{"id":"https://openalex.org/W3011982609","doi":"https://doi.org/10.1109/taslp.2020.2979603","title":"A Flow-Based Deep Latent Variable Model for Speech Spectrogram Modeling and Enhancement","display_name":"A Flow-Based Deep Latent Variable Model for Speech Spectrogram Modeling and Enhancement","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3011982609","doi":"https://doi.org/10.1109/taslp.2020.2979603","mag":"3011982609"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.2979603","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.2979603","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/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, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0001-5424-747X","affiliations":[{"raw_affiliation_string":"Center for Advanced Intelligence Project (AIP), RIKEN, Tokyo, 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/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":"Kouhei Sekiguchi","raw_affiliation_strings":["Center for Advanced Intelligence Project (AIP), RIKEN, Tokyo, Japan","Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0001-6160-9301","affiliations":[{"raw_affiliation_string":"Center for Advanced Intelligence Project (AIP), RIKEN, Tokyo, Japan","institution_ids":["https://openalex.org/I4210126580"]},{"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/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":["Center for Advanced Intelligence Project (AIP), RIKEN, Tokyo, Japan","Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8387-8609","affiliations":[{"raw_affiliation_string":"Center for Advanced Intelligence Project (AIP), RIKEN, Tokyo, Japan","institution_ids":["https://openalex.org/I4210126580"]},{"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":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7816,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.85088901,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"28","issue":null,"first_page":"1104","last_page":"1117"},"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/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"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":0.9979000091552734,"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/spectrogram","display_name":"Spectrogram","score":0.858090341091156},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.7814358472824097},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.759010910987854},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6367513537406921},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.6348873376846313},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5336658954620361},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5323545932769775},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5243906378746033},{"id":"https://openalex.org/keywords/latent-variable-model","display_name":"Latent variable model","score":0.5158464312553406},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.49331918358802795},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.48002496361732483},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42655321955680847},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.4250658452510834},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4241124093532562},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3476402759552002},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.30088961124420166},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2233024537563324},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.07402676343917847}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.858090341091156},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.7814358472824097},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.759010910987854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6367513537406921},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.6348873376846313},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5336658954620361},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5323545932769775},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5243906378746033},{"id":"https://openalex.org/C65965080","wikidata":"https://www.wikidata.org/wiki/Q1806885","display_name":"Latent variable model","level":3,"score":0.5158464312553406},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.49331918358802795},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.48002496361732483},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42655321955680847},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.4250658452510834},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4241124093532562},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3476402759552002},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.30088961124420166},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2233024537563324},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.07402676343917847},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2020.2979603","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.2979603","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5799999833106995}],"awards":[{"id":"https://openalex.org/G6575691015","display_name":"A Unified Computational Model for Audio-Visual Recognition of Human Social