{"id":"https://openalex.org/W2963177459","doi":"https://doi.org/10.1109/icassp.2018.8462430","title":"Deep Learning Based Speech Beamforming","display_name":"Deep Learning Based Speech Beamforming","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2963177459","doi":"https://doi.org/10.1109/icassp.2018.8462430","mag":"2963177459"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462430","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5030425371","display_name":"Kaizhi Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaizhi Qian","raw_affiliation_strings":["[University of Illinois at Urbana-Champaign,USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"[University of Illinois at Urbana-Champaign,USA]","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100354659","display_name":"Yang Zhang","orcid":"https://orcid.org/0000-0002-2739-1916"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang Zhang","raw_affiliation_strings":["IBM T.J.Watson Research Center, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T.J.Watson Research Center, USA#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112248869","display_name":"Shiyu Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiyu Chang","raw_affiliation_strings":["IBM T.J.Watson Research Center, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T.J.Watson Research Center, USA#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059726557","display_name":"Xuesong Yang","orcid":"https://orcid.org/0000-0001-8625-5044"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuesong Yang","raw_affiliation_strings":["[University of Illinois at Urbana-Champaign,USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"[University of Illinois at Urbana-Champaign,USA]","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088040986","display_name":"Dinei Flor\u00eancio","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dinei Florencio","raw_affiliation_strings":["Microsoft Research; USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research; USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["[University of Illinois at Urbana-Champaign,USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"[University of Illinois at Urbana-Champaign,USA]","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5389","last_page":"5393"},"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":0.9986000061035156,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9984999895095825,"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/beamforming","display_name":"Beamforming","score":0.714945912361145},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7002007961273193},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5068040490150452},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.45679333806037903},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39937624335289},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13155394792556763}],"concepts":[{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.714945912361145},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7002007961273193},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5068040490150452},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.45679333806037903},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39937624335289},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13155394792556763}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462430","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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":0.44999998807907104,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1510355813","https://openalex.org/W1515932869","https://openalex.org/W1808196926","https://openalex.org/W2031647436","https://openalex.org/W2046869671","https://openalex.org/W2101609516","https://openalex.org/W2106557043","https://openalex.org/W2117678320","https://openalex.org/W2151938450","https://openalex.org/W2160473997","https://openalex.org/W2170222430","https://openalex.org/W2170768669","https://openalex.org/W2394461504","https://openalex.org/W2398042854","https://openalex.org/W2412956798","https://openalex.org/W2515930231","https://openalex.org/W2517616541","https://openalex.org/W2519091744","https://openalex.org/W2594647430","https://openalex.org/W2678916739","https://openalex.org/W2714487941","https://openalex.org/W2718052359","https://openalex.org/W2747161606","https://openalex.org/W2963103134","https://openalex.org/W4300702110","https://openalex.org/W4302765731"],"related_works":["https://openalex.org/W2731899572","https://openalex.org/W3215138031","https://openalex.org/W3009238340","https://openalex.org/W2939353110","https://openalex.org/W4321369474","https://openalex.org/W4360585206","https://openalex.org/W4285208911","https://openalex.org/W3082895349","https://openalex.org/W4213079790","https://openalex.org/W2248239756"],"abstract_inverted_index":{"Multi-channel":[0],"speech":[1,25,53,129],"enhancement":[2,46,95,130],"with":[3,65,123],"ad-hoc":[4],"sensors":[5],"has":[6],"been":[7],"a":[8,76,109,127],"challenging":[9],"task.":[10],"Speech":[11],"model":[12],"guided":[13],"beamforming":[14,110],"algorithms":[15],"are":[16,48,61,121],"able":[17,49,143],"to":[18,28,50,63,112,144],"recover":[19],"natural":[20,114,149],"sounding":[21,115,150],"speech,":[22,116,151],"but":[23,59,117],"the":[24,32,40,82,101,118,124],"models":[26],"tend":[27],"be":[29,36],"oversimplified":[30],"or":[31],"inference":[33],"would":[34],"otherwise":[35],"too":[37],"complicated.":[38],"On":[39],"other":[41],"hand,":[42],"deep":[43,72],"learning":[44,73],"based":[45],"approaches":[47,74],"learn":[51],"complicated":[52],"distributions":[54],"and":[55,88,136,148,152],"perform":[56],"efficient":[57],"inference,":[58],"they":[60],"unable":[62],"deal":[64],"variable":[66],"number":[67],"of":[68,78,84,105,126],"input":[69],"channels.":[70],"Also,":[71],"introduce":[75],"lot":[77],"errors,":[79],"particularly":[80],"in":[81],"presence":[83],"unseen":[85,156],"noise":[86],"types":[87],"settings.":[89],"We":[90],"have":[91],"therefore":[92],"proposed":[93],"an":[94],"framework":[96],"called":[97],"DEEPBEAM,":[98],"which":[99],"combines":[100],"two":[102],"complementary":[103],"classes":[104],"algorithms.":[106],"DEEPBEAM":[107,141],"introduces":[108],"filter":[111,119],"produce":[113,145],"coefficients":[120],"determined":[122],"help":[125],"monaural":[128],"neural":[131],"network.":[132],"Experiments":[133],"on":[134],"synthetic":[135],"real-world":[137],"data":[138],"show":[139],"that":[140],"is":[142,153],"clean,":[146],"dry":[147],"robust":[154],"against":[155],"noise.":[157]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}