{"id":"https://openalex.org/W4408353498","doi":"https://doi.org/10.1109/icassp49660.2025.10890840","title":"DetailTTS: Learning Residual Detail Information for Zero-shot Text-to-speech","display_name":"DetailTTS: Learning Residual Detail Information for Zero-shot Text-to-speech","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353498","doi":"https://doi.org/10.1109/icassp49660.2025.10890840"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890840","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890840","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":"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/A5048004251","display_name":"Cong Wang","orcid":"https://orcid.org/0009-0003-8384-1373"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031705836","display_name":"Yichen Han","orcid":"https://orcid.org/0009-0008-7018-8949"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yichen Han","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102820117","display_name":"Yanli Geng","orcid":"https://orcid.org/0000-0002-4329-6476"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yizhong Geng","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079377968","display_name":"Yingming Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingming Gao","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101419335","display_name":"Fengping Wang","orcid":"https://orcid.org/0009-0001-4420-4553"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengping Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099111159","display_name":"Bingsong Bai","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingsong Bai","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101231780","display_name":"Qifei Li","orcid":"https://orcid.org/0009-0007-0422-6532"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qifei Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033565985","display_name":"Jinlong Xue","orcid":"https://orcid.org/0009-0000-0442-0932"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinlong Xue","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008597430","display_name":"Yayue Deng","orcid":"https://orcid.org/0009-0003-7642-4942"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yayue Deng","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111856667","display_name":"Zhengqi Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengqi Wen","raw_affiliation_strings":["Tsinghua University,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100343662","display_name":"Ya Li","orcid":"https://orcid.org/0000-0002-6284-5039"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ya Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01686139,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9882000088691711,"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":0.9882000088691711,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9848999977111816,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9674999713897705,"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":0.7502710819244385},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6535738110542297},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6308903694152832},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.517001748085022},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4934948682785034},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.4526330530643463},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37907934188842773},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13740602135658264},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.06740760803222656},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06544175744056702}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7502710819244385},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6535738110542297},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6308903694152832},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.517001748085022},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4934948682785034},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4526330530643463},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37907934188842773},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13740602135658264},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.06740760803222656},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06544175744056702},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890840","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890840","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2998572311","https://openalex.org/W3203407300","https://openalex.org/W3209984917","https://openalex.org/W4307323391","https://openalex.org/W4312933868","https://openalex.org/W4391020683","https://openalex.org/W4402111455","https://openalex.org/W4402672020","https://openalex.org/W4412353446","https://openalex.org/W6610566761","https://openalex.org/W6640963894","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6796464841","https://openalex.org/W6847363464","https://openalex.org/W6848735303","https://openalex.org/W6851724922","https://openalex.org/W6852421699","https://openalex.org/W6862144568"],"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":{"Traditional":[0],"text-to-speech":[1],"(TTS)":[2],"systems":[3,123],"often":[4,40],"face":[5],"challenges":[6],"in":[7,124,131],"aligning":[8],"text":[9],"and":[10,19,44,73,127,137],"speech,":[11],"leading":[12],"to":[13,32,93],"the":[14,69,74,90,103,107,114],"omission":[15],"of":[16],"critical":[17],"linguistic":[18],"acoustic":[20],"details.":[21],"This":[22],"misalignment":[23],"creates":[24],"an":[25],"information":[26,82],"gap,":[27],"which":[28,78],"existing":[29],"methods":[30],"attempt":[31],"address":[33,48],"by":[34,105],"incorporating":[35],"additional":[36,110],"inputs,":[37],"but":[38],"these":[39,49],"introduce":[41],"data":[42],"inconsistencies":[43],"increase":[45],"complexity.":[46],"To":[47],"issues,":[50],"we":[51],"propose":[52],"DetailTTS,":[53],"a":[54,60],"zero-shot":[55,132],"TTS":[56,122],"system":[57],"based":[58],"on":[59,113],"conditional":[61],"variational":[62],"autoencoder.":[63],"It":[64],"incorporates":[65],"two":[66],"key":[67],"components:":[68],"Prior":[70],"Detail":[71,76],"Module":[72],"Duration":[75],"Module,":[77],"capture":[79],"residual":[80],"detail":[81],"missed":[83],"during":[84],"alignment.":[85],"These":[86],"modules":[87],"effectively":[88],"enhance":[89],"model\u2019s":[91],"ability":[92],"retain":[94],"fine-grained":[95],"details,":[96],"significantly":[97],"improving":[98],"speech":[99],"quality":[100],"while":[101],"simplifying":[102],"model":[104],"obviating":[106],"need":[108],"for":[109],"inputs.":[111],"Experiments":[112],"WenetSpeech4TTS":[115],"dataset":[116],"show":[117],"that":[118],"DetailTTS":[119],"outperforms":[120],"traditional":[121],"both":[125],"naturalness":[126],"speaker":[128],"similarity,":[129],"even":[130],"scenarios.":[133],"Our":[134],"source":[135],"code":[136],"demo":[138],"page":[139],"are":[140],"available":[141],"at":[142],"https://detailtts.github.io/.":[143]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}