{"id":"https://openalex.org/W3015592506","doi":"https://doi.org/10.1109/icassp40776.2020.9053501","title":"Consistency-Aware Multi-Channel Speech Enhancement Using Deep Neural Networks","display_name":"Consistency-Aware Multi-Channel Speech Enhancement Using Deep Neural Networks","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015592506","doi":"https://doi.org/10.1109/icassp40776.2020.9053501","mag":"3015592506"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053501","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053501","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/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,Department of Intermedia Art and Science,Tokyo,Japan","Department of Intermedia Art and Science, Waseda University, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Department of Intermedia Art and Science,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Department of Intermedia Art and Science, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","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","LINE Corporation, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LINE Corporation,Tokyo,Japan","institution_ids":["https://openalex.org/I4210096607"]},{"raw_affiliation_string":"LINE Corporation, Tokyo, Japan","institution_ids":["https://openalex.org/I4210096607"]}]},{"author_position":"last","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","LINE Corporation, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LINE Corporation,Tokyo,Japan","institution_ids":["https://openalex.org/I4210096607"]},{"raw_affiliation_string":"LINE Corporation, Tokyo, Japan","institution_ids":["https://openalex.org/I4210096607"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8075,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.86642545,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"821","last_page":"825"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9980000257492065,"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"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9916999936103821,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.9209163784980774},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.8012778759002686},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.728187084197998},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.6254615783691406},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6130451560020447},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5886270403862},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5757448077201843},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5545458197593689},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.5278354287147522},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5220163464546204},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.44369858503341675},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43251675367355347},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3543385863304138},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3312889635562897},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18051698803901672},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.12262126803398132},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09953165054321289},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.06703811883926392}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9209163784980774},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.8012778759002686},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.728187084197998},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.6254615783691406},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6130451560020447},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5886270403862},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5757448077201843},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5545458197593689},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.5278354287147522},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5220163464546204},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.44369858503341675},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43251675367355347},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3543385863304138},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3312889635562897},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18051698803901672},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.12262126803398132},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09953165054321289},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.06703811883926392},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053501","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053501","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":0.4099999964237213,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1983108229","https://openalex.org/W1996304098","https://openalex.org/W2120847449","https://openalex.org/W2143027228","https://openalex.org/W2292743699","https://openalex.org/W2398042854","https://openalex.org/W2398972335","https://openalex.org/W2401387233","https://openalex.org/W2408744528","https://openalex.org/W2517616541","https://openalex.org/W2539508298","https://openalex.org/W2568308529","https://openalex.org/W2586584460","https://openalex.org/W2600628583","https://openalex.org/W2640112133","https://openalex.org/W2766901645","https://openalex.org/W2803322398","https://openalex.org/W2889411318","https://openalex.org/W2892163332","https://openalex.org/W2902806197","https://openalex.org/W2923728956","https://openalex.org/W2937235446","https://openalex.org/W2954049404","https://openalex.org/W2954695182","https://openalex.org/W2962905190","https://openalex.org/W2963189033","https://openalex.org/W2973084105","https://openalex.org/W3121132363","https://openalex.org/W4253928870","https://openalex.org/W6735168207"],"related_works":["https://openalex.org/W2064323827","https://openalex.org/W2782295999","https://openalex.org/W1970292246","https://openalex.org/W2162306796","https://openalex.org/W2015118744","https://openalex.org/W4247952185","https://openalex.org/W1642462315","https://openalex.org/W2005619368","https://openalex.org/W1879092539","https://openalex.org/W2526155427"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,14,52],"deep":[4],"neural":[5],"network":[6],"(DNN)\u2013based":[7],"multichannel":[8],"speech":[9,29,120],"enhancement":[10,30,121],"system":[11,178],"in":[12,34,46,128,157,166],"which":[13],"DNN":[15],"is":[16,31,70,83,122,135,155,164],"trained":[17],"to":[18,86,108,138,180],"maximize":[19],"the":[20,23,35,47,60,67,81,87,91,97,115,129,139,148,152,158,161,167,173,176],"quality":[21],"of":[22,175],"enhanced":[24,98],"time-domain":[25,99,117],"signal.":[26,118],"DNN-based":[27],"multi-channel":[28,125],"often":[32,71],"conducted":[33,123],"time-frequency":[36],"(T-F)":[37],"domain":[38],"because":[39],"spatial":[40],"filtering":[41,127],"can":[42],"be":[43],"efficiently":[44],"implemented":[45],"T-F":[48,62,130,168,181],"domain.":[49,169],"In":[50],"such":[51],"case,":[53],"ordinary":[54],"objective":[55,92,111,144],"functions":[56,145],"are":[57],"computed":[58,146],"on":[59,114,147],"estimated":[61,68],"mask":[63],"or":[64],"spectrogram.":[65],"However,":[66],"spectrogram":[69,82],"inconsistent,":[72],"and":[73,76,132,160,183],"its":[74,133],"amplitude":[75],"phase":[77],"may":[78],"change":[79],"when":[80],"converted":[84,136],"back":[85,137],"time-domain.":[88,140],"That":[89],"is,":[90],"function":[93,112],"does":[94],"not":[95],"evaluate":[96],"signal":[100,150],"properly.":[101],"To":[102],"address":[103],"this":[104],"problem,":[105],"we":[106],"propose":[107,142],"use":[109],"an":[110],"defined":[113,156,165],"reconstructed":[116,149],"Specifically,":[119],"by":[124],"Wiener":[126],"domain,":[131],"result":[134],"We":[141],"two":[143],"where":[151],"first":[153],"one":[154,163],"time-domain,":[159],"other":[162],"Our":[170],"experiment":[171],"demonstrates":[172],"effectiveness":[174],"proposed":[177],"comparing":[179],"masking":[182],"mask-based":[184],"beamforming.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}