{"id":"https://openalex.org/W4392930780","doi":"https://doi.org/10.1109/icassp48485.2024.10446855","title":"DETS: End-to-End Single-Stage Text-to-Speech Via Hierarchical Diffusion Gan Models","display_name":"DETS: End-to-End Single-Stage Text-to-Speech Via Hierarchical Diffusion Gan Models","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392930780","doi":"https://doi.org/10.1109/icassp48485.2024.10446855"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446855","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446855","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5076315968","display_name":"Linqin Wang","orcid":"https://orcid.org/0000-0001-6293-6742"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linqin Wang","raw_affiliation_strings":["Kunming University of Science and Technology","Yunnan Key Laboratory of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunming University of Science and Technology","institution_ids":["https://openalex.org/I10660446"]},{"raw_affiliation_string":"Yunnan Key Laboratory of Artificial Intelligence","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114488777","display_name":"Zhengtao Yu","orcid":"https://orcid.org/0000-0001-8952-8984"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengtao Yu","raw_affiliation_strings":["Kunming University of Science and Technology","Yunnan Key Laboratory of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunming University of Science and Technology","institution_ids":["https://openalex.org/I10660446"]},{"raw_affiliation_string":"Yunnan Key Laboratory of Artificial Intelligence","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017471172","display_name":"Shengxiang Gao","orcid":"https://orcid.org/0000-0002-2980-8420"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengxiang Gao","raw_affiliation_strings":["Kunming University of Science and Technology","Yunnan Key Laboratory of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunming University of Science and Technology","institution_ids":["https://openalex.org/I10660446"]},{"raw_affiliation_string":"Yunnan Key Laboratory of Artificial Intelligence","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016947527","display_name":"Cunli Mao","orcid":"https://orcid.org/0000-0002-8289-6036"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cunli Mao","raw_affiliation_strings":["Kunming University of Science and Technology","Yunnan Key Laboratory of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunming University of Science and Technology","institution_ids":["https://openalex.org/I10660446"]},{"raw_affiliation_string":"Yunnan Key Laboratory of Artificial Intelligence","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102000307","display_name":"Yuxin Huang","orcid":"https://orcid.org/0000-0003-1277-6212"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxin Huang","raw_affiliation_strings":["Kunming University of Science and Technology","Yunnan Key Laboratory of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunming University of Science and Technology","institution_ids":["https://openalex.org/I10660446"]},{"raw_affiliation_string":"Yunnan Key Laboratory of Artificial Intelligence","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I10660446"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10916","last_page":"10920"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7200454473495483},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6986784934997559},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6358957290649414},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5787132382392883},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.5410834550857544},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5207069516181946},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5036587119102478},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4372224509716034},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4191570281982422},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4187760651111603},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39848828315734863}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7200454473495483},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6986784934997559},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6358957290649414},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5787132382392883},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.5410834550857544},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5207069516181946},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5036587119102478},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4372224509716034},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4191570281982422},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4187760651111603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39848828315734863},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446855","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446855","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2519091744","https://openalex.org/W2591927543","https://openalex.org/W2903739847","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W3015338123","https://openalex.org/W4226063663","https://openalex.org/W6749489859","https://openalex.org/W6765987481","https://openalex.org/W6778823374","https://openalex.org/W6779337556","https://openalex.org/W6779823529","https://openalex.org/W6782760101","https://openalex.org/W6783182287","https://openalex.org/W6783713337","https://openalex.org/W6783867762","https://openalex.org/W6795288823","https://openalex.org/W6796464841","https://openalex.org/W6811008979","https://openalex.org/W6811424244"],"related_works":["https://openalex.org/W169399214","https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W10581632","https://openalex.org/W1927421023","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473"],"abstract_inverted_index":{"End-to-end":[0],"single-stage":[1,21,49],"text-to-speech":[2],"models":[3,22],"have":[4,23],"garnered":[5],"significant":[6],"attention":[7],"in":[8,32,123,131],"recent":[9],"research,":[10],"surpassing":[11],"the":[12,67,77,82,98,103,114,118,159,164,168],"performance":[13,166],"of":[14,81,167],"conventional":[15],"two-stage":[16],"pipeline":[17],"systems.":[18],"While":[19],"prior":[20],"made":[24],"substantial":[25],"advancements,":[26],"there":[27],"remains":[28],"room":[29],"for":[30],"improvement":[31],"addressing":[33],"intermittent":[34],"issues":[35],"related":[36],"to":[37,52,75,96],"unnaturalness":[38],"and":[39,79,106,137],"prosody":[40],"diversity.":[41],"Unlike":[42],"previous":[43],"works,":[44],"we":[45],"propose":[46],"a":[47,86,92,125],"novel":[48],"TTS":[50,115],"framework":[51],"tackle":[53],"these":[54],"problems":[55],"via":[56],"hierarchical":[57],"denoising":[58,68,99,153],"diffusion":[59],"generative":[60],"adversarial":[61],"networks":[62],"(GAN)":[63],"modeling,":[64],"which":[65,101,124],"parameterizes":[66],"model":[69,97,116],"by":[70],"directly":[71],"predicting":[72],"latent":[73],"variables":[74],"improve":[76],"naturalness":[78],"diversity":[80],"generated":[83],"speech.":[84],"Specifically,":[85],"conditional":[87],"GAN":[88],"is":[89],"adopted":[90],"as":[91],"non-Gaussian":[93],"multimodal":[94],"function":[95],"distribution,":[100],"construct":[102],"duration":[104],"predictor":[105],"speech":[107,148],"decoder":[108],"respectively.":[109],"As":[110],"such,":[111],"it":[112],"allows":[113],"learn":[117],"more":[119],"natural":[120],"one-to-many":[121],"relationship":[122],"text":[126],"input":[127],"can":[128,145],"be":[129],"spoken":[130],"multiple":[132],"ways":[133],"with":[134,150],"different":[135],"pitches":[136],"rhythms.":[138],"In":[139],"addition,":[140],"We":[141],"show":[142],"that":[143],"DETS":[144],"generate":[146],"high-fidelity":[147],"waveform":[149],"only":[151],"1":[152],"step.":[154],"Extensive":[155],"experimental":[156],"results":[157],"on":[158],"LJSpeech":[160],"benchmark":[161],"dataset":[162],"demonstrate":[163],"favourable":[165],"proposed":[169],"method.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}