{"id":"https://openalex.org/W4288043185","doi":"https://doi.org/10.1109/iwaenc53105.2022.9914729","title":"DNN-free Low-Latency Adaptive Speech Enhancement Based on Frame-Online Beamforming Powered by Block-Online FastMNMF","display_name":"DNN-free Low-Latency Adaptive Speech Enhancement Based on Frame-Online Beamforming Powered by Block-Online FastMNMF","publication_year":2022,"publication_date":"2022-09-05","ids":{"openalex":"https://openalex.org/W4288043185","doi":"https://doi.org/10.1109/iwaenc53105.2022.9914729"},"language":"en","primary_location":{"id":"doi:10.1109/iwaenc53105.2022.9914729","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc53105.2022.9914729","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Workshop on Acoustic Signal Enhancement (IWAENC)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2207.10934","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":["Center for Advanced Intelligence Project (AIP),RIKEN,Japan","RIKEN, Center for Advanced Intelligence Project (AIP), Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Advanced Intelligence Project (AIP),RIKEN,Japan","institution_ids":["https://openalex.org/I4210126580"]},{"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/A5069659508","display_name":"Kouhei Sekiguchi","orcid":"https://orcid.org/0000-0001-6160-9301"},"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":"Kouhei Sekiguchi","raw_affiliation_strings":["Center for Advanced Intelligence Project (AIP),RIKEN,Japan","RIKEN, Center for Advanced Intelligence Project (AIP), Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Advanced Intelligence Project (AIP),RIKEN,Japan","institution_ids":["https://openalex.org/I4210126580"]},{"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/A5082784886","display_name":"Mathieu Fontaine","orcid":"https://orcid.org/0000-0002-7657-6271"},"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"]},{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]},{"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","JP"],"is_corresponding":false,"raw_author_name":"Mathieu Fontaine","raw_affiliation_strings":["Institut Polytechnique de Paris,LTCI, Télécom Paris,France","RIKEN, Center for Advanced Intelligence Project (AIP), Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,LTCI, Télécom Paris,France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I4210145102"]},{"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/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"]},{"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),Japan","RIKEN, Center for Advanced Intelligence Project (AIP), Japan","National Institute of Advanced Industrial Science and Technology (AIST), Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST),Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"RIKEN, Center for Advanced Intelligence Project (AIP), Japan","institution_ids":["https://openalex.org/I4210126580"]},{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"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"]},{"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"]},{"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":"Kazuyoshi Yoshii","raw_affiliation_strings":["Kyoto University,Graduate School of Informatics,Japan","RIKEN, Center for Advanced Intelligence Project (AIP), Japan","Graduate School of Informatics, Kyoto University, 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"]},{"raw_affiliation_string":"RIKEN, Center for Advanced Intelligence Project (AIP), Japan","institution_ids":["https://openalex.org/I4210126580"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08014797,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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":1.0,"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":1.0,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9991000294685364,"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"}},{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.9972000122070312,"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/computer-science","display_name":"Computer science","score":0.7719336748123169},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.6558616161346436},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5315636992454529},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5263962745666504},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.525160014629364},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.4922102987766266},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.48309922218322754},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4448775351047516},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.44424736499786377},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4373360276222229},{"id":"https://openalex.org/keywords/covariance-matrix","display_name":"Covariance