{"id":"https://openalex.org/W2922004249","doi":"https://doi.org/10.23919/apsipa.2018.8659591","title":"Bayesian Multichannel Speech Enhancement with a Deep Speech Prior","display_name":"Bayesian Multichannel Speech Enhancement with a Deep Speech Prior","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2922004249","doi":"https://doi.org/10.23919/apsipa.2018.8659591","mag":"2922004249"},"language":"en","primary_location":{"id":"doi:10.23919/apsipa.2018.8659591","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659591","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5069659508","display_name":"Kouhei Sekiguchi","orcid":"https://orcid.org/0000-0001-6160-9301"},"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":true,"raw_author_name":"Kouhei Sekiguchi","raw_affiliation_strings":["Kyoto University"],"affiliations":[{"raw_affiliation_string":"Kyoto University","institution_ids":["https://openalex.org/I22299242"]}]},{"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), Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","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"],"affiliations":[{"raw_affiliation_string":"Kyoto University","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"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":"Tatsuya Kawahara","raw_affiliation_strings":["Kyoto University"],"affiliations":[{"raw_affiliation_string":"Kyoto University","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5069659508"],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":5.4497,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.96731419,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1233","last_page":"1239"},"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9980000257492065,"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":0.9969000220298767,"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":0.740319013595581},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7085543870925903},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6194251775741577},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5763675570487976},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.5137406587600708},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4922601282596588},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4592115879058838},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41331779956817627},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4113888740539551},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.28289854526519775},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.14735651016235352},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.09995925426483154}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.740319013595581},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7085543870925903},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6194251775741577},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5763675570487976},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.5137406587600708},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4922601282596588},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4592115879058838},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41331779956817627},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4113888740539551},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.28289854526519775},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.14735651016235352},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.09995925426483154},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/apsipa.2018.8659591","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659591","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1845880232","https://openalex.org/W1959608418","https://openalex.org/W2054221677","https://openalex.org/W2113990625","https://openalex.org/W2117332620","https://openalex.org/W2127851351","https://openalex.org/W2158291955","https://openalex.org/W2168273590","https://openalex.org/W2176035349","https://openalex.org/W2401820494","https://openalex.org/W2405774341","https://openalex.org/W2407685581","https://openalex.org/W2408744528","https://openalex.org/W2412956798","https://openalex.org/W2517616541","https://openalex.org/W2559809918","https://openalex.org/W2702006285","https://openalex.org/W2746904187","https://openalex.org/W2766672686","https://openalex.org/W2787211894","https://openalex.org/W2919011965","https://openalex.org/W2963969588","https://openalex.org/W6640963894","https://openalex.org/W6683202405","https://openalex.org/W6713658392"],"related_works":["https://openalex.org/W2551137307","https://openalex.org/W2098101267","https://openalex.org/W2113526703","https://openalex.org/W2123043102","https://openalex.org/W2577807713","https://openalex.org/W2897924318","https://openalex.org/W2138997758","https://openalex.org/W2919389044","https://openalex.org/W1997528538","https://openalex.org/W2777466939"],"abstract_inverted_index":{"This":[0,67],"paper":[1],"describes":[2],"statistical":[3],"multichannel":[4,76],"speech":[5,14,28,32,53,57,104,129,140,156,166,169,173,181],"enhancement":[6],"based":[7,115],"on":[8,91,116,188],"a":[9,39,44,70,112,124,132,162,201],"deep":[10,17,125],"generative":[11,126],"model":[12,127,135,141,187],"of":[13,47,51,97,119,123,164,179,211],"spectra.":[15,105,138],"Recently,":[16],"neural":[18],"networks":[19],"(DNNs)":[20],"have":[21],"widely":[22],"been":[23],"used":[24,160],"for":[25,69,103,128,136,168],"converting":[26],"noisy":[27,52,65,172],"spectra":[29,33,87,130,167,182],"to":[30],"clean":[31,56,155,165,180],"or":[34],"estimating":[35,184],"time-frequency":[36],"masks.":[37],"Such":[38,191],"supervised":[40],"approach,":[41],"however,":[42],"requires":[43],"sufficient":[45],"amount":[46],"training":[48],"data":[49,54,157],"(pairs":[50],"and":[55,59,88,131,158],"data)":[58],"often":[60],"fails":[61],"in":[62,145,200],"an":[63,117],"unseen":[64],"environment.":[66],"calls":[68],"blind":[71],"source":[72,86],"separation":[73],"method":[74,114],"called":[75],"nonnegative":[77],"matrix":[78],"factorization":[79],"(MNMF)":[80],"that":[81,121],"can":[82,142],"jointly":[83],"estimate":[84,176],"low-rank":[85,134],"spatial":[89],"covariances":[90],"the":[92,95,177,185,189,209,212],"fly.":[93,190],"However,":[94],"assumption":[96],"low-rankness":[98],"does":[99],"not":[100],"hold":[101],"true":[102],"To":[106],"solve":[107],"these":[108],"problems,":[109],"we":[110,175],"propose":[111],"semi-supervised":[113],"extension":[118],"MNMF":[120],"consists":[122],"standard":[133],"noise":[137,186],"The":[139,205],"be":[143],"trained":[144],"advance":[146],"with":[147],"auto-encoding":[148],"variational":[149],"Bayes":[150],"(AEVB)":[151],"by":[152,196],"using":[153,197],"only":[154],"is":[159,194],"as":[161],"prior":[163],"enhancement.":[170],"Given":[171],"spectrogram,":[174],"posterior":[178],"while":[183],"adaptive":[192],"estimation":[193],"achieved":[195],"Gibbs":[198],"sampling":[199],"unified":[202],"Bayesian":[203],"framework.":[204],"experimental":[206],"results":[207],"showed":[208],"potential":[210],"proposed":[213],"method.":[214]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":15}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}