set":[72],"audio":[73],"samples.":[74],"An":[75],"intelligent":[76],"retrieval":[77],"strategy":[78],"is":[79,95],"then":[80],"employed":[81],"to":[82],"train":[83],"matcher":[86],"for":[87],"optimal":[88],"matching.":[90],"Additionally,":[91],"text":[93],"encoder":[94],"enhanced":[96],"incorporating":[98],"adaptive":[99],"normalization":[100],"layers,":[101],"rotary":[102],"positional":[103],"encoding,":[104],"local":[106],"attention":[107],"mechanisms.":[108],"Experimental":[109],"results":[110],"demonstrate":[111],"that":[112],"proposed":[114],"significantly":[116],"enhances":[117],"of":[121],"synthesized":[122]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}