{"id":"https://openalex.org/W4225306949","doi":"https://doi.org/10.1109/icassp43922.2022.9746904","title":"Importance of Switch Optimization Criterion in Switching WPE Dereverberation","display_name":"Importance of Switch Optimization Criterion in Switching WPE Dereverberation","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225306949","doi":"https://doi.org/10.1109/icassp43922.2022.9746904"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746904","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746904","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084590882","display_name":"Rintaro Ikeshita","orcid":"https://orcid.org/0000-0003-2608-1999"},"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":"Rintaro Ikeshita","raw_affiliation_strings":["NTT Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069398831","display_name":"Keisuke Kinoshita","orcid":"https://orcid.org/0009-0008-7987-8188"},"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":"Keisuke Kinoshita","raw_affiliation_strings":["NTT Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation","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":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":null,"first_page":"176","last_page":"180"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"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/maximization","display_name":"Maximization","score":0.6925205588340759},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6195155382156372},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.4747063219547272},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4633868634700775},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45631441473960876},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4509470462799072},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.43495437502861023},{"id":"https://openalex.org/keywords/linear-prediction","display_name":"Linear prediction","score":0.43166983127593994},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.43123936653137207},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.42992573976516724},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42842137813568115},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.32552874088287354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31099534034729004},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.17067331075668335},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.16570618748664856},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11377528309822083}],"concepts":[{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.6925205588340759},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6195155382156372},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.4747063219547272},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4633868634700775},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45631441473960876},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4509470462799072},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.43495437502861023},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.43166983127593994},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.43123936653137207},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.42992573976516724},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42842137813568115},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32552874088287354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31099534034729004},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.17067331075668335},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.16570618748664856},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11377528309822083},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746904","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746904","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W1983812858","https://openalex.org/W2018735295","https://openalex.org/W2080145918","https://openalex.org/W2096819401","https://openalex.org/W2103034511","https://openalex.org/W2107992675","https://openalex.org/W2111512576","https://openalex.org/W2119923861","https://openalex.org/W2127851351","https://openalex.org/W2164502538","https://openalex.org/W2242685705","https://openalex.org/W2486913545","https://openalex.org/W2559260703","https://openalex.org/W2559809918","https://openalex.org/W2622203030","https://openalex.org/W2884797218","https://openalex.org/W2916985722","https://openalex.org/W2930641205","https://openalex.org/W2954695182","https://openalex.org/W2962780374","https://openalex.org/W2963045393","https://openalex.org/W2982471419","https://openalex.org/W3020336359","https://openalex.org/W3128534387","https://openalex.org/W3185812430","https://openalex.org/W4296927107","https://openalex.org/W4385245566","https://openalex.org/W6735168207","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2362031592","https://openalex.org/W2022349254","https://openalex.org/W2996353927","https://openalex.org/W2073854657","https://openalex.org/W2035224173","https://openalex.org/W3082502994","https://openalex.org/W4293771590","https://openalex.org/W2189593149","https://openalex.org/W1969107787"],"abstract_inverted_index":{"Weighted":[0],"prediction":[1,22],"error":[2,82],"(WPE)":[3],"is":[4,67,167],"a":[5,92,161],"fundamental":[6],"dereverberation":[7],"method":[8],"to":[9,28,42,100,147,189],"predict":[10],"the":[11,44,60,116,134,140,154,180,185,190],"late":[12],"reverberation":[13],"component":[14],"of":[15,72,85,119,184],"an":[16,106,124,170],"observed":[17],"signal":[18,73],"based":[19,58,104],"on":[20,59,105],"linear":[21],"(LP).":[23],"Recently,":[24],"WPE":[25,30,192],"was":[26],"extended":[27],"Switching":[29],"(SwWPE),":[31],"which":[32,153],"optimizes":[33],"(i)":[34],"multiple":[35],"LP":[36,46],"filters":[37],"and":[38,80,136,193],"(ii)":[39],"switching":[40,102,155],"parameters":[41,55,103,156],"determine":[43],"best":[45],"filter":[47],"used":[48],"for":[49],"each":[50],"time-frequency":[51],"bin.":[52],"Conventionally,":[53],"these":[54],"are":[56,157],"optimized":[57],"maximum":[61],"likelihood":[62],"(ML)":[63],"criterion,":[64,127],"but":[65],"this":[66],"not":[68],"optimal":[69],"in":[70,152],"terms":[71],"quality,":[74],"such":[75],"as":[76],"signal-to-distortion":[77],"ratio":[78],"(SDR)":[79],"word":[81],"rate":[83],"(WER)":[84],"automatic":[86],"speech":[87],"recognition.":[88],"We":[89],"thus":[90],"propose":[91,148],"new":[93,121,149,186],"SwWPE":[94,150],"processing":[95,151],"flow":[96],"that":[97,129,166],"enables":[98],"us":[99,146],"optimize":[101],"arbitrary":[107],"optimization":[108],"criterion.":[109,174],"Using":[110],"oracle":[111],"clean":[112],"signals,":[113],"we":[114],"demonstrate":[115],"potential":[117],"performance":[118,183],"our":[120],"approach":[122,187],"with":[123,169],"SDR":[125,135,172,182],"maximization":[126,173],"revealing":[128],"it":[130],"can":[131],"significantly":[132],"improve":[133],"WER":[137],"obtained":[138],"by":[139],"conventional":[141,191],"ML-based":[142],"SwWPE.":[143,194],"This":[144],"motivates":[145],"externally":[158],"estimated":[159],"using":[160],"deep":[162],"neural":[163],"network":[164],"(DNN)":[165],"trained":[168],"end-to-end":[171],"The":[175],"experimental":[176],"result":[177],"clearly":[178],"demonstrates":[179],"improved":[181],"compared":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}