{"id":"https://openalex.org/W4408352615","doi":"https://doi.org/10.1109/icassp49660.2025.10888169","title":"Incremental Disentanglement for Environment-Aware Zero-Shot Text-to-Speech Synthesis","display_name":"Incremental Disentanglement for Environment-Aware Zero-Shot Text-to-Speech Synthesis","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352615","doi":"https://doi.org/10.1109/icassp49660.2025.10888169"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888169","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888169","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5072371384","display_name":"Ye-Xin Lu","orcid":"https://orcid.org/0009-0009-8026-0702"},"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":"Ye-Xin Lu","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067982618","display_name":"Hui-Peng Du","orcid":null},"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":"Hui-Peng Du","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004434747","display_name":"Zheng-Yan Sheng","orcid":"https://orcid.org/0009-0002-0638-5530"},"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":"Zheng-Yan Sheng","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045907056","display_name":"Yang Ai","orcid":"https://orcid.org/0000-0001-6668-022X"},"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":"Yang Ai","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","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":"Zhen-Hua Ling","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9977999925613403,"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":0.9977999925613403,"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":0.9628999829292297,"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":0.9474999904632568,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.729899525642395},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6368759870529175},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5346004366874695},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5175789594650269},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5130242705345154},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33487701416015625},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3270016014575958},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07462289929389954}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.729899525642395},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6368759870529175},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5346004366874695},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5175789594650269},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5130242705345154},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33487701416015625},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3270016014575958},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07462289929389954},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888169","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888169","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6200000047683716}],"awards":[],"funders":[{"id":"https://openalex.org/F4320330944","display_name":"Nature","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1677182931","https://openalex.org/W1989337816","https://openalex.org/W2086139506","https://openalex.org/W2141411743","https://openalex.org/W2808631503","https://openalex.org/W3015676952","https://openalex.org/W3024869864","https://openalex.org/W3037038648","https://openalex.org/W3196584150","https://openalex.org/W3205925339","https://openalex.org/W3209984917","https://openalex.org/W4297841519","https://openalex.org/W4385245566","https://openalex.org/W4385807442","https://openalex.org/W4385822407","https://openalex.org/W4385822534","https://openalex.org/W4392910492","https://openalex.org/W4392910802","https://openalex.org/W6757817989","https://openalex.org/W6777694618","https://openalex.org/W6783527727","https://openalex.org/W6796464841","https://openalex.org/W6805710207","https://openalex.org/W6848735303"],"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":{"This":[0],"paper":[1],"proposes":[2],"an":[3,49,54,66,70,80],"Incremental":[4],"Disentanglement-based":[5],"Environment-Aware":[6],"zero-shot":[7],"text-to-speech":[8],"(TTS)":[9],"method,":[10],"dubbed":[11],"IDEA-TTS,":[12],"that":[13,140],"can":[14],"synthesize":[15],"speech":[16,114,135,152],"for":[17,133],"unseen":[18],"speakers":[19],"while":[20,87],"preserving":[21],"the":[22,35,41,62,88,92,96,102,105,112,123,131,146,165],"acoustic":[23,166],"characteristics":[24],"of":[25,95,104,164],"a":[26,116],"given":[27],"environment":[28,55,67,74,81,85,126,167],"reference":[29],"speech.":[30],"IDEA-TTS":[31,141,160],"adopts":[32],"VITS":[33],"as":[34],"TTS":[36,148],"backbone.":[37],"To":[38],"effectively":[39],"disentangle":[40],"environment,":[42],"speaker,":[43],"and":[44,69,98,125,156,170],"text":[45,99],"factors,":[46],"we":[47],"propose":[48],"incremental":[50],"disentanglement":[51,94],"process,":[52],"where":[53],"estimator":[56],"is":[57,76,161],"designed":[58],"to":[59,83],"first":[60],"decompose":[61],"environmental":[63,113,157],"spectrogram":[64,90],"into":[65,130],"mask":[68,75],"enhanced":[71,89],"spectrogram.":[72],"The":[73],"then":[77],"processed":[78],"by":[79],"encoder":[82],"extract":[84],"embeddings,":[86,107],"facilitates":[91],"subsequent":[93],"speaker":[97,106,119,124,154],"factors":[100],"with":[101],"condition":[103],"which":[108],"are":[109,128],"extracted":[110],"from":[111],"using":[115],"pretrained":[117],"environment-robust":[118],"encoder.":[120],"Finally,":[121],"both":[122],"embeddings":[127],"conditioned":[129],"decoder":[132],"environment-aware":[134,147],"generation.":[136],"Experimental":[137],"results":[138],"demonstrate":[139],"achieves":[142,171],"superior":[143],"performance":[144],"in":[145,151],"task,":[149],"excelling":[150],"quality,":[153],"similarity,":[155],"similarity.":[158],"Additionally,":[159],"also":[162],"capable":[163],"conversion":[168],"task":[169],"state-of-the-art":[172],"performance.":[173]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}