{"id":"https://openalex.org/W4403999409","doi":"https://doi.org/10.1007/978-981-97-8795-1_18","title":"StyleFusion TTS: Multimodal Style-Control and\u00a0Enhanced Feature Fusion for\u00a0Zero-Shot Text-to-Speech Synthesis","display_name":"StyleFusion TTS: Multimodal Style-Control and\u00a0Enhanced Feature Fusion for\u00a0Zero-Shot Text-to-Speech Synthesis","publication_year":2024,"publication_date":"2024-11-02","ids":{"openalex":"https://openalex.org/W4403999409","doi":"https://doi.org/10.1007/978-981-97-8795-1_18"},"language":"en","primary_location":{"id":"doi:10.1007/978-981-97-8795-1_18","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-97-8795-1_18","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"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/A5057534444","display_name":"Zhiyong Chen","orcid":"https://orcid.org/0000-0002-9629-6111"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Chen","raw_affiliation_strings":["School of Communication and Information Engineering, Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-9629-6111","affiliations":[{"raw_affiliation_string":"School of Communication and Information Engineering, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015889784","display_name":"Xinnuo Li","orcid":null},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinnuo Li","raw_affiliation_strings":["School of Communication and Information Engineering, Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0003-9600-868X","affiliations":[{"raw_affiliation_string":"School of Communication and Information Engineering, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113231440","display_name":"Zhiqi Ai","orcid":"https://orcid.org/0009-0005-1034-9972"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqi Ai","raw_affiliation_strings":["School of Communication and Information Engineering, Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0005-1034-9972","affiliations":[{"raw_affiliation_string":"School of Communication and Information Engineering, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084521046","display_name":"Shugong Xu","orcid":"https://orcid.org/0000-0003-1905-6269"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shugong Xu","raw_affiliation_strings":["School of Communication and Information Engineering, Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1905-6269","affiliations":[{"raw_affiliation_string":"School of Communication and Information Engineering, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5015889784"],"corresponding_institution_ids":["https://openalex.org/I113940042"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"263","last_page":"277"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9958999752998352,"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":0.9933000206947327,"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":0.7754426002502441},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6942969560623169},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.653759241104126},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5493615865707397},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5381271839141846},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5160307884216309},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.47321170568466187},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46176594495773315},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.45139357447624207},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.425403356552124},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37342432141304016},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1896589696407318},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.0695754885673523}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7754426002502441},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6942969560623169},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.653759241104126},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5493615865707397},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5381271839141846},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5160307884216309},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.47321170568466187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46176594495773315},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.45139357447624207},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.425403356552124},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37342432141304016},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1896589696407318},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0695754885673523},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-981-97-8795-1_18","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-97-8795-1_18","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W3099284785","https://openalex.org/W3135367836","https://openalex.org/W3163573274","https://openalex.org/W4375869257","https://openalex.org/W4385822787","https://openalex.org/W4385823163","https://openalex.org/W4385823483","https://openalex.org/W4391021679","https://openalex.org/W4391620705","https://openalex.org/W4393152865","https://openalex.org/W4399096462","https://openalex.org/W6600020652","https://openalex.org/W6600042225","https://openalex.org/W6600231796","https://openalex.org/W6600402904","https://openalex.org/W6601658864","https://openalex.org/W6601949647","https://openalex.org/W6602958129","https://openalex.org/W6604820196"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
