{"id":"https://openalex.org/W2589857635","doi":"https://doi.org/10.1109/taslp.2017.2672401","title":"Multichannel Signal Processing With Deep Neural Networks for Automatic Speech Recognition","display_name":"Multichannel Signal Processing With Deep Neural Networks for Automatic Speech Recognition","publication_year":2017,"publication_date":"2017-02-20","ids":{"openalex":"https://openalex.org/W2589857635","doi":"https://doi.org/10.1109/taslp.2017.2672401","mag":"2589857635"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2017.2672401","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2672401","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tara N. Sainath","raw_affiliation_strings":["Google, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Google, New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103273436","display_name":"Ron J. Weiss","orcid":"https://orcid.org/0000-0003-2010-4053"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ron J. Weiss","raw_affiliation_strings":["Google, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Google, New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087313939","display_name":"Kevin Wilson","orcid":"https://orcid.org/0000-0001-9141-2219"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin W. Wilson","raw_affiliation_strings":["Google, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Google, New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374448","display_name":"Bo Li","orcid":"https://orcid.org/0000-0002-6711-3603"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Li","raw_affiliation_strings":["Google, Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000078382","display_name":"Arun Narayanan","orcid":"https://orcid.org/0009-0008-3325-8928"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arun Narayanan","raw_affiliation_strings":["Google, Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040131037","display_name":"Ehsan Variani","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ehsan Variani","raw_affiliation_strings":["Google, Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049614700","display_name":"Michiel Bacchiani","orcid":"https://orcid.org/0000-0003-4527-0197"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michiel Bacchiani","raw_affiliation_strings":["Google, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Google, New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025419994","display_name":"Izhak Shafran","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Izhak Shafran","raw_affiliation_strings":["Google, Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079708487","display_name":"Andrew Senior","orcid":"https://orcid.org/0000-0002-2401-5691"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Senior","raw_affiliation_strings":["Google, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Google, New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058000820","display_name":"K. K. Chin","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kean Chin","raw_affiliation_strings":["Google, Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091715883","display_name":"Ananya Misra","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ananya Misra","raw_affiliation_strings":["Google, Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100684423","display_name":"Chanwoo Kim","orcid":"https://orcid.org/0000-0003-2526-4371"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chanwoo Kim","raw_affiliation_strings":["Google, Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5070513394"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":21.928,"has_fulltext":false,"cited_by_count":240,"citation_normalized_percentile":{"value":0.99686478,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"25","issue":"5","first_page":"965","last_page":"979"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9988999962806702,"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":0.8297827243804932},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.6777284145355225},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.656255841255188},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.6177146434783936},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6079673171043396},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5365578532218933},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.48806703090667725},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.46601560711860657},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.44101861119270325},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.4358968436717987},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41208416223526},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35995936393737793},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1268531084060669},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.11464139819145203}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8297827243804932},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.6777284145355225},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.656255841255188},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.6177146434783936},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6079673171043396},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5365578532218933},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.48806703090667725},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.46601560711860657},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.44101861119270325},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.4358968436717987},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41208416223526},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35995936393737793},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1268531084060669},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.11464139819145203},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software 