{"id":"https://openalex.org/W4416250952","doi":"https://doi.org/10.1109/waspaa66052.2025.11231009","title":"Unsupervised Multi-channel Speech Dereverberation via Diffusion","display_name":"Unsupervised Multi-channel Speech Dereverberation via Diffusion","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4416250952","doi":"https://doi.org/10.1109/waspaa66052.2025.11231009"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa66052.2025.11231009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11231009","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.02071","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043561002","display_name":"Yulun Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yulun Wu","raw_affiliation_strings":["University of Illinois Urbana-Champaign,Department of Electrical and Computer Engineering,Champaign,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign,Department of Electrical and Computer Engineering,Champaign,USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069215134","display_name":"Zhongweiyang Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhongweiyang Xu","raw_affiliation_strings":["University of Illinois Urbana-Champaign,Department of Electrical and Computer Engineering,Champaign,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign,Department of Electrical and Computer Engineering,Champaign,USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080038319","display_name":"Jianchong Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianchong Chen","raw_affiliation_strings":["University of Illinois Urbana-Champaign,Department of Electrical and Computer Engineering,Champaign,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign,Department of Electrical and Computer Engineering,Champaign,USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101607498","display_name":"Zhong-Qiu Wang","orcid":"https://orcid.org/0000-0002-4204-9430"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhong-Qiu Wang","raw_affiliation_strings":["Southern University of Science and Technology,Department of Computer Science and Engineering,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology,Department of Computer Science and Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"last","author":{"id":null,"display_name":"Romit Roy Choudhury","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Romit Roy Choudhury","raw_affiliation_strings":["University of Illinois Urbana-Champaign,Department of Electrical and Computer Engineering,Champaign,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign,Department of Electrical and Computer Engineering,Champaign,USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5043561002"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":1.239,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84620098,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"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/T10860","display_name":"Speech and Audio Processing","score":0.9702000021934509,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9702000021934509,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.00559999980032444,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.004399999976158142,"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/microphone","display_name":"Microphone","score":0.678600013256073},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.6179999709129333},{"id":"https://openalex.org/keywords/impulse-response","display_name":"Impulse response","score":0.49709999561309814},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.47859999537467957},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4609000086784363},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4429999887943268},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4343000054359436},{"id":"https://openalex.org/keywords/impulse","display_name":"Impulse (physics)","score":0.42980000376701355}],"concepts":[{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.678600013256073},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6575999855995178},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.6179999709129333},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.583299994468689},{"id":"https://openalex.org/C72279823","wikidata":"https://www.wikidata.org/wiki/Q1139726","display_name":"Impulse response","level":2,"score":0.49709999561309814},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.47859999537467957},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4609000086784363},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4429999887943268},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4343000054359436},{"id":"https://openalex.org/C70836080","wikidata":"https://www.wikidata.org/wiki/Q837940","display_name":"Impulse (physics)","level":2,"score":0.42980000376701355},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.374099999666214},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3571000099182129},{"id":"https://openalex.org/C149712133","wikidata":"https://www.wikidata.org/wiki/Q332774","display_name":"Anechoic chamber","level":2,"score":0.35010001063346863},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.3409000039100647},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32659998536109924},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3116999864578247},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3091999888420105},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.2879999876022339},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.27129998803138733},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.26269999146461487},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.25780001282691956},{"id":"https://openalex.org/C168031717","wikidata":"https://www.wikidata.org/wiki/Q1530280","display_name":"Balance (ability)","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/waspaa66052.2025.11231009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11231009","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.02071","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.02071","pdf_url":"https://arxiv.org/pdf/2508.02071","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.02071","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.02071","pdf_url":"https://arxiv.org/pdf/2508.02071","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1973669708","https://openalex.org/W2096819401","https://openalex.org/W2130722890","https://openalex.org/W2141998673","https://openalex.org/W2164502538","https://openalex.org/W2242685705","https://openalex.org/W2747732471","https://openalex.org/W2918296821","https://openalex.org/W2964058413","https://openalex.org/W2972359262","https://openalex.org/W3015679215","https://openalex.org/W3195155284","https://openalex.org/W3205567090","https://openalex.org/W3215005424","https://openalex.org/W4223583411","https://openalex.org/W4372341905","https://openalex.org/W4385756463","https://openalex.org/W4386066264","https://openalex.org/W4386437472","https://openalex.org/W4386764055","https://openalex.org/W4401634166","https://openalex.org/W4404787821","https://openalex.org/W4408352491","https://openalex.org/W4411019955"],"related_works":[],"abstract_inverted_index":{"We":[0,103,114],"consider":[1],"the":[2,16,48,100],"problem":[3,49],"of":[4,93],"multi-channel":[5,10,74,82],"single-speaker":[6],"blind":[7],"dereverberation,":[8],"where":[9],"mixtures":[11],"are":[12,68],"used":[13,70],"to":[14,46,71],"recover":[15],"clean":[17,38],"anechoic":[18],"speech.":[19],"To":[20],"solve":[21,47],"this":[22,117],"problem,":[23],"we":[24,58,85],"propose":[25],"USD-DPS,":[26],"Unsupervised":[27],"Speech":[28],"Dereverberation":[29],"via":[30],"Diffusion":[31],"Posterior":[32],"Sampling.":[33],"USD-DPS":[34],"uses":[35],"an":[36],"unconditional":[37],"speech":[39],"diffusion":[40,55,79],"model":[41],"as":[42],"a":[43,73,94,120],"strong":[44],"prior":[45,128],"by":[50,89],"posterior":[51],"sampling.":[52],"At":[53],"each":[54],"sampling":[56,124],"step,":[57],"estimate":[59,86,104],"all":[60],"microphone":[61],"channels\u2019":[62,106],"room":[63],"impulse":[64],"responses":[65],"(RIRs),":[66],"which":[67,130],"further":[69],"enforce":[72],"mixture":[75],"consistency":[76],"constraint":[77],"for":[78],"guidance.":[80],"For":[81],"RIR":[83,88,91,96,127],"estimation,":[84],"reference-channel":[87],"optimizing":[90],"parameters":[92],"sub-band":[95],"signal":[97],"model,":[98],"with":[99],"Adam":[101],"optimizer.":[102],"non-reference":[105],"RIRs":[107],"analytically":[108],"using":[109],"forward":[110],"convolutive":[111],"prediction":[112],"(FCP).":[113],"found":[115],"that":[116],"combination":[118],"provides":[119],"good":[121],"balance":[122],"between":[123],"efficiency":[125],"and":[126],"modeling,":[129],"shows":[131],"superior":[132],"performance":[133],"among":[134],"unsupervised":[135],"dereverberation":[136],"approaches.":[137],"An":[138],"audio":[139],"demo":[140],"page":[141],"is":[142],"provided":[143],"in":[144],"https://usddps.github.io/USDDPS_demo/.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}