{"id":"https://openalex.org/W4372260509","doi":"https://doi.org/10.1109/icassp49357.2023.10095776","title":"Multi-Speaker Expressive Speech Synthesis via Multiple Factors Decoupling","display_name":"Multi-Speaker Expressive Speech Synthesis via Multiple Factors Decoupling","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260509","doi":"https://doi.org/10.1109/icassp49357.2023.10095776"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095776","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095776","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/I2800643029","display_name":"Association for Symbolic Logic","ror":"https://ror.org/00baryp08","country_code":"US","type":"other","lineage":["https://openalex.org/I2800643029"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xinfa Zhu","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU)"],"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU)","institution_ids":["https://openalex.org/I2800643029"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100678947","display_name":"Yi Lei","orcid":"https://orcid.org/0000-0003-1105-3258"},"institutions":[{"id":"https://openalex.org/I2800643029","display_name":"Association for Symbolic Logic","ror":"https://ror.org/00baryp08","country_code":"US","type":"other","lineage":["https://openalex.org/I2800643029"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Lei","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU)"],"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU)","institution_ids":["https://openalex.org/I2800643029"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100722258","display_name":"Kun Song","orcid":"https://orcid.org/0000-0001-6110-2770"},"institutions":[{"id":"https://openalex.org/I2800643029","display_name":"Association for Symbolic Logic","ror":"https://ror.org/00baryp08","country_code":"US","type":"other","lineage":["https://openalex.org/I2800643029"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kun Song","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU)"],"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU)","institution_ids":["https://openalex.org/I2800643029"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060467975","display_name":"Yongmao Zhang","orcid":"https://orcid.org/0009-0000-0526-5778"},"institutions":[{"id":"https://openalex.org/I2800643029","display_name":"Association for Symbolic Logic","ror":"https://ror.org/00baryp08","country_code":"US","type":"other","lineage":["https://openalex.org/I2800643029"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yongmao Zhang","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU)"],"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU)","institution_ids":["https://openalex.org/I2800643029"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108515500","display_name":"Tao Li","orcid":"https://orcid.org/0000-0001-6114-8461"},"institutions":[{"id":"https://openalex.org/I2800643029","display_name":"Association for Symbolic Logic","ror":"https://ror.org/00baryp08","country_code":"US","type":"other","lineage":["https://openalex.org/I2800643029"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tao Li","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU)"],"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU)","institution_ids":["https://openalex.org/I2800643029"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100365442","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0002-2994-6743"},"institutions":[{"id":"https://openalex.org/I2800643029","display_name":"Association for Symbolic Logic","ror":"https://ror.org/00baryp08","country_code":"US","type":"other","lineage":["https://openalex.org/I2800643029"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU)"],"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU)","institution_ids":["https://openalex.org/I2800643029"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101883211"],"corresponding_institution_ids":["https://openalex.org/I2800643029"],"apc_list":null,"apc_paid":null,"fwci":2.6185,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.91579281,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9980999827384949,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive 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/computer-science","display_name":"Computer science","score":0.7545691728591919},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7057808637619019},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.6421778202056885},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5291222333908081},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07579880952835083}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7545691728591919},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7057808637619019},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.6421778202056885},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5291222333908081},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07579880952835083},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095776","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095776","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":35,"referenced_works":["https://openalex.org/W2187089797","https://openalex.org/W2770743791","https://openalex.org/W2890287821","https://openalex.org/W2904459034","https://openalex.org/W2932022923","https://openalex.org/W2947445680","https://openalex.org/W3024869864","https://openalex.org/W3096457008","https://openalex.org/W3135644023","https://openalex.org/W3162508345","https://openalex.org/W3163475957","https://openalex.org/W3163568691","https://openalex.org/W3174758275","https://openalex.org/W3197478142","https://openalex.org/W3197659778","https://openalex.org/W3198048667","https://openalex.org/W3198082505","https://openalex.org/W4210777104","https://openalex.org/W4221151538","https://openalex.org/W4226039367","https://openalex.org/W4226421465","https://openalex.org/W4294311176","https://openalex.org/W4320451749","https://openalex.org/W4385245566","https://openalex.org/W6746238782","https://openalex.org/W6750489868","https://openalex.org/W6757422803","https://openalex.org/W6760861152","https://openalex.org/W6778823374","https://openalex.org/W6779459370","https://openalex.org/W6783867762","https://openalex.org/W6795807602","https://openalex.org/W6796464841","https://openalex.org/W6796730497","https://openalex.org/W6849600165"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4313561376","https://openalex.org/W3103825105","https://openalex.org/W3027880158","https://openalex.org/W3207533102","https://openalex.org/W1617565119","https://openalex.org/W160381218","https://openalex.org/W2512958550"],"abstract_inverted_index":{"This":[0],"paper":[1],"aims":[2],"to":[3,80,105,127],"synthesize":[4],"the":[5,17,58,70,83,122,128,149],"target":[6,129],"speaker\u2019s":[7],"speech":[8,23],"with":[9,33],"desired":[10],"speaking":[11,62],"style":[12,18,63],"and":[13,19,43,64,75,86,95,116,139],"emotion":[14,20],"by":[15,25,50],"transferring":[16],"from":[21,108,125],"reference":[22,143],"recorded":[24],"other":[26],"speakers.":[27],"We":[28],"address":[29],"this":[30],"challenging":[31],"problem":[32],"a":[34,39,44,101,136],"two-stage":[35],"framework":[36],"composed":[37],"of":[38,152],"text-to-style-and-emotion":[40],"(Text2SE)":[41],"module":[42],"style-and-":[45],"emotion-to-wave":[46],"(SE2Wave)":[47],"module,":[48],"bridging":[49],"neural":[51],"bottleneck":[52],"(BN)":[53],"features.":[54],"To":[55,119],"further":[56],"solve":[57],"multi-factor":[59],"(speaker":[60],"timbre,":[61],"emotion)":[65],"decoupling":[66],"problem,":[67],"we":[68,99,134],"adopt":[69],"multi-label":[71],"binary":[72],"vector":[73],"(MBV)":[74],"mutual":[76],"information":[77],"(MI)":[78],"minimization":[79],"respectively":[81],"discretize":[82],"extracted":[84],"embeddings":[85],"disentangle":[87],"these":[88],"highly":[89],"entangled":[90],"factors":[91],"in":[92,131],"both":[93],"Text2SE":[94],"SE2Wave":[96],"modules.":[97],"Moreover,":[98],"introduce":[100,135],"semi-supervised":[102],"training":[103],"strategy":[104],"leverage":[106],"data":[107],"multiple":[109],"speakers,":[110],"including":[111],"emotion-labeled":[112],"data,":[113,115],"style-labeled":[114],"unlabeled":[117],"data.":[118],"better":[120],"transfer":[121],"fine-grained":[123],"expression":[124],"references":[126],"speaker":[130],"non-parallel":[132],"transfer,":[133],"reference-candidate":[137],"pool":[138],"propose":[140],"an":[141],"attention-based":[142],"selection":[144],"approach.":[145],"Extensive":[146],"experiments":[147],"demonstrate":[148],"good":[150],"design":[151],"our":[153],"model.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}