{"id":"https://openalex.org/W4405709416","doi":"https://doi.org/10.1109/iscslp63861.2024.10800403","title":"Expressive Speech Synthesis with Theme-Oriented Few-Shot Learning in ICAGC 2024","display_name":"Expressive Speech Synthesis with Theme-Oriented Few-Shot Learning in ICAGC 2024","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709416","doi":"https://doi.org/10.1109/iscslp63861.2024.10800403"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800403","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800403","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5032698563","display_name":"Haoyu Wang","orcid":"https://orcid.org/0000-0002-3604-4799"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haoyu Wang","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049261843","display_name":"Tianrui Wang","orcid":"https://orcid.org/0009-0005-1517-9589"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianrui Wang","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Cheng Gong","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Gong","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086017661","display_name":"Yu Jiang","orcid":"https://orcid.org/0000-0002-0728-5673"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Jiang","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050293960","display_name":"Qiuyu Liu","orcid":"https://orcid.org/0009-0000-9494-646X"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiuyu Liu","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101745213","display_name":"Longbiao Wang","orcid":"https://orcid.org/0000-0002-8094-6861"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longbiao Wang","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017251198","display_name":"Jianwu Dang","orcid":"https://orcid.org/0000-0002-9237-4821"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianwu Dang","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5032698563"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21370838,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"606","last_page":"610"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9690999984741211,"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":0.9690999984741211,"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":0.7379521131515503},{"id":"https://openalex.org/keywords/theme","display_name":"Theme (computing)","score":0.6313107013702393},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6165945529937744},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4687424302101135},{"id":"https://openalex.org/keywords/one-shot","display_name":"One shot","score":0.4570198059082031},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.44329962134361267},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3948850929737091},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37456345558166504},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.16040006279945374},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10423967242240906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7379521131515503},{"id":"https://openalex.org/C33566652","wikidata":"https://www.wikidata.org/wiki/Q1065927","display_name":"Theme (computing)","level":2,"score":0.6313107013702393},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6165945529937744},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4687424302101135},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.4570198059082031},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.44329962134361267},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3948850929737091},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37456345558166504},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.16040006279945374},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10423967242240906},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800403","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800403","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":30,"referenced_works":["https://openalex.org/W1975163393","https://openalex.org/W2129142580","https://openalex.org/W2752796333","https://openalex.org/W3023996010","https://openalex.org/W3034942609","https://openalex.org/W3044514286","https://openalex.org/W3096831136","https://openalex.org/W3160844600","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3213544594","https://openalex.org/W4221165968","https://openalex.org/W4221166168","https://openalex.org/W4283689139","https://openalex.org/W4307323391","https://openalex.org/W4385486424","https://openalex.org/W4391020683","https://openalex.org/W4391021721","https://openalex.org/W4392903524","https://openalex.org/W4392909624","https://openalex.org/W4401070302","https://openalex.org/W4402301063","https://openalex.org/W4405709275","https://openalex.org/W6755207826","https://openalex.org/W6767111847","https://openalex.org/W6777694618","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6796464841","https://openalex.org/W6848735303"],"related_works":["https://openalex.org/W2497720472","https://openalex.org/W4292659306","https://openalex.org/W3044321615","https://openalex.org/W2806221744","https://openalex.org/W2326937258","https://openalex.org/W394267150","https://openalex.org/W2773965352","https://openalex.org/W4294892107","https://openalex.org/W2357748469","https://openalex.org/W2392917037"],"abstract_inverted_index":{"This":[0,78,96],"paper":[1],"introduces":[2],"an":[3],"expressive":[4],"speech":[5,31,61],"synthesis":[6,62],"system":[7,52],"submitted":[8],"to":[9,21,36,75,99,103],"Track":[10],"1":[11],"of":[12,17,25,120],"ICAGC":[13],"2024.":[14],"The":[15,114],"objective":[16],"this":[18],"track":[19],"is":[20],"clone":[22],"the":[23,26,82,93,101,107,118],"voices":[24],"target":[27],"speakers":[28,90],"using":[29],"provided":[30],"data":[32],"and":[33,47,110],"modulate":[34],"them":[35],"convey":[37],"appropriate":[38],"emotions":[39],"for":[40],"various":[41],"themes,":[42],"such":[43],"as":[44],"novel":[45],"chapters":[46],"ancient":[48],"Chinese":[49],"poems.":[50],"Our":[51],"primarily":[53],"employs":[54],"a":[55,58,69,125],"pretrained":[56],"GPT-SoVITS,":[57],"two-stage":[59],"large-scale":[60],"system.":[63],"In":[64],"addition,":[65],"we":[66],"have":[67],"developed":[68],"theme-oriented":[70],"few-shot":[71],"learning":[72],"strategy":[73,79],"tailored":[74],"specific":[76,108],"themes.":[77],"involves":[80],"fine-tuning":[81],"pre-trained":[83],"models":[84,102],"with":[85],"sentences":[86],"spoken":[87],"by":[88],"different":[89],"but":[91],"on":[92,105],"same":[94],"theme.":[95],"approach":[97],"aims":[98],"refine":[100],"focus":[104],"both":[106],"themes":[109],"individual":[111],"speaker":[112],"characteristics.":[113],"competition":[115],"results":[116],"underscore":[117],"efficacy":[119],"our":[121],"approach,":[122],"culminating":[123],"in":[124],"fourth-place":[126],"finish":[127],"among":[128],"all":[129],"participating":[130],"teams.":[131]},"counts_by_year":[],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}
