{"id":"https://openalex.org/W4403126715","doi":"https://doi.org/10.1109/iwaenc61483.2024.10694664","title":"Multi-Stream Diffusion Model for Probabilistic Integration of Model-Based and Data-Driven Speech Enhancement","display_name":"Multi-Stream Diffusion Model for Probabilistic Integration of Model-Based and Data-Driven Speech Enhancement","publication_year":2024,"publication_date":"2024-09-09","ids":{"openalex":"https://openalex.org/W4403126715","doi":"https://doi.org/10.1109/iwaenc61483.2024.10694664"},"language":"en","primary_location":{"id":"doi:10.1109/iwaenc61483.2024.10694664","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc61483.2024.10694664","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)","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/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":"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":"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":"65","last_page":"69"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9930999875068665,"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":0.9930999875068665,"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":0.9161999821662903,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6973340511322021},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.649827778339386},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.6021696329116821},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5675981640815735},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.5627421140670776},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4541482627391815},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35621634125709534},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3155013620853424},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.13143426179885864},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.0777483582496643}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6973340511322021},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.649827778339386},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.6021696329116821},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5675981640815735},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.5627421140670776},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4541482627391815},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35621634125709534},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3155013620853424},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.13143426179885864},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0777483582496643},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwaenc61483.2024.10694664","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc61483.2024.10694664","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6600000262260437,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1983812858","https://openalex.org/W1991111872","https://openalex.org/W2017957151","https://openalex.org/W2042860487","https://openalex.org/W2046317813","https://openalex.org/W2242685705","https://openalex.org/W2289394825","https://openalex.org/W2563666542","https://openalex.org/W2568308529","https://openalex.org/W2810434345","https://openalex.org/W2900212944","https://openalex.org/W2962780374","https://openalex.org/W2962866211","https://openalex.org/W2964058413","https://openalex.org/W3171278394","https://openalex.org/W4281820413","https://openalex.org/W4380434618","https://openalex.org/W4384080510","https://openalex.org/W4385756463","https://openalex.org/W4385822449","https://openalex.org/W4385822703","https://openalex.org/W4401597527","https://openalex.org/W4401609190","https://openalex.org/W6786375611","https://openalex.org/W6890361730"],"related_works":["https://openalex.org/W2002739602","https://openalex.org/W1968042686","https://openalex.org/W2897881820","https://openalex.org/W2345647014","https://openalex.org/W2201192772","https://openalex.org/W3136891595","https://openalex.org/W2535030201","https://openalex.org/W1964819397","https://openalex.org/W2073891040","https://openalex.org/W1510133244"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,8,61,72,83,103,108,121],"novel":[4],"approach":[5,96],"that":[6,64,94],"leverages":[7],"diffusion":[9,62,104],"model":[10,63],"to":[11,39,141],"seamlessly":[12],"integrate":[13],"multiple":[14],"Speech":[15],"Enhancement":[16],"(SE)":[17],"methods,":[18],"resulting":[19],"in":[20,71],"high-quality":[21],"speech":[22,99,137],"estimates.":[23],"Traditionally,":[24],"researchers":[25],"have":[26],"combined":[27],"various":[28],"strategies,":[29],"including":[30],"model-based":[31,105],"signal":[32],"processing":[33],"and":[34,114],"data-driven":[35],"neural":[36],"networks":[37],"(NNs),":[38],"achieve":[40],"state-of-the-art":[41],"SE":[42,69,89,106,113],"performance.":[43],"However,":[44],"these":[45],"methods":[46,70],"often":[47],"relied":[48],"on":[49,143],"manually":[50],"designed":[51],"integration":[52,67],"schemes,":[53],"which":[54],"lacked":[55],"optimality.":[56],"In":[57],"contrast,":[58],"we":[59],"propose":[60],"optimizes":[65],"the":[66,127,134,144],"of":[68],"probabilistic":[73],"manner":[74],"using":[75],"training":[76],"data.":[77],"The":[78],"proposed":[79],"method":[80,125],"is":[81],"called":[82],"multi-stream":[84],"Score-based":[85],"Generative":[86],"Model":[87],"for":[88],"(mSGMSE).":[90],"We":[91],"experimentally":[92],"demonstrate":[93],"our":[95,124],"significantly":[97],"enhances":[98],"quality":[100],"by":[101,133],"integrating":[102],"with":[107],"Complex":[109],"Spectral":[110],"Mapping":[111],"(CSM)-based":[112],"Weighted":[115],"Prediction":[116],"Error":[117,129],"(WPE)":[118],"dereverberation.":[119],"Utilizing":[120],"two-microphone":[122],"setup,":[123],"reduces":[126],"Word":[128],"Rate":[130],"(WER)":[131],"obtained":[132],"ESPnet2":[135],"automatic":[136],"recognizer":[138],"from":[139],"6.14%":[140],"3.46%":[142],"REVERB":[145],"challenge":[146],"real":[147],"dataset.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}