{"id":"https://openalex.org/W4401609190","doi":"https://doi.org/10.1109/icasspw62465.2024.10626291","title":"Diffusion Model-Based MIMO Speech Denoising and Dereverberation","display_name":"Diffusion Model-Based MIMO Speech Denoising and Dereverberation","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4401609190","doi":"https://doi.org/10.1109/icasspw62465.2024.10626291"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10626291","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10626291","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/A5113336007","display_name":"R. Kimura","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Rino Kimura","raw_affiliation_strings":["NTT Corporation,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Corporation,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034382743","display_name":"Naoyuki Kamo","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoyuki Kamo","raw_affiliation_strings":["NTT Corporation,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Delcroix Marc","raw_affiliation_strings":["NTT Corporation,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009309584","display_name":"Shoko Araki","orcid":"https://orcid.org/0000-0003-4363-4305"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoko Araki","raw_affiliation_strings":["NTT Corporation,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103194936","display_name":"T. Ueda","orcid":"https://orcid.org/0009-0007-0158-6356"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuya Ueda","raw_affiliation_strings":["Waseda University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075702573","display_name":"Shoji Makino","orcid":"https://orcid.org/0000-0003-1934-640X"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoji Makino","raw_affiliation_strings":["Waseda University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"455","last_page":"459"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9884999990463257,"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":0.9884999990463257,"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":0.972000002861023,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9621000289916992,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.6480703353881836},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5521025061607361},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5498077273368835},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4910309314727783},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4586808979511261},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2638949751853943},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08525514602661133}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6480703353881836},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5521025061607361},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5498077273368835},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4910309314727783},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4586808979511261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2638949751853943},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08525514602661133},{"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:10.1109/icasspw62465.2024.10626291","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10626291","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1901129140","https://openalex.org/W1919482273","https://openalex.org/W1983812858","https://openalex.org/W1991111872","https://openalex.org/W2017957151","https://openalex.org/W2046317813","https://openalex.org/W2127851351","https://openalex.org/W2159788726","https://openalex.org/W2242685705","https://openalex.org/W2289394825","https://openalex.org/W2810434345","https://openalex.org/W2935873029","https://openalex.org/W2964058413","https://openalex.org/W3015279216","https://openalex.org/W3036167779","https://openalex.org/W3158974159","https://openalex.org/W4211127940","https://openalex.org/W4221144097","https://openalex.org/W4281820413","https://openalex.org/W4286850199","https://openalex.org/W4297841790","https://openalex.org/W4380434618","https://openalex.org/W4385822449","https://openalex.org/W6610861953","https://openalex.org/W6631362777","https://openalex.org/W6779823529","https://openalex.org/W6786375611","https://openalex.org/W6804811285","https://openalex.org/W6890361730"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2275432853"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3],"extension":[4],"of":[5,68,131],"a":[6,25,35,59,80],"diffusion":[7,81,92],"model-based":[8],"single":[9],"microphone":[10,61,127],"Speech":[11],"Enhancement":[12],"(SE)":[13],"method,":[14],"known":[15],"as":[16],"the":[17,65,73,90,143,151,164],"Score-Based":[18],"Generative":[19],"Model":[20],"for":[21,76,111],"SE":[22,114],"(SGMSE),":[23],"to":[24,43,98,105,125,150],"Multi-Input":[26],"Multi-Output":[27],"(MIMO)":[28],"SE.":[29],"The":[30],"extended":[31],"method":[32],"is":[33,42],"called":[34],"multi-stream":[36],"SGMSE":[37,121],"(mSGMSE).":[38],"MIMO":[39,113],"SE\u2019s":[40],"goal":[41],"estimate":[44],"multi-microphone":[45,77],"clean":[46,69,85],"speech":[47,55,70,86,145],"signals":[48,56,71,75,78],"with":[49],"spatial":[50,134],"cues":[51],"from":[52,163],"noisy,":[53],"reverberant":[54],"captured":[57,74],"by":[58,88],"distant":[60],"array.":[62],"mSGMSE":[63,100,119,139,180],"models":[64],"conditional":[66],"distribution":[67],"given":[72],"using":[79,89],"model":[82],"and":[83,103,136],"generates":[84],"estimates":[87],"reverse":[91],"process.":[93],"We":[94],"also":[95,140],"propose":[96],"techniques":[97],"make":[99],"computationally":[101],"efficient":[102],"adaptable":[104],"various":[106],"or":[107],"unknown":[108],"array":[109,161],"geometries":[110,162],"general":[112],"scenarios.":[115],"Experiments":[116],"show":[117],"that":[118,170],"outperforms":[120],"(when":[122],"separately":[123],"applied":[124,149],"each":[126],"signal)":[128],"in":[129],"terms":[130],"signal":[132],"quality,":[133],"cues,":[135],"computation":[137],"times.":[138],"significantly":[141],"improves":[142],"automatic":[144],"recognition":[146],"performance":[147],"when":[148],"REVERB":[152],"challenge":[153],"real":[154],"dataset,":[155],"which":[156],"has":[157],"substantial":[158],"mismatches":[159],"including":[160],"training":[165],"dataset.":[166],"Finally,":[167],"we":[168],"confirm":[169],"Weighted":[171],"Prediction":[172],"Error":[173],"dereverberation":[174],"(WPE)":[175],"preprocessing":[176],"can":[177],"further":[178],"enhance":[179],"more":[181],"than":[182],"SGMSE.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}