{"id":"https://openalex.org/W3114440105","doi":"https://doi.org/10.23919/eusipco47968.2020.9287464","title":"Semi-supervised Multichannel Speech Separation Based on a Phone- and Speaker-Aware Deep Generative Model of Speech Spectrograms","display_name":"Semi-supervised Multichannel Speech Separation Based on a Phone- and Speaker-Aware Deep Generative Model of Speech Spectrograms","publication_year":2020,"publication_date":"2020-12-18","ids":{"openalex":"https://openalex.org/W3114440105","doi":"https://doi.org/10.23919/eusipco47968.2020.9287464","mag":"3114440105"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco47968.2020.9287464","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco47968.2020.9287464","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th European Signal Processing Conference (EUSIPCO)","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/A5062623275","display_name":"Yicheng Du","orcid":null},"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":"Yicheng Du","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/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","Center for Advanced Intelligence Project (AIP), RIKEN, Tokyo, Japan; Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"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"]},{"raw_affiliation_string":"Center for Advanced Intelligence Project (AIP), RIKEN, Tokyo, Japan; Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I4210126580","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), Tokyo, Japan","National Institute of Advanced Industrial Science and Technology (AIST),,,Tokyo,,Japan,135-0064"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), Tokyo, Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST),,,Tokyo,,Japan,135-0064","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","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","RIKEN,Center for Advanced Intelligence Project (AIP),Tokyo,Japan,103-0027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Advanced Intelligence Project (AIP), RIKEN, Tokyo, Japan","institution_ids":["https://openalex.org/I4210126580"]},{"raw_affiliation_string":"RIKEN,Center for Advanced Intelligence Project (AIP),Tokyo,Japan,103-0027","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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mathieu Fontaine","raw_affiliation_strings":["Center for Advanced Intelligence Project (AIP), RIKEN, Tokyo, Japan","RIKEN,Center for Advanced Intelligence Project (AIP),Tokyo,Japan,103-0027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Advanced Intelligence Project (AIP), RIKEN, Tokyo, Japan","institution_ids":["https://openalex.org/I4210126580"]},{"raw_affiliation_string":"RIKEN,Center for Advanced Intelligence Project (AIP),Tokyo,Japan,103-0027","institution_ids":["https://openalex.org/I4210126580"]}]},{"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"]},{"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","Center for Advanced Intelligence Project (AIP), RIKEN, Tokyo, Japan; Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"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"]},{"raw_affiliation_string":"Center for Advanced Intelligence Project (AIP), RIKEN, Tokyo, Japan; Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I4210126580","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":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6083,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.68516828,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"870","last_page":"874"},"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":0.9995999932289124,"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":0.9994999766349792,"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":0.7657631039619446},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7597180604934692},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7517125606536865},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5764094591140747},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.554722785949707},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.5409127473831177},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5374397039413452},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5293601155281067},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5244410634040833},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.42953264713287354},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.42141324281692505},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3686680495738983},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.34068524837493896},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.22331419587135315}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7657631039619446},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7597180604934692},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7517125606536865},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5764094591140747},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.554722785949707},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.5409127473831177},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5374397039413452},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5293601155281067},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5244410634040833},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.42953264713287354},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.42141324281692505},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3686680495738983},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.34068524837493896},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.22331419587135315},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco47968.2020.9287464","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco47968.2020.9287464","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th European Signal Processing Conference (EUSIPCO)","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":38,"referenced_works":["https://openalex.org/W1522199561","https://openalex.org/W1815076433","https://openalex.org/W1902027874","https://openalex.org/W1959608418","https://openalex.org/W2019927695","https://openalex.org/W2072548008","https://openalex.org/W2108501770","https://openalex.org/W2113990625","https://openalex.org/W2117332620","https://openalex.org/W2127851351","https://openalex.org/W2143027228","https://openalex.org/W2168273590","https://openalex.org/W2289394825","https://openalex.org/W2398264106","https://openalex.org/W2412956798","https://openalex.org/W2567070169","https://openalex.org/W2763188033","https://openalex.org/W2766672686","https://openalex.org/W2883322837","https://openalex.org/W2901552243","https://openalex.org/W2905196628","https://openalex.org/W2908510526","https://openalex.org/W2949416428","https://openalex.org/W2963375116","https://openalex.org/W2963970792","https://openalex.org/W2979850772","https://openalex.org/W2989942677","https://openalex.org/W3015225820","https://openalex.org/W3100968126","https://openalex.org/W6638545294","https://openalex.org/W6640963894","https://openalex.org/W6675944832","https://openalex.org/W6681345275","https://openalex.org/W6684562281","https://openalex.org/W6715525401","https://openalex.org/W6731370813","https://openalex.org/W6757817989","https://openalex.org/W6890361730"],"related_works":["https://openalex.org/W3094316140","https://openalex.org/W3133205200","https://openalex.org/W4289363934","https://openalex.org/W2898145319","https://openalex.org/W2098101267","https://openalex.org/W2898606530","https://openalex.org/W2059119686","https://openalex.org/W4289362680","https://openalex.org/W2403380333","https://openalex.org/W2761596192"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,34,82,94,124,129,137,147],"semi-supervised":[4],"multichannel":[5,38],"speech":[6,12,61,83,91,112,134,142,158,186],"separation":[7,30,62,187],"method":[8],"that":[9,41,103,127,182],"uses":[10],"clean":[11,90],"signals":[13,92],"with":[14,51,68,93,136,146],"frame-wise":[15],"phonetic":[16,117,194],"labels":[17,21,106,154,172],"and":[18,63,119,131,152,168,170],"sample-level":[19],"speaker":[20,105,120,153,171,197],"for":[22],"pre-training.":[23],"A":[24],"standard":[25],"approach":[26],"to":[27,32],"statistical":[28],"source":[29,43,76],"is":[31,113,144],"formulate":[33],"probabilistic":[35,125],"model":[36,84,126,135,143],"of":[37,49,80,166,173,185],"mixture":[39],"spectrograms":[40],"combines":[42,128],"models":[44,53,67],"representing":[45,54],"the":[46,55,160,183],"time-frequency":[47],"characteristics":[48],"sources":[50,174],"spatial":[52,139,161],"covariance":[56,162],"structure":[57],"between":[58],"channels.":[59],"For":[60],"enhancement,":[64],"deep":[65,133],"generative":[66],"latent":[69,164],"variables":[70,165],"have":[71],"successfully":[72],"been":[73],"used":[74],"as":[75,107,155],"models.":[77],"The":[78],"parameters":[79],"such":[81],"can":[85,188],"be":[86,189],"trained":[87,145],"beforehand":[88],"from":[89],"variational":[95],"autoencoder":[96],"(VAE)":[97],"or":[98],"its":[99],"conditional":[100],"variant":[101],"(CVAE)":[102],"takes":[104],"auxiliary":[108],"inputs.":[109],"Because":[110],"human":[111],"characterized":[114],"by":[115,191],"both":[116,150],"features":[118,195],"identities,":[121],"we":[122],"propose":[123],"phone-":[130],"speaker-aware":[132],"full-rank":[138],"model.":[140],"Our":[141],"CVAE":[148],"taking":[149],"phone":[151,169],"conditions.":[156],"Given":[157],"mixtures,":[159],"matrices,":[163],"sources,":[167],"are":[175],"jointly":[176],"estimated.":[177],"Comparative":[178],"experimental":[179],"results":[180],"showed":[181],"performance":[184],"improved":[190],"explicitly":[192],"considering":[193],"and/or":[196],"identities.":[198]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}