{"id":"https://openalex.org/W4304099317","doi":"https://doi.org/10.1145/3503161.3547855","title":"ProDiff","display_name":"ProDiff","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304099317","doi":"https://doi.org/10.1145/3503161.3547855"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3547855","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547855","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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 30th ACM International Conference on Multimedia","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/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":true,"raw_author_name":"Rongjie Huang","raw_affiliation_strings":["Zhejiang University, HangZhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, HangZhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","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, HangZhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, HangZhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070862393","display_name":"Huadai Liu","orcid":null},"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":"Huadai Liu","raw_affiliation_strings":["Zhejiang University, HangZhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, HangZhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065126806","display_name":"Jinglin Liu","orcid":"https://orcid.org/0000-0002-9905-3887"},"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":"Jinglin Liu","raw_affiliation_strings":["Zhejiang University, HangZhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, HangZhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012657658","display_name":"Chenye Cui","orcid":"https://orcid.org/0009-0009-9083-1628"},"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":"Chenye Cui","raw_affiliation_strings":["Zhejiang University, HangZhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, HangZhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101812346","display_name":"Yi Ren","orcid":"https://orcid.org/0000-0001-7423-6719"},"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, HangZhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, HangZhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5011787904"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":12.8566,"has_fulltext":false,"cited_by_count":176,"citation_normalized_percentile":{"value":0.99242063,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2595","last_page":"2605"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9991000294685364,"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":0.7917883396148682},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6530069708824158},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5062558054924011},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4453069269657135},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.43743178248405457},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4290922284126282},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.42611610889434814},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4122306704521179},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3844478130340576},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37206482887268066},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.17755573987960815},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.08417046070098877}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7917883396148682},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6530069708824158},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5062558054924011},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4453069269657135},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.43743178248405457},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4290922284126282},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.42611610889434814},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4122306704521179},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3844478130340576},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37206482887268066},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.17755573987960815},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.08417046070098877},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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:10.1145/3503161.3547855","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547855","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2067295501","https://openalex.org/W2107860279","https://openalex.org/W2133665775","https://openalex.org/W2765811365","https://openalex.org/W2903739847","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W3015338123","https://openalex.org/W3026874504","https://openalex.org/W3180196270","https://openalex.org/W3206191467","https://openalex.org/W4285345683"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2157978810","https://openalex.org/W4391547476","https://openalex.org/W2597809628"],"abstract_inverted_index":{"Denoising":[0],"diffusion":[1,32,69,109,217],"probabilistic":[2],"models":[3,41,195,218],"(DDPMs)":[4],"have":[5],"recently":[6],"achieved":[7],"leading":[8],"performances":[9],"in":[10,98,116,237],"many":[11],"generative":[12],"tasks.":[13],"However,":[14],"the":[15,28,78,85,103,113,117,124,128,137,142,155,165,226,252],"inherited":[16],"iterative":[17],"sampling":[18,166,203],"process":[19],"costs":[20],"hinder":[21],"their":[22],"applications":[23],"to":[24,48,93,158,181,221,251],"text-to-speech":[25,222],"deployment.":[26],"Through":[27],"preliminary":[29],"study":[30],"on":[31,66,210],"model":[33,70,87,104,126,147,157],"parameterization,":[34],"we":[35,63,242],"find":[36],"that":[37,175,234,245],"previous":[38,75],"gradient-based":[39],"TTS":[40,156],"require":[42],"hundreds":[43,197],"or":[44],"thousands":[45],"of":[46,170,198,205],"iterations":[47,180],"guarantee":[49],"high":[50],"sample":[51,188],"quality,":[52],"which":[53],"poses":[54],"a":[55,145,202,211],"challenge":[56,106],"for":[57,71,80,225],"accelerating":[58,99],"sampling.":[59,100],"In":[60],"this":[61],"work,":[62],"propose":[64],"ProDiff,":[65],"progressive":[67],"fast":[68],"high-quality":[72],"text-to-speech.":[73],"Unlike":[74],"work":[76],"estimating":[77],"gradient":[79],"data":[81,92,114],"density,":[82],"ProDiff":[83,111,176,200,238,246],"parameterizes":[84],"denoising":[86,125],"by":[88,168],"directly":[89],"predicting":[90],"clean":[91],"avoid":[94],"distinct":[95],"quality":[96,189],"degradation":[97],"To":[101],"tackle":[102],"convergence":[105],"with":[107,148,193],"decreased":[108],"iterations,":[110],"reduces":[112,164],"variance":[115],"target":[118,139],"site":[119],"via":[120],"knowledge":[121],"distillation.":[122],"Specifically,":[123],"uses":[127],"generated":[129],"mel-spectrogram":[130],"from":[131],"an":[132],"N-step":[133],"DDIM":[134],"teacher":[135],"as":[136],"training":[138],"and":[140,162,190,241],"distills":[141],"behavior":[143],"into":[144],"new":[146],"N/2":[149],"steps.":[150,199],"As":[151],"such,":[152],"it":[153,186],"allows":[154],"make":[159],"sharp":[160],"predictions":[161],"further":[163,243],"time":[167],"orders":[169],"magnitude.":[171],"Our":[172,229],"evaluation":[173],"demonstrates":[174],"needs":[177],"only":[178],"2":[179],"synthesize":[182],"high-fidelity":[183],"mel-spectrograms,":[184],"while":[185],"maintains":[187],"diversity":[191],"competitive":[192],"state-of-the-art":[194],"using":[196],"enables":[201],"speed":[204],"24x":[206],"faster":[207],"than":[208],"real-time":[209],"single":[212],"NVIDIA":[213],"2080Ti":[214],"GPU,":[215],"making":[216],"practically":[219],"applicable":[220],"synthesis":[223],"deployment":[224],"first":[227],"time.":[228],"extensive":[230],"ablation":[231],"studies":[232],"demonstrate":[233],"each":[235],"design":[236],"is":[239],"effective,":[240],"show":[244],"can":[247],"be":[248],"easily":[249],"extended":[250],"multi-speaker":[253],"setting.":[254]},"counts_by_year":[{"year":2026,"cited_by_count":53},{"year":2025,"cited_by_count":50},{"year":2024,"cited_by_count":49},{"year":2023,"cited_by_count":24}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2022-10-10T00:00:00"}