{"id":"https://openalex.org/W4402979888","doi":"https://doi.org/10.1109/icme57554.2024.10688322","title":"Boosting Multi-Speaker Expressive Speech Synthesis with Semi-Supervised Contrastive Learning","display_name":"Boosting Multi-Speaker Expressive Speech Synthesis with Semi-Supervised Contrastive Learning","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979888","doi":"https://doi.org/10.1109/icme57554.2024.10688322"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10688322","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688322","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5101883211","display_name":"Xinfa Zhu","orcid":"https://orcid.org/0000-0001-9275-523X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinfa Zhu","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi’an,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100697204","display_name":"Yuke Li","orcid":"https://orcid.org/0009-0000-7282-8964"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuke Li","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi’an,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013928267","display_name":"Yi Lei","orcid":"https://orcid.org/0000-0002-9256-9311"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Lei","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi’an,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052756710","display_name":"Ning Jiang","orcid":"https://orcid.org/0000-0003-1579-3114"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ning Jiang","raw_affiliation_strings":["Mashang Consumer Finance Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Mashang Consumer Finance Co., Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033795434","display_name":"Guoqing Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guoqing Zhao","raw_affiliation_strings":["Mashang Consumer Finance Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Mashang Consumer Finance Co., Ltd","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi’an,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101883211"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":1.1586,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.81934834,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.995199978351593,"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":0.995199978351593,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9616000056266785,"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/T12031","display_name":"Speech and dialogue systems","score":0.9491000175476074,"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/boosting","display_name":"Boosting (machine learning)","score":0.8094305992126465},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7961703538894653},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6679309606552124},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5217902660369873},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48015064001083374},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.41117575764656067}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.8094305992126465},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7961703538894653},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6679309606552124},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5217902660369873},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48015064001083374},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.41117575764656067}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10688322","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688322","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.49000000953674316,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1731081199","https://openalex.org/W2051217765","https://openalex.org/W2123864036","https://openalex.org/W3024869864","https://openalex.org/W3096457008","https://openalex.org/W3114632476","https://openalex.org/W3135644023","https://openalex.org/W3162811262","https://openalex.org/W3194347141","https://openalex.org/W3197478142","https://openalex.org/W3197659778","https://openalex.org/W3209059054","https://openalex.org/W4210777104","https://openalex.org/W4226421465","https://openalex.org/W4252279978","https://openalex.org/W4290712827","https://openalex.org/W4293691212","https://openalex.org/W4294311176","https://openalex.org/W4297841615","https://openalex.org/W4372260509","https://openalex.org/W4385572372","https://openalex.org/W4387968266"],"related_works":["https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W321304764","https://openalex.org/W2249138175","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2029134149","https://openalex.org/W2368768466"],"abstract_inverted_index":{"This":[0],"paper":[1],"aims":[2],"to":[3,31,51,74],"build":[4],"a":[5,11,25,68,103],"multi-speaker":[6],"expressive":[7,95],"TTS":[8,29],"system,":[9],"synthesizing":[10],"target":[12,104],"speaker\u2019s":[13],"speech":[14,61,96],"with":[15,97],"multiple":[16],"styles":[17,99],"and":[18,34,46,57,64,89,100],"emotions.":[19],"To":[20,93],"this":[21],"end,":[22],"we":[23],"propose":[24],"novel":[26],"contrastive":[27,39],"learning-based":[28],"approach":[30],"transfer":[32],"style":[33,63],"emotion":[35,65],"across":[36],"speakers.":[37],"Specifically,":[38],"learning":[40],"from":[41,60],"different":[42],"levels,":[43],"i.e.":[44],"utterance":[45],"category":[47],"level,":[48],"is":[49,72],"leveraged":[50],"extract":[52],"the":[53,76,106,122,125],"disentangled":[54,108],"style,":[55],"emotion,":[56],"speaker":[58],"representations":[59,109],"for":[62,102],"transfer.":[66],"Furthermore,":[67],"semi-supervised":[69],"training":[70],"strategy":[71],"introduced":[73],"improve":[75],"data":[77,120],"utilization":[78],"efficiency":[79],"by":[80],"involving":[81],"multi-domain":[82,119],"data,":[83,86,88],"including":[84],"style-labeled":[85],"emotion-labeled":[87],"abundant":[90],"unlabeled":[91],"data.":[92],"achieve":[94],"diverse":[98],"emotions":[101],"speaker,":[105],"learned":[107],"are":[110],"integrated":[111],"into":[112],"an":[113],"improved":[114],"VITS":[115],"model.":[116],"Experiments":[117],"on":[118],"demonstrate":[121],"effectiveness":[123],"of":[124],"proposed":[126],"method.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}