{"id":"https://openalex.org/W3198213150","doi":"https://doi.org/10.21437/interspeech.2021-469","title":"Diff-TTS: A Denoising Diffusion Model for Text-to-Speech","display_name":"Diff-TTS: A Denoising Diffusion Model for Text-to-Speech","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3198213150","doi":"https://doi.org/10.21437/interspeech.2021-469","mag":"3198213150"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-469","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-469","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5103069095","display_name":"Myeonghun Jeong","orcid":"https://orcid.org/0000-0002-4689-3110"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Myeonghun Jeong","raw_affiliation_strings":["Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047164073","display_name":"Hyeongju Kim","orcid":"https://orcid.org/0000-0001-8668-0323"},"institutions":[{"id":"https://openalex.org/I4210104771","display_name":"SiliconSapiens (South Korea)","ror":"https://ror.org/015rsk965","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210104771"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyeongju Kim","raw_affiliation_strings":["Neosapience, Inc., Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Neosapience, Inc., Seoul, South Korea","institution_ids":["https://openalex.org/I4210104771"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005088101","display_name":"Sung Jun Cheon","orcid":"https://orcid.org/0000-0002-7293-6997"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sung Jun Cheon","raw_affiliation_strings":["Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101424423","display_name":"Byoung Jin Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byoung Jin Choi","raw_affiliation_strings":["Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051356511","display_name":"Nam Soo Kim","orcid":"https://orcid.org/0000-0002-0568-4902"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nam Soo Kim","raw_affiliation_strings":["Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103069095"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":11.6137,"has_fulltext":false,"cited_by_count":107,"citation_normalized_percentile":{"value":0.9879321,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3605","last_page":"3609"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9965999722480774,"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":0.9965999722480774,"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":0.9876000285148621,"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/T11309","display_name":"Music and Audio Processing","score":0.9139000177383423,"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":0.6938275694847107},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6839579343795776},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.6492533683776855},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.60185706615448},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.486970990896225},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4051496982574463},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07751238346099854}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6938275694847107},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6839579343795776},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.6492533683776855},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.60185706615448},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.486970990896225},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4051496982574463},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07751238346099854},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-469","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-469","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320324891","display_name":"Iran Telecommunication Research Center","ror":"https://ror.org/01a3g2z22"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2519091744","https://openalex.org/W2747874407","https://openalex.org/W2903739847","https://openalex.org/W2946200149","https://openalex.org/W2962834855","https://openalex.org/W2963300588","https://openalex.org/W2963609956","https://openalex.org/W2963691546","https://openalex.org/W2963975282","https://openalex.org/W2964243274","https://openalex.org/W3015282541","https://openalex.org/W3025528898","https://openalex.org/W3026874504","https://openalex.org/W3033411150","https://openalex.org/W3036167779","https://openalex.org/W3038172701","https://openalex.org/W3092028330","https://openalex.org/W3095883095","https://openalex.org/W3118605064","https://openalex.org/W3121370741","https://openalex.org/W3123097577","https://openalex.org/W3125481789","https://openalex.org/W3129651364","https://openalex.org/W3150572638","https://openalex.org/W3166714886","https://openalex.org/W3168053944","https://openalex.org/W4287761884","https://openalex.org/W4320930577","https://openalex.org/W4394666973"],"related_works":["https://openalex.org/W2216757598","https://openalex.org/W3013209356","https://openalex.org/W4387496629","https://openalex.org/W2387796150","https://openalex.org/W2955431177","https://openalex.org/W2772917594","https://openalex.org/W4306742369","https://openalex.org/W4303457083","https://openalex.org/W2799713421","https://openalex.org/W2386796262"],"abstract_inverted_index":{"Although":[0],"neural":[1],"text-to-speech":[2],"(TTS)":[3],"models":[4],"have":[5],"attracted":[6],"a":[7,33,52,62,80,125],"lot":[8],"of":[9],"attention":[10],"and":[11,26,44],"succeeded":[12],"in":[13],"generating":[14],"human-like":[15],"speech,":[16],"there":[17],"is":[18],"still":[19],"room":[20],"for":[21,84],"improvements":[22],"to":[23,56,69,86,101],"its":[24],"naturalness":[25],"architectural":[27],"efficiency.In":[28],"this":[29],"work,":[30],"we":[31,78,92,113],"propose":[32],"novel":[34],"nonautoregressive":[35],"TTS":[36],"model,":[37],"namely":[38],"Diff-TTS,":[39],"which":[40],"achieves":[41],"highly":[42],"natural":[43],"efficient":[45],"speech":[46],"synthesis.Given":[47],"the":[48,58,71,76,89,94,122],"text,":[49,77],"Diff-TTS":[50,100,116],"exploits":[51],"denoising":[53],"diffusion":[54,65],"framework":[55],"transform":[57],"noise":[59],"signal":[60],"into":[61],"mel-spectrogram":[63,72],"via":[64],"time":[66],"steps.In":[67],"order":[68],"learn":[70],"distribution":[73],"conditioned":[74],"on":[75],"present":[79],"likelihood-based":[81],"optimization":[82],"method":[83,97],"TTS.Furthermore,":[85],"boost":[87],"up":[88],"inference":[90],"speed,":[91],"leverage":[93],"accelerated":[95],"sampling":[96],"that":[98,115],"allows":[99],"generate":[102],"raw":[103],"waveforms":[104],"much":[105],"faster":[106,120],"without":[107],"significantly":[108],"degrading":[109],"perceptual":[110],"quality.Through":[111],"experiments,":[112],"verified":[114],"generates":[117],"28":[118],"times":[119],"than":[121],"real-time":[123],"with":[124],"single":[126],"NVIDIA":[127],"2080Ti":[128],"GPU.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":32},{"year":2023,"cited_by_count":38},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":2}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}