{"id":"https://openalex.org/W3015756037","doi":"https://doi.org/10.1109/icassp40776.2020.9053791","title":"Joint Training of Deep Neural Networks for Multi-Channel Dereverberation and Speech Source Separation","display_name":"Joint Training of Deep Neural Networks for Multi-Channel Dereverberation and Speech Source Separation","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015756037","doi":"https://doi.org/10.1109/icassp40776.2020.9053791","mag":"3015756037"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053791","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":"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/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":true,"raw_author_name":"Masahito Togami","raw_affiliation_strings":["LINE Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"LINE Corporation, Tokyo, Japan","institution_ids":["https://openalex.org/I4210096607"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5021883714"],"corresponding_institution_ids":["https://openalex.org/I4210096607"],"apc_list":null,"apc_paid":null,"fwci":0.9092,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.73166557,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3032","last_page":"3036"},"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":0.9975000023841858,"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":0.9968000054359436,"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/computer-science","display_name":"Computer science","score":0.7615789771080017},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.636123538017273},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6273614764213562},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6192806363105774},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5920031070709229},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5395113825798035},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4985685348510742},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.4932093024253845},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4648066759109497},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4624621570110321},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.43591535091400146},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4202054738998413},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34311214089393616},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.17732396721839905},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10804453492164612},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05774891376495361}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7615789771080017},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.636123538017273},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6273614764213562},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6192806363105774},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5920031070709229},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5395113825798035},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4985685348510742},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.4932093024253845},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4648066759109497},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4624621570110321},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.43591535091400146},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4202054738998413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34311214089393616},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.17732396721839905},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10804453492164612},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05774891376495361},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053791","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":[{"display_name":"Peace, Justice and strong institutions","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1982310295","https://openalex.org/W1996304098","https://openalex.org/W2002146237","https://openalex.org/W2127851351","https://openalex.org/W2143027228","https://openalex.org/W2164502538","https://openalex.org/W2221409856","https://openalex.org/W2242685705","https://openalex.org/W2398042854","https://openalex.org/W2408744528","https://openalex.org/W2460742184","https://openalex.org/W2747732471","https://openalex.org/W2800675406","https://openalex.org/W2803322398","https://openalex.org/W2886577208","https://openalex.org/W2889801373","https://openalex.org/W2890489755","https://openalex.org/W2890553422","https://openalex.org/W2891219041","https://openalex.org/W2892163332","https://openalex.org/W2894192904","https://openalex.org/W2899625056","https://openalex.org/W2937235446","https://openalex.org/W2963969588","https://openalex.org/W2964121744","https://openalex.org/W2973084105","https://openalex.org/W2982840733","https://openalex.org/W3127686677","https://openalex.org/W6631190155","https://openalex.org/W6754172774","https://openalex.org/W6755236810","https://openalex.org/W6917638038"],"related_works":["https://openalex.org/W1656519308","https://openalex.org/W2042717753","https://openalex.org/W2037265366","https://openalex.org/W2022849831","https://openalex.org/W2391832549","https://openalex.org/W2286653370","https://openalex.org/W1499578372","https://openalex.org/W2368849850","https://openalex.org/W1799937301","https://openalex.org/W2026603686"],"abstract_inverted_index":{"In":[0,106],"this":[1,107,111],"paper,":[2,108],"we":[3,88,109],"propose":[4],"a":[5,40,78,90,115],"joint":[6,174,196],"training":[7,175,197],"of":[8,102,135,145,150,164,176],"two":[9,177],"deep":[10],"neural":[11],"networks":[12],"(DNNs)":[13],"for":[14],"dereverberation":[15,28,63,137],"and":[16,33,64],"speech":[17,35,65,84,122,128],"source":[18,36,66,85,123],"separation.":[19],"The":[20,43,70],"proposed":[21,44,71,89,173],"method":[22,45,72],"connects":[23],"the":[24,27,30,34,74,83,95,103,132,136,142,146,151,157,161,165,172,186,195],"first":[25,158],"DNN,":[26,32,148],"part,":[29],"second":[31,147,166],"separation":[37,67,86,124],"part":[38,138],"in":[39,82,194],"cascade":[41],"manner.":[42],"does":[46],"not":[47,120],"train":[48],"each":[49],"DNN":[50,159],"separately.":[51],"Instead,":[52],"an":[53,59],"integrated":[54],"loss":[55,91,112,116,152,190],"function":[56,92,100,113,117,153,191],"which":[57,93,118],"evaluates":[58,94,119],"output":[60,75,104,133],"signal":[61,76,134],"after":[62],"is":[68,139,154,179,182,192],"adopted.":[69],"estimates":[73],"as":[77],"probabilistic":[79],"variable.":[80],"Recently,":[81],"context,":[87],"estimated":[96],"posterior":[97,187],"probability":[98],"density":[99],"(PDF)":[101],"signal.":[105],"extend":[110],"into":[114,141,156],"only":[121],"performance":[125],"but":[126],"also":[127,183],"derevereberation":[129],"performance.":[130],"Since":[131],"converted":[140],"input":[143,162],"feature":[144,163],"gradient":[149],"back-propagated":[155],"through":[160],"DNN.":[167],"Experimental":[168],"results":[169],"show":[170],"that":[171,185],"DNNs":[178],"effective.":[180],"It":[181],"shown":[184],"PDF":[188],"based":[189],"effective":[193],"context.":[198]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}