{"id":"https://openalex.org/W4386765255","doi":"https://doi.org/10.1109/waspaa58266.2023.10248168","title":"Time-Domain Audio Source Separation Based on Gaussian Processes with Deep Kernel Learning","display_name":"Time-Domain Audio Source Separation Based on Gaussian Processes with Deep Kernel Learning","publication_year":2023,"publication_date":"2023-09-15","ids":{"openalex":"https://openalex.org/W4386765255","doi":"https://doi.org/10.1109/waspaa58266.2023.10248168"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa58266.2023.10248168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa58266.2023.10248168","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-04172863/document","any_repository_has_fulltext":true},"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/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"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":["RIKEN,Center for Advanced Intelligence Project (AIP),Japan","Graduate School of Informatics, Kyoto University, Japan","Center for Advanced Intelligence Project (AIP), RIKEN, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RIKEN,Center for Advanced Intelligence Project (AIP),Japan","institution_ids":["https://openalex.org/I4210126580"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Center for Advanced Intelligence Project (AIP), RIKEN, Japan","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023307571","display_name":"Diego Di Carlo","orcid":"https://orcid.org/0000-0002-4090-2872"},"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/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":"Diego Di Carlo","raw_affiliation_strings":["RIKEN,Center for Advanced Intelligence Project (AIP),Japan","Center for Advanced Intelligence Project (AIP), RIKEN, Japan","Graduate School of Informatics, Kyoto University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RIKEN,Center for Advanced Intelligence Project (AIP),Japan","institution_ids":["https://openalex.org/I4210126580"]},{"raw_affiliation_string":"Center for Advanced Intelligence Project (AIP), RIKEN, Japan","institution_ids":["https://openalex.org/I4210126580"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Japan","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/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"]},{"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","National Institute of Advanced Industrial Science and Technology (AIST), Japan","Center for Advanced Intelligence Project (AIP), RIKEN, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST),Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"Center for Advanced Intelligence Project (AIP), RIKEN, Japan","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"]},{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR","JP"],"is_corresponding":false,"raw_author_name":"Mathieu Fontaine","raw_affiliation_strings":["Institut Polytechnique de Paris,LTCI, Télécom Paris,France","Center for Advanced Intelligence Project (AIP), RIKEN, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,LTCI, Télécom Paris,France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I4210145102"]},{"raw_affiliation_string":"Center for Advanced Intelligence Project (AIP), RIKEN, Japan","institution_ids":["https://openalex.org/I4210126580"]}]},{"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":["Kyoto University,Graduate School of Informatics,Japan","Graduate School of Informatics, Kyoto University, Japan","Center for Advanced Intelligence Project (AIP), RIKEN, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University,Graduate School of Informatics,Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Center for Advanced Intelligence Project (AIP), RIKEN, Japan","institution_ids":["https://openalex.org/I4210126580"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3476,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.5383478,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9934999942779541,"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/covariance-function","display_name":"Covariance function","score":0.5490477681159973},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5354912877082825},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5218074321746826},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.5195134878158569},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.514560878276825},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.43755921721458435},{"id":"https://openalex.org/keywords/covariance-matrix","display_name":"Covariance matrix","score":0.43740174174308777},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42958056926727295},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4160791337490082},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40634724497795105},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38358357548713684},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.347785621881485},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.17480266094207764}],"concepts":[{"id":"https://openalex.org/C137250428","wikidata":"https://www.wikidata.org/wiki/Q5178897","display_name":"Covariance