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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2017.2672401","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2672401","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W1499999342","https://openalex.org/W1533861849","https://openalex.org/W1542280630","https://openalex.org/W1600744878","https://openalex.org/W1603075283","https://openalex.org/W1831449718","https://openalex.org/W1847088711","https://openalex.org/W2035846950","https://openalex.org/W2046317813","https://openalex.org/W2057035781","https://openalex.org/W2058641082","https://openalex.org/W2059652044","https://openalex.org/W2060108923","https://openalex.org/W2061074721","https://openalex.org/W2090958120","https://openalex.org/W2100089127","https://openalex.org/W2101609516","https://openalex.org/W2117678320","https://openalex.org/W2119203697","https://openalex.org/W2121573996","https://openalex.org/W2130361043","https://openalex.org/W2132037657","https://openalex.org/W2168231600","https://openalex.org/W2172097686","https://openalex.org/W2289394825","https://openalex.org/W2291652038","https://openalex.org/W2293634267","https://openalex.org/W2398826216","https://openalex.org/W2398972335","https://openalex.org/W2407277936","https://openalex.org/W2408093180","https://openalex.org/W2475988411","https://openalex.org/W2506203739","https://openalex.org/W2512499206","https://openalex.org/W2516857479","https://openalex.org/W2546191734","https://openalex.org/W2613634265","https://openalex.org/W2755891984","https://openalex.org/W2953061907","https://openalex.org/W2962719052","https://openalex.org/W2963175699","https://openalex.org/W3149448910","https://openalex.org/W4249052411","https://openalex.org/W4297801963","https://openalex.org/W6621543089","https://openalex.org/W6631943919","https://openalex.org/W6638670064","https://openalex.org/W6638824847","https://openalex.org/W6678409544","https://openalex.org/W6684859321","https://openalex.org/W6696934422","https://openalex.org/W6712560600","https://openalex.org/W6744261651"],"related_works":["https://openalex.org/W1809875158","https://openalex.org/W2149699223","https://openalex.org/W2930648092","https://openalex.org/W106163518","https://openalex.org/W2952917250","https://openalex.org/W1491017269","https://openalex.org/W2636483419","https://openalex.org/W2229498876","https://openalex.org/W2161947961","https://openalex.org/W4286800517"],"abstract_inverted_index":{"Multichannel":[0],"automatic":[1],"speech":[2,8],"recognition":[3],"(ASR)":[4],"systems":[5],"commonly":[6],"separate":[7,131],"enhancement,":[9],"including":[10],"localization,":[11],"beamforming,":[12,37],"and":[13,84,210],"postfiltering,":[14],"from":[15,56,137],"acoustic":[16,27],"modeling.":[17],"In":[18],"this":[19,87],"paper,":[20],"we":[21,59,118,169,184],"perform":[22],"multichannel":[23,75,133,188,207],"enhancement":[24],"jointly":[25],"with":[26],"modeling":[28,61],"in":[29,41,77,179],"a":[30,69,104,138,144,192,204,216],"deep":[31],"neural":[32,70,189],"network":[33,71,88],"framework.":[34],"Inspired":[35],"by":[36,125],"which":[38,73,142,153],"leverages":[39],"differences":[40],"the":[42,47,62,78,82,112,127,132,155,165,180],"fine":[43],"time":[44,161],"structure":[45],"of":[46,81,98,111,198],"signal":[48],"at":[49,159],"different":[50,57],"microphones":[51],"to":[52,90,93,130,203,215],"filter":[53,157],"energy":[54],"arriving":[55],"directions,":[58],"explore":[60],"raw":[63],"time-domain":[64],"waveform":[65,219],"directly.":[66],"We":[67,147],"introduce":[68,149],"architecture,":[72],"performs":[74],"filtering":[76,135],"first":[79,128],"layer":[80,129],"network,":[83],"show":[85,119],"that":[86,106,171,186],"learns":[89],"be":[91,123,175],"robust":[92],"varying":[94],"target":[95,114],"speaker":[96,115],"direction":[97],"arrival,":[99],"performing":[100],"as":[101,103],"well":[102],"model":[105],"is":[107],"given":[108],"oracle":[109],"knowledge":[110],"true":[113],"direction.":[116],"Next,":[117],"how":[120],"performance":[121],"can":[122,174],"improved":[124],"factoring":[126],"spatial":[134,156],"operation":[136],"single":[139,217],"channel":[140,218],"filterbank":[141],"computes":[143],"frequency":[145,181],"decomposition.":[146],"also":[148],"an":[150],"adaptive":[151],"variant,":[152],"updates":[154],"coefficients":[158],"each":[160],"frame":[162],"based":[163],"on":[164],"previous":[166],"inputs.":[167],"Finally,":[168],"demonstrate":[170],"these":[172],"approaches":[173],"implemented":[176],"more":[177,199,211],"efficiently":[178],"domain.":[182],"Overall,":[183],"find":[185],"such":[187],"networks":[190],"give":[191],"relative":[193],"word":[194],"error":[195],"rate":[196],"improvement":[197],"than":[200,212],"5%":[201],"compared":[202,214],"traditional":[205],"beamforming-based":[206],"ASR":[208],"system":[209],"10%":[213],"model.":[220]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":32},{"year":2021,"cited_by_count":40},{"year":2020,"cited_by_count":40},{"year":2019,"cited_by_count":40},{"year":2018,"cited_by_count":29},{"year":2017,"cited_by_count":8}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}