{"id":"https://openalex.org/W4406858854","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849318","title":"Run-Time Adaptation of Neural Beamforming for Robust Speech Dereverberation and Denoising","display_name":"Run-Time Adaptation of Neural Beamforming for Robust Speech Dereverberation and Denoising","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406858854","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849318"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10849318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5089632772","display_name":"Yoto Fujita","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoto Fujita","raw_affiliation_strings":["Kyoto University,Graduate School of Informatics,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University,Graduate School of Informatics,Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082272880","display_name":"Aditya Arie Nugraha","orcid":"https://orcid.org/0000-0001-5424-747X"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Aditya Arie Nugraha","raw_affiliation_strings":["RIKEN,Center for Advanced Intelligence Project (AIP),Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RIKEN,Center for Advanced Intelligence Project (AIP),Japan","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023307571","display_name":"Diego Di Carlo","orcid":"https://orcid.org/0000-0002-4090-2872"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Diego Di Carlo","raw_affiliation_strings":["RIKEN,Center for Advanced Intelligence Project (AIP),Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RIKEN,Center for Advanced Intelligence Project (AIP),Japan","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007353694","display_name":"Yoshiaki Bando","orcid":"https://orcid.org/0000-0002-3934-0745"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshiaki Bando","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST),AIRC,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST),AIRC,Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082784886","display_name":"Mathieu Fontaine","orcid":"https://orcid.org/0000-0002-7657-6271"},"institutions":[{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mathieu Fontaine","raw_affiliation_strings":["Télécom Paris,LTCI,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Télécom Paris,LTCI,France","institution_ids":["https://openalex.org/I4210165912"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067956319","display_name":"Kazuyoshi Yoshii","orcid":"https://orcid.org/0000-0001-8387-8609"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuyoshi Yoshii","raw_affiliation_strings":["Kyoto University,Graduate School of Engineering,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University,Graduate School of Engineering,Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2827,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55663771,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9980999827384949,"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":0.9980999827384949,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9854000210762024,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9779999852180481,"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/beamforming","display_name":"Beamforming","score":0.7483070492744446},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7202633619308472},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7039008140563965},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5515937805175781},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5324970483779907},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.49671584367752075},{"id":"https://openalex.org/keywords/adaptive-beamformer","display_name":"Adaptive beamformer","score":0.4128512144088745},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2972806692123413},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10679459571838379},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06218096613883972}],"concepts":[{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.7483070492744446},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7202633619308472},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7039008140563965},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5515937805175781},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5324970483779907},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.49671584367752075},{"id":"https://openalex.org/C33378366","wikidata":"https://www.wikidata.org/wiki/Q4680719","display_name":"Adaptive