{"id":"https://openalex.org/W4406858508","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849063","title":"Disentangling Speaker Representations from Intuitive Prosodic Features for Speaker-Adaptative and Prosody-Controllable Speech Synthesis","display_name":"Disentangling Speaker Representations from Intuitive Prosodic Features for Speaker-Adaptative and Prosody-Controllable Speech Synthesis","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406858508","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849063"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10849063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"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/A5038132023","display_name":"Pengyu Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengyu Cheng","raw_affiliation_strings":["Xiaomi Inc.,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Inc.,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenhua Ling","raw_affiliation_strings":["University of Science and Technology of China,NERC-SLIP,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,NERC-SLIP,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070060970","display_name":"Meng Meng","orcid":"https://orcid.org/0000-0002-5697-9970"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng Meng","raw_affiliation_strings":["Xiaomi Inc.,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Inc.,Beijing,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100362605","display_name":"Yujun Wang","orcid":"https://orcid.org/0000-0002-8353-0423"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yujun Wang","raw_affiliation_strings":["Xiaomi Inc.,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Inc.,Beijing,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9983000159263611,"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":0.9983000159263611,"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":0.9708999991416931,"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":0.9567000269889832,"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/prosody","display_name":"Prosody","score":0.848534345626831},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7318814992904663},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7130613923072815},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5966846942901611},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5067372918128967},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4324076771736145},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3959643840789795}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.848534345626831},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7318814992904663},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7130613923072815},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5966846942901611},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5067372918128967},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4324076771736145},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3959643840789795}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc63619.2025.10849063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2107860279","https://openalex.org/W2767052532","https://openalex.org/W2903739847","https://openalex.org/W2963796886","https://openalex.org/W2964243274","https://openalex.org/W2972440097","https://openalex.org/W2972574864","https://openalex.org/W3010893827","https://openalex.org/W3015338123","https://openalex.org/W3015645837","https://openalex.org/W3015826515","https://openalex.org/W3016008406","https://openalex.org/W3097003111","https://openalex.org/W3097892637","https://openalex.org/W3162791003","https://openalex.org/W3163929126","https://openalex.org/W3198533616","https://openalex.org/W4221162790","https://openalex.org/W6637618735","https://openalex.org/W6748573829","https://openalex.org/W6748588790","https://openalex.org/W6750489868","https://openalex.org/W6752888775","https://openalex.org/W6755135894","https://openalex.org/W6757322325","https://openalex.org/W6778823374","https://openalex.org/W6783867762"],"related_works":["https://openalex.org/W1927421023","https://openalex.org/W10581632","https://openalex.org/W2206035908","https://openalex.org/W3149582125","https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"In":[0,23],"this":[1,24],"paper,":[2],"we":[3],"propose":[4],"a":[5,14,45],"method":[6,97],"of":[7,47,69],"speaker-adaptative":[8],"and":[9,20,37,104],"prosody-controllable":[10],"speech":[11,100],"synthesis":[12],"with":[13,44,77,101],"disentanglement":[15],"between":[16],"intuitive":[17,27,63,78],"prosodic":[18,28,64,79],"features":[19,29,80],"speaker":[21,41,55,72,84],"representations.":[22],"method,":[25],"the":[26,54,67,70,112],"include":[30],"utterance-level":[31],"pitch,":[32],"pitch":[33],"range,":[34],"speak":[35],"rate":[36],"energy.":[38],"A":[39],"residual":[40,71],"information":[42,73],"encoder":[43,74],"set":[46],"adversarial":[48],"classifiers":[49],"is":[50],"designed":[51],"to":[52,81],"extract":[53],"characteristics":[56],"that":[57,94],"can\u2019t":[58],"be":[59],"described":[60],"by":[61],"these":[62],"features.":[65],"Further,":[66],"outputs":[68],"are":[75],"concatenated":[76],"obtain":[82],"complete":[83],"representations":[85],"for":[86],"acoustic":[87],"feature":[88],"prediction.":[89],"Experimental":[90],"results":[91],"have":[92],"demonstrated":[93],"our":[95],"proposed":[96],"can":[98],"synthesize":[99],"better":[102],"naturalness":[103],"higher":[105],"prosody":[106],"controllability":[107],"than":[108],"its":[109],"counterpart":[110],"without":[111],"disentanglement.":[113]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}