{"id":"https://openalex.org/W2766672686","doi":"https://doi.org/10.1109/icassp.2018.8461530","title":"Statistical Speech Enhancement Based on Probabilistic Integration of Variational Autoencoder and Non-Negative Matrix Factorization","display_name":"Statistical Speech Enhancement Based on Probabilistic Integration of Variational Autoencoder and Non-Negative Matrix Factorization","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2766672686","doi":"https://doi.org/10.1109/icassp.2018.8461530","mag":"2766672686"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461530","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461530","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1710.11439","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007353694","display_name":"Yoshiaki Bando","orcid":"https://orcid.org/0000-0002-3934-0745"},"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":"Yoshiaki Bando","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102851028","display_name":"Masato Mimura","orcid":"https://orcid.org/0000-0002-2403-0680"},"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":"Masato Mimura","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003325000","display_name":"Katsutoshi Itoyama","orcid":"https://orcid.org/0000-0002-7098-3896"},"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":"Katsutoshi Itoyama","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"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"]},{"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":"Kazuyoshi Yoshii","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","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"]},{"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":"Tatsuya Kawahara","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":136,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"716","last_page":"720"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9965000152587891,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9952999949455261,"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/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.7927675843238831},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.738307535648346},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7144526243209839},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7131494283676147},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6825528144836426},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6277212500572205},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5140300989151001},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47769811749458313},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.47251543402671814},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.44917556643486023},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.43961507081985474},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43357953429222107},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.42978015542030334},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41009122133255005},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19534751772880554},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.15066829323768616},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.14288166165351868},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09374621510505676},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07239329814910889}],"concepts":[{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.7927675843238831},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.738307535648346},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7144526243209839},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7131494283676147},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6825528144836426},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6277212500572205},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5140300989151001},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47769811749458313},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.47251543402671814},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.44917556643486023},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.43961507081985474},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43357953429222107},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.42978015542030334},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41009122133255005},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19534751772880554},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.15066829323768616},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.14288166165351868},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09374621510505676},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07239329814910889},{"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},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2018.8461530","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461530","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1710.11439","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1710.11439","pdf_url":"https://arxiv.org/pdf/1710.11439","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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1710.11439","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1710.11439","pdf_url":"https://arxiv.org/pdf/1710.11439","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":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","score":0.4399999976158142,"display_name":"No poverty"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W592244745","https://openalex.org/W1495679096","https://openalex.org/W1504438288","https://openalex.org/W1522301498","https://openalex.org/W1663973292","https://openalex.org/W1933340426","https://openalex.org/W1959608418","https://openalex.org/W2009086942","https://openalex.org/W2031696998","https://openalex.org/W2039844283","https://openalex.org/W2053165762","https://openalex.org/W2077799289","https://openalex.org/W2096698681","https://openalex.org/W2113990625","https://openalex.org/W2121973264","https://openalex.org/W2127851351","https://openalex.org/W2141411743","https://openalex.org/W2164098335","https://openalex.org/W2167873188","https://openalex.org/W2289394825","https://openalex.org/W2398042854","https://openalex.org/W2401089611","https://openalex.org/W2405774341","https://openalex.org/W2408744528","https://openalex.org/W2515020857","https://openalex.org/W2587141595","https://openalex.org/W2605762339","https://openalex.org/W2698117193","https://openalex.org/W2747161606","https://openalex.org/W2919011965","https://openalex.org/W2962850167","https://openalex.org/W2963341071","https://openalex.org/W2964121744","https://openalex.org/W3147539069","https://openalex.org/W4253928870","https://openalex.org/W4320013936","https://openalex.org/W6617744952","https://openalex.org/W6664102729","https://openalex.org/W6680858114","https://openalex.org/W6683782126","https://openalex.org/W6696392866","https://openalex.org/W6712876440","https://openalex.org/W6713658392","https://openalex.org/W6733498539","https://openalex.org/W6740374833"],"related_works":["https://openalex.org/W2551137307","https://openalex.org/W2113526703","https://openalex.org/W2396837968","https://openalex.org/W2127243424","https://openalex.org/W4390394189","https://openalex.org/W2037504162","https://openalex.org/W2123043102","https://openalex.org/W2098101267","https://openalex.org/W2577807713","https://openalex.org/W2900450731"],"abstract_inverted_index":{"This":[0,95],"paper":[1],"presents":[2],"a":[3,12,17,32,52,133,145],"statistical":[4],"method":[5,170,175],"of":[6,56,117,127,150],"single-channel":[7],"speech":[8,27,40,84,105,112,129,155,163],"enhancement":[9,28],"that":[10,111],"uses":[11],"variational":[13],"autoencoder":[14],"(VAE)":[15],"as":[16,41,156],"prior":[18],"distribution":[19],"on":[20,78,82,92,140],"clean":[21,45,83,128,141,162],"speech.":[22,46,152],"A":[23],"standard":[24],"approach":[25,50,69],"to":[26,30,37,71,90,107],"is":[29,62,70],"train":[31],"deep":[33,137],"neural":[34],"network":[35],"(DNN)":[36],"take":[38],"noisy":[39,151,154,178],"input":[42],"and":[43,87],"output":[44],"Although":[47],"this":[48],"supervised":[49],"requires":[51],"very":[53],"large":[54],"amount":[55],"pair":[57],"data":[58],"for":[59],"training,":[60],"it":[61],"not":[63],"robust":[64],"against":[65],"unknown":[66],"environments.":[67,179],"Another":[68],"use":[72],"non-negative":[73],"matrix":[74],"factorization":[75],"(NMF)":[76],"based":[77],"basis":[79,119],"spectra":[80],"trained":[81],"in":[85,103,130,176],"advance":[86],"those":[88],"adapted":[89],"noise":[91],"the":[93,108,118,122,172],"fly.":[94],"semi-supervised":[96],"approach,":[97],"however,":[98],"causes":[99],"considerable":[100],"signal":[101],"distortion":[102],"enhanced":[104],"due":[106],"unrealistic":[109],"assumption":[110],"spectrograms":[113],"are":[114],"linear":[115,124],"combinations":[116],"spectra.":[120],"Replacing":[121],"poor":[123],"generative":[125,138,148],"model":[126,149],"NMF":[131],"with":[132],"VAE-a":[134],"powerful":[135],"nonlinear":[136],"model-trained":[139],"speech,":[142],"we":[143,159],"formulate":[144],"unified":[146],"probabilistic":[147],"Given":[153],"observed":[157],"data,":[158],"can":[160],"sample":[161],"from":[164],"its":[165],"posterior":[166],"distribution.":[167],"The":[168],"proposed":[169],"outperformed":[171],"conventional":[173],"DNN-based":[174],"unseen":[177]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":21},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":27},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":23},{"year":2018,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}