{"id":"https://openalex.org/W4285605725","doi":"https://doi.org/10.24963/ijcai.2022/577","title":"FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis","display_name":"FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4285605725","doi":"https://doi.org/10.24963/ijcai.2022/577"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2022/577","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/577","pdf_url":"https://www.ijcai.org/proceedings/2022/0577.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2022/0577.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011787904","display_name":"Rongjie Huang","orcid":"https://orcid.org/0000-0002-1695-9000"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongjie Huang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102313170","display_name":"Max W. Y. Lam","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Max W. Y. Lam","raw_affiliation_strings":["Tencent AI Lab, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100384686","display_name":"Jun Wang","orcid":"https://orcid.org/0000-0002-1305-5735"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Wang","raw_affiliation_strings":["Tencent AI Lab, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075183307","display_name":"Dan Su","orcid":"https://orcid.org/0000-0001-5746-9545"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Su","raw_affiliation_strings":["Tencent AI Lab, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088179161","display_name":"Yi Ren","orcid":"https://orcid.org/0000-0001-9889-5460"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Ren","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.9912,"has_fulltext":false,"cited_by_count":86,"citation_normalized_percentile":{"value":0.9819242,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4157","last_page":"4163"},"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":0.9987999796867371,"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":0.9986000061035156,"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":0.8143287897109985},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6841413974761963},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.672880232334137},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.625968337059021},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.42309603095054626},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4173811674118042},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.41302230954170227},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33553028106689453}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8143287897109985},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6841413974761963},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.672880232334137},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.625968337059021},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.42309603095054626},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4173811674118042},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.41302230954170227},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33553028106689453},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.24963/ijcai.2022/577","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/577","pdf_url":"https://www.ijcai.org/proceedings/2022/0577.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10156662","is_oa":false,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10156662/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"     In:  Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence (IJCAI-22).  (pp. pp. 4157-4163).  IJCAI:International Joint Conferences on Artificial Intelligence Organization: Vienna. (2022)     ","raw_type":"Proceedings paper"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2022/577","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/577","pdf_url":"https://www.ijcai.org/proceedings/2022/0577.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.41999998688697815,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285605725.pdf","grobid_xml":"https://content.openalex.org/works/W4285605725.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2067295501","https://openalex.org/W2519091744","https://openalex.org/W2765811365","https://openalex.org/W2963300588","https://openalex.org/W3026874504","https://openalex.org/W3033411150","https://openalex.org/W3036167779","https://openalex.org/W3092028330","https://openalex.org/W3121370741","https://openalex.org/W3123097577","https://openalex.org/W3129651364","https://openalex.org/W3161172673","https://openalex.org/W3169905056","https://openalex.org/W3173110665","https://openalex.org/W3197273793","https://openalex.org/W4226213470","https://openalex.org/W4226376398","https://openalex.org/W4285345683","https://openalex.org/W4287184558","https://openalex.org/W4287761884","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2897924318","https://openalex.org/W2138997758","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W4253660971","https://openalex.org/W2041273198","https://openalex.org/W1599055764","https://openalex.org/W2131711534"],"abstract_inverted_index":{"Denoising":[0],"diffusion":[1,34,130],"probabilistic":[2],"models":[3,131],"(DDPMs)":[4],"have":[5],"recently":[6],"achieved":[7],"leading":[8],"performances":[9],"in":[10,162],"many":[11],"generative":[12],"tasks.":[13],"However,":[14],"the":[15,71,76,105,139,150],"inherited":[16],"iterative":[17],"sampling":[18,72,118],"process":[19],"costs":[20],"hindered":[21],"their":[22],"applications":[23],"to":[24,53,69,134,149],"speech":[25,38,92,112,135],"synthesis.":[26,39,165],"This":[27],"paper":[28],"proposes":[29],"FastDiff,":[30,81],"a":[31,42,117,126],"fast":[32],"conditional":[33],"model":[35,55],"for":[36,138],"high-quality":[37],"FastDiff":[40,103,115,146],"employs":[41],"stack":[43],"of":[44,48,102,120,153],"time-aware":[45],"location-variable":[46],"convolutions":[47],"diverse":[49],"receptive":[50],"field":[51],"patterns":[52],"efficiently":[54],"long-term":[56],"time":[57],"dependencies":[58],"with":[59,108],"adaptive":[60],"conditions.":[61],"A":[62],"noise":[63],"schedule":[64],"predictor":[65],"is":[66],"also":[67],"adopted":[68],"reduce":[70],"steps":[73],"without":[74,94],"sacrificing":[75],"generation":[77],"quality.":[78],"Based":[79],"on":[80,125],"we":[82],"design":[83],"an":[84],"end-to-end":[85,163],"text-to-speech":[86,164],"synthesizer,":[87],"FastDiff-TTS,":[88],"which":[89],"generates":[90],"high-fidelity":[91],"waveforms":[93],"any":[95],"intermediate":[96],"feature":[97],"(e.g.,":[98],"Mel-spectrogram).":[99],"Our":[100],"evaluation":[101],"demonstrates":[104],"state-of-the-art":[106],"results":[107],"higher-quality":[109],"(MOS":[110],"4.28)":[111],"samples.":[113],"Also,":[114],"enables":[116],"speed":[119],"58x":[121],"faster":[122],"than":[123],"real-time":[124],"V100":[127],"GPU,":[128],"making":[129],"practically":[132],"applicable":[133],"synthesis":[136],"deployment":[137],"first":[140],"time.":[141],"We":[142],"further":[143],"show":[144],"that":[145],"generalized":[147],"well":[148],"mel-spectrogram":[151],"inversion":[152],"unseen":[154],"speakers,":[155],"and":[156],"FastDiff-TTS":[157],"outperformed":[158],"other":[159],"competing":[160],"methods":[161],"Audio":[166],"samples":[167],"are":[168],"available":[169],"at":[170],"https://FastDiff.github.io/.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":32},{"year":2024,"cited_by_count":25},{"year":2023,"cited_by_count":20}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}