function","level":3,"score":0.5490477681159973},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5354912877082825},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5218074321746826},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.5195134878158569},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.514560878276825},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43755921721458435},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.43740174174308777},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42958056926727295},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4160791337490082},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40634724497795105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38358357548713684},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.347785621881485},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.17480266094207764},{"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/waspaa58266.2023.10248168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa58266.2023.10248168","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04172863v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04172863","pdf_url":"https://hal.science/hal-04172863/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"WASPAA, Oct 2023, New Paltz, France","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04172863v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04172863","pdf_url":"https://hal.science/hal-04172863/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"WASPAA, Oct 2023, New Paltz, France","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.699999988079071,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G3510745091","display_name":"Speaker diarization with a unified robust multimodal and spatial audio model","funder_award_id":"ANR-22-CE23-0011","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386765255.pdf"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W188967299","https://openalex.org/W1552314771","https://openalex.org/W1870250857","https://openalex.org/W2120847449","https://openalex.org/W2134807719","https://openalex.org/W2141998673","https://openalex.org/W2149273154","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2502139158","https://openalex.org/W2735471653","https://openalex.org/W2918296821","https://openalex.org/W2952218014","https://openalex.org/W2962880441","https://openalex.org/W2962935966","https://openalex.org/W2964058413","https://openalex.org/W2972541922","https://openalex.org/W3015191643","https://openalex.org/W3020336359","https://openalex.org/W3030356194","https://openalex.org/W3092342941","https://openalex.org/W3095717210","https://openalex.org/W3099330747","https://openalex.org/W3104574805","https://openalex.org/W3160845765","https://openalex.org/W3163652268","https://openalex.org/W3167533889","https://openalex.org/W3191469971","https://openalex.org/W3199957557","https://openalex.org/W4211049957","https://openalex.org/W4225905067","https://openalex.org/W4372348953","https://openalex.org/W4375869348","https://openalex.org/W4379797396","https://openalex.org/W6631190155","https://openalex.org/W6638545294","https://openalex.org/W6678818196","https://openalex.org/W6684770997","https://openalex.org/W6741166455","https://openalex.org/W6769827846","https://openalex.org/W6785394617","https://openalex.org/W6791136995"],"related_works":["https://openalex.org/W2386803684","https://openalex.org/W3178402891","https://openalex.org/W651058035","https://openalex.org/W143964308","https://openalex.org/W2073389045","https://openalex.org/W2046078371","https://openalex.org/W4315750325","https://openalex.org/W1971337326","https://openalex.org/W2060696366","https://openalex.org/W4213259725"],"abstract_inverted_index":{"This":[0,150],"paper":[1],"revisits":[2],"single-channel":[3],"audio":[4],"source":[5,27,67,83,135,148,160],"separation":[6],"based":[7],"on":[8],"a":[9,14,30,43,54,71,97,113,155,163],"probabilistic":[10],"generative":[11],"model":[12],"of":[13,39,65,81,119,139,154],"mixture":[15,62,93,156],"signal":[16,28,63,157],"defined":[17],"in":[18,112,187],"the":[19,79,82,88,92,109,125,129,134,141,146,152,159,171,182,188,204,213,220],"continuous":[20],"time":[21],"domain.":[22],"We":[23],"assume":[24],"that":[25,107,169,212],"each":[26],"follows":[29,42,70],"non-stationary":[31],"Gaussian":[32,46],"process":[33],"(GP),":[34],"i.e.,":[35],"any":[36],"finite":[37],"set":[38],"sampled":[40],"points":[41],"zero-mean":[44],"multivariate":[45],"distribution":[47],"whose":[48,73],"covariance":[49,74,84,136,173],"matrix":[50,75],"is":[51,76,122],"governed":[52],"by":[53,78],"kernel":[55,130,179],"function":[56,131,180],"over":[57,175],"time-varying":[58],"latent":[59,89,110,126],"variables.":[60],"The":[61,116,178],"composed":[64],"such":[66],"signals":[68,161],"thus":[69],"GP":[72],"given":[77],"sum":[80],"matrices.":[85],"To":[86],"estimate":[87],"variables":[90,111,127],"from":[91,203],"signal,":[94],"we":[95],"use":[96],"deep":[98],"neural":[99],"network":[100,183],"with":[101,162],"an":[102],"encoder-separator-decoder":[103],"architecture":[104],"(e.g.,":[105],"Conv-TasNet)":[106],"separates":[108],"pseudo-time-frequency":[114],"space.":[115],"key":[117],"feature":[118],"our":[120],"method":[121,215,222],"to":[123],"feed":[124],"into":[128,158],"for":[132,143],"estimating":[133,145],"matrices,":[137],"instead":[138],"using":[140,194],"decoder":[142],"directly":[144],"time-domain":[147],"signals.":[149],"enables":[151],"decomposition":[153],"classical":[164],"yet":[165],"powerful":[166],"Wiener":[167],"filter":[168],"considers":[170],"full":[172],"structure":[174],"all":[176],"samples.":[177],"and":[181,200,207,218,225],"are":[184],"trained":[185],"jointly":[186],"maximum":[189],"likelihood":[190],"framework.":[191],"Comparative":[192],"experiments":[193],"two-speech":[195],"mixtures":[196],"under":[197,223],"clean,":[198],"noisy,":[199],"noisy-reverberant":[201,226],"conditions":[202],"WSJ0-2mix,":[205],"WHAM!,":[206],"WHAMR!":[208],"benchmark":[209],"datasets":[210],"demonstrated":[211],"proposed":[214],"performed":[216],"well":[217],"outperformed":[219],"baseline":[221],"noisy":[224],"conditions.":[227]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T08:27:34.040176","created_date":"2025-10-10T00:00:00"}