{"id":"https://openalex.org/W4401597527","doi":"https://doi.org/10.1109/icasspw62465.2024.10627051","title":"Ensemble Inference for Diffusion Model-Based Speech Enhancement","display_name":"Ensemble Inference for Diffusion Model-Based Speech Enhancement","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4401597527","doi":"https://doi.org/10.1109/icasspw62465.2024.10627051"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10627051","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10627051","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/A5088361896","display_name":"Hao Shi","orcid":"https://orcid.org/0000-0003-3373-2147"},"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":"Hao Shi","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":"Marc Delcroix","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":"last","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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"735","last_page":"739"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9656999707221985,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9194999933242798,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7011620402336121},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7004215717315674},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5622854232788086},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4942150413990021},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4463898539543152},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.437676340341568},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.10168498754501343},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09895974397659302}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7011620402336121},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7004215717315674},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5622854232788086},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4942150413990021},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4463898539543152},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.437676340341568},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.10168498754501343},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09895974397659302},{"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/icasspw62465.2024.10627051","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10627051","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1991111872","https://openalex.org/W1992475611","https://openalex.org/W2044893557","https://openalex.org/W2051057783","https://openalex.org/W2096779346","https://openalex.org/W2289394825","https://openalex.org/W2883322837","https://openalex.org/W2952218014","https://openalex.org/W2963341071","https://openalex.org/W2971417062","https://openalex.org/W3015912787","https://openalex.org/W3027008958","https://openalex.org/W3099330747","https://openalex.org/W3197912330","https://openalex.org/W3213188934","https://openalex.org/W4221144097","https://openalex.org/W4375869120","https://openalex.org/W4380434618","https://openalex.org/W4385822449","https://openalex.org/W6765775151","https://openalex.org/W6777776875","https://openalex.org/W6786375611","https://openalex.org/W6796411514","https://openalex.org/W6797906067","https://openalex.org/W6890361730"],"related_works":["https://openalex.org/W2055243143","https://openalex.org/W1630865680","https://openalex.org/W4321636575","https://openalex.org/W1986418932","https://openalex.org/W2357796999","https://openalex.org/W2373767407","https://openalex.org/W2045526782","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2275432853"],"abstract_inverted_index":{"Diffusion-based":[0],"speech":[1,64],"enhancement":[2],"(SE)":[3],"is":[4],"a":[5,27,102,161],"probabilistic":[6],"model":[7],"that":[8,25],"provides":[9],"distribution":[10],"of":[11,152,164],"enhanced":[12],"speech.":[13],"Based":[14],"on":[15,62,69],"this":[16],"property,":[17],"we":[18,48,58],"previously":[19],"proposed":[20,54,169],"ensemble":[21,38,55,111,154,174],"inference":[22,112,142,155],"and":[23,35,67,100,110,128,133,136,166],"showed":[24],"solving":[26],"reverse":[28],"Stochastic":[29],"Differential":[30],"Equation":[31],"(SDE)":[32],"multiple":[33],"times":[34],"performing":[36],"an":[37],"over":[39],"the":[40,45,81,85,119,126,138,150,153,173],"obtained":[41],"samples":[42,89],"significantly":[43],"improves":[44,172],"performance.":[46],"Unfortunately,":[47],"failed":[49],"to":[50,117],"sufficiently":[51],"explore":[52],"our":[53],"inference.":[56],"First,":[57],"only":[59],"tested":[60],"it":[61],"target":[63],"extraction":[65],"(TSE)":[66],"not":[68],"such":[70],"general":[71],"SE":[72],"tasks":[73,135],"as":[74],"denoising.":[75],"Second,":[76],"sample":[77,105],"generation":[78,106],"greatly":[79],"increased":[80],"computational":[82],"complexity.":[83],"Finally,":[84],"method":[86],"considered":[87],"all":[88],"equally":[90],"without":[91],"heeding":[92],"potential":[93],"outliers.":[94],"This":[95],"paper":[96],"addresses":[97],"these":[98],"issues":[99],"proposes":[101],"computationally":[103],"efficient":[104],"technique":[107],"called":[108],"SplitTree":[109,148],"combined":[113],"with":[114],"outlier":[115,170],"removal":[116,171],"improve":[118],"ensemble\u2019s":[120],"effectiveness.":[121],"We":[122],"conducted":[123],"experiments":[124],"using":[125],"WSJ-CHiME3":[127],"LibriMix2spk":[129],"datasets":[130],"for":[131,176],"denoising":[132,145],"TSE":[134,177],"confirmed":[137],"following:":[139],"1)":[140],"Ensemble":[141],"also":[143],"helps":[144],"tasks;":[146],"2)":[147],"reduces":[149],"complexity":[151],"by":[156],"about":[157],"40%":[158],"while":[159],"maintaining":[160],"similar":[162],"level":[163],"performance;":[165],"3)":[167],"Our":[168],"performance":[175],"task.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}