{"id":"https://openalex.org/W3016244615","doi":"https://doi.org/10.1109/icassp40776.2020.9054171","title":"Unsupervised Training for Deep Speech Source Separation with Kullback-Leibler Divergence Based Probabilistic Loss Function","display_name":"Unsupervised Training for Deep Speech Source Separation with Kullback-Leibler Divergence Based Probabilistic Loss Function","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016244615","doi":"https://doi.org/10.1109/icassp40776.2020.9054171","mag":"3016244615"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054171","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054171","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5021883714","display_name":"Masahito Togami","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masahito Togami","raw_affiliation_strings":["LINE Corporation, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LINE Corporation, Tokyo, Japan","institution_ids":["https://openalex.org/I4210096607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042385500","display_name":"Yoshiki Masuyama","orcid":"https://orcid.org/0000-0002-5881-0474"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshiki Masuyama","raw_affiliation_strings":["Waseda University, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113730169","display_name":"Tatsuya Komatsu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Komatsu","raw_affiliation_strings":["LINE Corporation, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LINE Corporation, Tokyo, Japan","institution_ids":["https://openalex.org/I4210096607"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070736822","display_name":"Yu Nakagome","orcid":"https://orcid.org/0000-0002-5837-8212"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yu Nakagome","raw_affiliation_strings":["Waseda University, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.122,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.93456958,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"56","last_page":"60"},"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":0.9976999759674072,"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":0.9970999956130981,"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":0.7131548523902893},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.6693276762962341},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.6473128795623779},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6364486217498779},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6140512228012085},{"id":"https://openalex.org/keywords/kullback\u2013leibler-divergence","display_name":"Kullback\u2013Leibler divergence","score":0.5826095342636108},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5708886384963989},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5415407419204712},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.4439120888710022},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4369155168533325},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.4361165761947632},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.43564170598983765},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42892634868621826},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4226270318031311},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34841907024383545},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.25276342034339905},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.10514473915100098}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7131548523902893},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.6693276762962341},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.6473128795623779},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6364486217498779},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6140512228012085},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.5826095342636108},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5708886384963989},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5415407419204712},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.4439120888710022},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4369155168533325},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.4361165761947632},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.43564170598983765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42892634868621826},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4226270318031311},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34841907024383545},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.25276342034339905},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.10514473915100098},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/icassp40776.2020.9054171","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054171","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1522301498","https://openalex.org/W1543386260","https://openalex.org/W1845880232","https://openalex.org/W1987906574","https://openalex.org/W1996304098","https://openalex.org/W2031583051","https://openalex.org/W2099741732","https://openalex.org/W2114461480","https://openalex.org/W2127851351","https://openalex.org/W2143027228","https://openalex.org/W2164502538","https://openalex.org/W2168273590","https://openalex.org/W2221409856","https://openalex.org/W2408744528","https://openalex.org/W2460742184","https://openalex.org/W2558649592","https://openalex.org/W2563666542","https://openalex.org/W2735663686","https://openalex.org/W2785420794","https://openalex.org/W2792498316","https://openalex.org/W2803322398","https://openalex.org/W2892163332","https://openalex.org/W2899515918","https://openalex.org/W2933708090","https://openalex.org/W2937235446","https://openalex.org/W2952519342","https://openalex.org/W2963969588","https://openalex.org/W2964121744","https://openalex.org/W2964237233","https://openalex.org/W2973084105","https://openalex.org/W2981096075","https://openalex.org/W3124972797","https://openalex.org/W3127686677","https://openalex.org/W6631190155","https://openalex.org/W6632571750","https://openalex.org/W6769307377","https://openalex.org/W6917638038"],"related_works":["https://openalex.org/W1509813908","https://openalex.org/W2031820693","https://openalex.org/W3024816962","https://openalex.org/W973023320","https://openalex.org/W1910172735","https://openalex.org/W2118307209","https://openalex.org/W2107364365","https://openalex.org/W2539388437","https://openalex.org/W2107688514","https://openalex.org/W2137288760"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,64],"propose":[4],"a":[5,12,33,53,57,66,107,124,129,141],"multi-channel":[6],"speech":[7,42,47],"source":[8,48],"separation":[9,49,116],"method":[10,38,50,139,182],"with":[11],"deep":[13],"neural":[14],"network":[15],"(DNN)":[16],"which":[17,51,73,95,127,144],"is":[18,27,104,133],"trained":[19],"under":[20,175],"the":[21,36,100,137,146,159,166,170,180,187],"condition":[22],"that":[23,179],"no":[24],"clean":[25,34],"signal":[26,43,149],"available.":[28],"As":[29,56],"an":[30,40,45],"alternative":[31],"to":[32,82,112,115],"signal,":[35,63],"proposed":[37,138,181],"adopts":[39,65,140],"estimated":[41],"by":[44],"unsupervised":[46],"leverages":[52],"statistical":[54,58],"model.":[55],"model":[59,72],"of":[60,158],"microphone":[61],"input":[62],"time-varying":[67,101],"spatial":[68],"covariance":[69],"matrix":[70],"(SCM)":[71],"includes":[74],"reverberation":[75,86],"and":[76,87],"background":[77,88],"noise":[78],"submodels":[79],"so":[80,110],"as":[81,111],"achieve":[83],"robustness":[84],"against":[85],"noise.":[89],"The":[90,156],"DNN":[91,167],"infers":[92],"intermediate":[93,122,131,171],"variables":[94],"are":[96,120],"needed":[97],"for":[98],"constructing":[99],"SCM.":[102],"Separation":[103],"performed":[105],"in":[106],"probabilistic":[108,148],"manner":[109],"avoid":[113],"overfitting":[114],"error.":[117],"Since":[118],"there":[119],"multiple":[121],"variables,":[123],"loss":[125,142,160],"function":[126,143,161],"evaluates":[128,145],"single":[130],"variable":[132],"not":[134],"applicable.":[135],"Instead,":[136],"output":[147],"directly":[150],"based":[151],"on":[152],"Kullback-Leibler":[153],"Divergence":[154],"(KLD).":[155],"gradient":[157],"can":[162],"be":[163],"back-propagated":[164],"into":[165],"through":[168],"all":[169],"variables.":[172],"Experimental":[173],"results":[174,185],"reverberant":[176],"conditions":[177],"show":[178],"achieves":[183],"better":[184],"than":[186],"conventional":[188],"methods.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}