matrix","score":0.43166327476501465},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3910784125328064},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.3367171287536621},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3316342830657959},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1268412470817566},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12082847952842712},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11953821778297424},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07772472500801086}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7719336748123169},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.6558616161346436},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5315636992454529},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5263962745666504},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.525160014629364},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.4922102987766266},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.48309922218322754},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4448775351047516},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.44424736499786377},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4373360276222229},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.43166327476501465},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3910784125328064},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.3367171287536621},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3316342830657959},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1268412470817566},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12082847952842712},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11953821778297424},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07772472500801086},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iwaenc53105.2022.9914729","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc53105.2022.9914729","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Workshop on Acoustic Signal Enhancement (IWAENC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2207.10934","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2207.10934","pdf_url":"https://arxiv.org/pdf/2207.10934","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":"","raw_type":"text"},{"id":"pmh:oai:HAL:hal-03821095v1","is_oa":false,"landing_page_url":"https://telecom-paris.hal.science/hal-03821095","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"17th International Workshop on Acoustic Signal Enhancement (IWAENC 2022), 2022, Bamberg, Germany","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2207.10934","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2207.10934","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2207.10934","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2207.10934","pdf_url":"https://arxiv.org/pdf/2207.10934","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":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W182831726","https://openalex.org/W1494198834","https://openalex.org/W1932968309","https://openalex.org/W1982728343","https://openalex.org/W1983812858","https://openalex.org/W2113990625","https://openalex.org/W2143027228","https://openalex.org/W2168729028","https://openalex.org/W2559260703","https://openalex.org/W2586584460","https://openalex.org/W2591810467","https://openalex.org/W2748661748","https://openalex.org/W2783358616","https://openalex.org/W2900212944","https://openalex.org/W2918296821","https://openalex.org/W2923728956","https://openalex.org/W2937284863","https://openalex.org/W2963197115","https://openalex.org/W3015509183","https://openalex.org/W3081267827","https://openalex.org/W3158652463","https://openalex.org/W3167533889","https://openalex.org/W4200629932","https://openalex.org/W4225323908","https://openalex.org/W4285787282"],"related_works":["https://openalex.org/W2037504162","https://openalex.org/W2774154397","https://openalex.org/W2146544734","https://openalex.org/W2921513691","https://openalex.org/W2156699640","https://openalex.org/W2098101267","https://openalex.org/W1979654135","https://openalex.org/W2156181515","https://openalex.org/W1984255382","https://openalex.org/W2576645943"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,34,81,107],"practical":[4],"dual-process":[5],"speech":[6],"enhancement":[7],"system":[8,118,147,164],"that":[9,39,144],"adapts":[10],"environment-sensitive":[11],"frame-online":[12,108,139,146],"beamforming":[13,167],"(front-end)":[14],"with":[15,64,80,165],"help":[16],"from":[17],"environment-free":[18],"block-online":[19,129,163],"source":[20,77,84,125,135],"separation":[21,85],"(back-end).":[22],"To":[23],"use":[24],"minimum":[25],"variance":[26],"distortionless":[27],"response":[28],"(MVDR)":[29],"beamforming,":[30],"one":[31,70],"may":[32,71],"train":[33],"deep":[35],"neural":[36],"network":[37],"(DNN)":[38],"estimates":[40],"time-frequency":[41],"masks":[42],"used":[43],"for":[44,62,138],"computing":[45],"the":[46,58,65,76,98,101,120,123,133,174],"covariance":[47,78,136],"matrices":[48,79,137],"of":[49,57,122,173],"sources":[50],"(speech":[51],"and":[52,159],"noise).":[53],"Backpropagation-based":[54],"run-time":[55],"adaptation":[56],"DNN":[59,99],"was":[60],"proposed":[61],"dealing":[63],"mismatched":[66],"training-test":[67],"conditions.":[68],"Instead,":[69],"try":[72],"to":[73,111,131,151],"directly":[74],"estimate":[75],"state-of-the-art":[82],"blind":[83],"method":[86],"called":[87],"fast":[88],"multichannel":[89],"non-negative":[90],"matrix":[91],"factorization":[92],"(FastMNMF).":[93],"In":[94],"practice,":[95],"however,":[96],"neither":[97],"nor":[100],"FastMNMF":[102,130],"can":[103,148],"be":[104],"updated":[105],"in":[106,171],"manner":[109],"due":[110],"its":[112],"computationally-expensive":[113],"iterative":[114],"nature.":[115],"Our":[116],"DNN-free":[117],"leverages":[119],"posteriors":[121],"latest":[124],"spectrograms":[126],"given":[127],"by":[128,155,168],"derive":[132],"current":[134],"beamforming.":[140],"The":[141],"evaluation":[142],"shows":[143],"our":[145],"quickly":[149],"respond":[150],"scene":[152],"changes":[153],"caused":[154],"interfering":[156],"speaker":[157],"movements":[158],"outperformed":[160],"an":[161],"existing":[162],"DNN-based":[166],"5.0":[169],"points":[170],"terms":[172],"word":[175],"error":[176],"rate.":[177]},"counts_by_year":[],"updated_date":"2026-07-13T07:31:44.756512","created_date":"2022-07-27T00:00:00"}