beamformer","level":3,"score":0.4128512144088745},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2972806692123413},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10679459571838379},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06218096613883972},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc63619.2025.10849318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G28753467","display_name":"User-controllable and Physics-informed Neural Acoustics Fields for Multichannel Audio Rendering and Analysis in Mixed Reality Application","funder_award_id":"23K16913","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3510745091","display_name":"Speaker diarization with a unified robust multimodal and spatial audio model","funder_award_id":"ANR-22-CE23-0011","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1983812858","https://openalex.org/W2113638573","https://openalex.org/W2113990625","https://openalex.org/W2164502538","https://openalex.org/W2168273590","https://openalex.org/W2412956798","https://openalex.org/W2591810467","https://openalex.org/W2763188033","https://openalex.org/W2889224938","https://openalex.org/W2905402910","https://openalex.org/W2909607850","https://openalex.org/W2918296821","https://openalex.org/W2937284863","https://openalex.org/W2962866211","https://openalex.org/W2963341071","https://openalex.org/W2964058413","https://openalex.org/W2972728246","https://openalex.org/W3015661721","https://openalex.org/W3015756037","https://openalex.org/W3081267827","https://openalex.org/W3096073522","https://openalex.org/W3167533889","https://openalex.org/W4221144097","https://openalex.org/W4232282348","https://openalex.org/W4285787282","https://openalex.org/W4372260337","https://openalex.org/W4387870693"],"related_works":["https://openalex.org/W818226659","https://openalex.org/W2996333928","https://openalex.org/W2009075871","https://openalex.org/W2132841313","https://openalex.org/W2518591292","https://openalex.org/W1976800395","https://openalex.org/W2105408150","https://openalex.org/W2606661315","https://openalex.org/W2548445082","https://openalex.org/W2767070583"],"abstract_inverted_index":{"This":[0,76],"paper":[1],"describes":[2],"speech":[3,8,40,87],"enhancement":[4,57],"for":[5,60,78,90,119],"real-time":[6],"automatic":[7],"recognition":[9],"(ASR)":[10],"in":[11,29],"real":[12],"environments.":[13],"A":[14],"standard":[15],"approach":[16],"to":[17,21,173],"this":[18,129],"task":[19],"is":[20,70,92,199],"use":[22,174],"neural":[23,50,162],"beamforming":[24,150,163],"that":[25],"can":[26,116],"work":[27,133],"efficiently":[28],"an":[30],"online":[31],"manner.":[32],"It":[33],"estimates":[34],"the":[35,82,85,158,206],"masks":[36],"of":[37,64,81,142,185,208,217],"clean":[38],"dry":[39],"from":[41,124],"a":[42,48,56,66,125,131,135,140,182,202],"noisy":[43],"echoic":[44],"mixture":[45],"spectrogram":[46,88],"with":[47,214],"deep":[49],"network":[51],"(DNN)":[52],"and":[53,100,109,144,164,187,196,221],"then":[54],"computes":[55],"filter":[58,198],"used":[59,118],"beamforming.":[61],"The":[62],"performance":[63],"such":[65,103],"supervised":[67],"approach,":[68],"however,":[69],"drastically":[71],"degraded":[72],"under":[73,211],"mismatched":[74],"conditions.":[75],"calls":[77],"run-time":[79,209],"adaptation":[80,91,210],"DNN.":[83,203],"Although":[84],"ground-truth":[86,122],"required":[89],"not":[93],"available":[94],"at":[95,168],"run":[96,169],"time,":[97,170],"blind":[98],"dereverberation":[99,159,195],"separation":[101],"methods":[102],"as":[104],"weighted":[105,175],"prediction":[106],"error":[107],"(WPE)":[108],"fast":[110],"multichannel":[111],"nonnegative":[112],"matrix":[113],"factorization":[114],"(FastMNMF)":[115],"be":[117],"generating":[120],"pseudo":[121],"data":[123],"mixture.":[126],"Based":[127],"on":[128,139],"idea,":[130],"prior":[132],"proposed":[134],"dual-process":[136],"system":[137],"based":[138],"cascade":[141],"WPE":[143,186],"minimum":[145,188],"variance":[146],"distortionless":[147,178,190],"response":[148,179,191],"(MVDR)":[149],"asynchronously":[151],"fine-tuned":[152],"by":[153],"block-online":[154],"FastMNMF.":[155],"To":[156],"integrate":[157],"capability":[160],"into":[161],"make":[165],"it":[166],"fine-tunable":[167],"we":[171],"propose":[172],"power":[176,189],"minimization":[177],"(WPD)":[180],"beamforming,":[181],"unified":[183],"version":[184],"(MPDR),":[192],"whose":[193],"joint":[194],"denoising":[197],"estimated":[200],"using":[201],"We":[204],"evaluated":[205],"impact":[207],"various":[212],"conditions":[213],"different":[215],"numbers":[216],"speakers,":[218],"reverberation":[219],"times,":[220],"signal-to-noise":[222],"ratios":[223],"(SNRs).":[224]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-09T07:52:08.696243","created_date":"2025-10-10T00:00:00"}