Interaction","funder_award_id":"20K19833","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":87,"referenced_works":["https://openalex.org/W165956390","https://openalex.org/W565955800","https://openalex.org/W1409984952","https://openalex.org/W1498436455","https://openalex.org/W1516111018","https://openalex.org/W1560013842","https://openalex.org/W1582774210","https://openalex.org/W1601795611","https://openalex.org/W1663973292","https://openalex.org/W1815076433","https://openalex.org/W1836465849","https://openalex.org/W1902027874","https://openalex.org/W1959608418","https://openalex.org/W1965555277","https://openalex.org/W2020997493","https://openalex.org/W2056760934","https://openalex.org/W2062931547","https://openalex.org/W2127851351","https://openalex.org/W2138309709","https://openalex.org/W2141998673","https://openalex.org/W2143027228","https://openalex.org/W2188365844","https://openalex.org/W2289394825","https://openalex.org/W2326138198","https://openalex.org/W2489539531","https://openalex.org/W2502139158","https://openalex.org/W2519091744","https://openalex.org/W2559260703","https://openalex.org/W2620025707","https://openalex.org/W2766672686","https://openalex.org/W2771132365","https://openalex.org/W2804998325","https://openalex.org/W2874689226","https://openalex.org/W2883322837","https://openalex.org/W2886577208","https://openalex.org/W2901552243","https://openalex.org/W2905196628","https://openalex.org/W2918296821","https://openalex.org/W2922004249","https://openalex.org/W2922391058","https://openalex.org/W2943237054","https://openalex.org/W2952405182","https://openalex.org/W2962688977","https://openalex.org/W2962695743","https://openalex.org/W2962820504","https://openalex.org/W2962882868","https://openalex.org/W2962911072","https://openalex.org/W2962911378","https://openalex.org/W2963081964","https://openalex.org/W2963090522","https://openalex.org/W2963135265","https://openalex.org/W2963223306","https://openalex.org/W2963300588","https://openalex.org/W2963467180","https://openalex.org/W2963568578","https://openalex.org/W2964020555","https://openalex.org/W2964121744","https://openalex.org/W2964328256","https://openalex.org/W2964972896","https://openalex.org/W2972516210","https://openalex.org/W2979850772","https://openalex.org/W2994689640","https://openalex.org/W3100968126","https://openalex.org/W4206551434","https://openalex.org/W4237840503","https://openalex.org/W4255052368","https://openalex.org/W6610566761","https://openalex.org/W6631190155","https://openalex.org/W6635084905","https://openalex.org/W6638545294","https://openalex.org/W6638667902","https://openalex.org/W6640963894","https://openalex.org/W6687045409","https://openalex.org/W6712840351","https://openalex.org/W6714644935","https://openalex.org/W6718362372","https://openalex.org/W6738101965","https://openalex.org/W6745535286","https://openalex.org/W6749820799","https://openalex.org/W6752910514","https://openalex.org/W6754172774","https://openalex.org/W6754559877","https://openalex.org/W6755300632","https://openalex.org/W6756159577","https://openalex.org/W6758800702","https://openalex.org/W6766355753","https://openalex.org/W6767164110"],"related_works":["https://openalex.org/W2461917396","https://openalex.org/W1966667550","https://openalex.org/W2037497866","https://openalex.org/W1502435251","https://openalex.org/W2616125534","https://openalex.org/W2770703741","https://openalex.org/W4289300509","https://openalex.org/W2963987720","https://openalex.org/W2146310005","https://openalex.org/W4310661400"],"abstract_inverted_index":{"This":[0],"article":[1],"describes":[2],"a":[3,20,31,36,41,46,88,101],"deep":[4,21,28],"latent":[5,48,58,102,152],"variable":[6,49,103],"model":[7,50,104],"of":[8,76,90,125],"speech":[9,17,22,126,149,168,173],"power":[10],"spectrograms":[11,150],"and":[12,35,67,99,142,180],"its":[13],"application":[14],"to":[15,64,71,80,147],"semi-supervised":[16],"enhancement":[18],"with":[19],"prior.":[23],"By":[24],"integrating":[25],"two":[26],"major":[27],"generative":[29,94],"models,":[30],"variational":[32],"autoencoder":[33],"(VAE)":[34],"normalizing":[37],"flow":[38,95],"(NF),":[39],"in":[40,129],"mutually-beneficial":[42],"manner,":[43],"we":[44,86],"formulate":[45,100],"flexible":[47],"called":[51,92,105],"the":[52,65,74,77,81,93,106,112,118,130,140,143,157,175,178,181],"NF-VAE":[53],"that":[54,111],"can":[55],"extract":[56],"low-dimensional":[57],"representations":[59],"from":[60,151,156],"high-dimensional":[61],"observations,":[62,78],"akin":[63,79],"VAE,":[66],"does":[68],"not":[69],"need":[70],"explicitly":[72],"represent":[73],"distribution":[75],"NF.":[82],"In":[83],"this":[84],"article,":[85],"consider":[87],"variant":[89],"NF":[91],"(GF":[96],"a.k.a.":[97],"Glow)":[98],"GF-VAE.":[107],"We":[108],"experimentally":[109],"show":[110],"proposed":[113],"GF-VAE":[114,141,176],"is":[115,136],"better":[116],"than":[117],"standard":[119,158],"VAE":[120,144,179],"at":[121],"capturing":[122],"fine-structured":[123],"harmonics":[124],"spectrograms,":[127],"especially":[128],"high-frequency":[131],"range.":[132],"A":[133],"similar":[134],"finding":[135],"also":[137],"obtained":[138],"when":[139,162],"are":[145,165],"used":[146,166],"generate":[148],"variables":[153],"randomly":[154],"sampled":[155],"Gaussian":[159],"distribution.":[160],"Lastly,":[161],"these":[163],"models":[164],"as":[167],"priors":[169],"for":[170],"statistical":[171],"multichannel":[172],"enhancement,":[174],"outperforms":[177],"GF.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-09T07:52:08.696243","created_date":"2025-10-10T00:00:00"}