{"id":"https://openalex.org/W2398972335","doi":"https://doi.org/10.1109/icassp.2016.7472778","title":"Deep beamforming networks for multi-channel speech recognition","display_name":"Deep beamforming networks for multi-channel speech recognition","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2398972335","doi":"https://doi.org/10.1109/icassp.2016.7472778","mag":"2398972335"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472778","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472778","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/20.500.11820/bee88512-f139-4fd9-bab3-8143d5cfd0f3","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057945477","display_name":"Xiong Xiao","orcid":"https://orcid.org/0000-0003-4471-7946"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiong Xiao","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["MERL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MERL, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065994318","display_name":"Hakan Erdo\u011fan","orcid":"https://orcid.org/0000-0003-3140-8642"},"institutions":[{"id":"https://openalex.org/I134235054","display_name":"Sabanc\u0131 \u00dcniversitesi","ror":"https://ror.org/049asqa32","country_code":"TR","type":"education","lineage":["https://openalex.org/I134235054"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Hakan Erdogan","raw_affiliation_strings":["Sabanci University, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sabanci University, Turkey","institution_ids":["https://openalex.org/I134235054"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101607148","display_name":"Liang Lu","orcid":"https://orcid.org/0000-0003-4005-679X"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Liang Lu","raw_affiliation_strings":["University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112763337","display_name":"John R. Hershey","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John Hershey","raw_affiliation_strings":["MERL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MERL, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041313589","display_name":"Michael L. Seltzer","orcid":"https://orcid.org/0000-0003-3474-2451"},"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":"Michael L. Seltzer","raw_affiliation_strings":["Microsoft Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081371370","display_name":"Guoguo Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guoguo Chen","raw_affiliation_strings":["Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433648","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0002-9505-1833"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["MIT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043596676","display_name":"Michael Mandel","orcid":null},"institutions":[{"id":"https://openalex.org/I83041322","display_name":"Brooklyn College","ror":"https://ror.org/019k4jq75","country_code":"US","type":"education","lineage":["https://openalex.org/I83041322"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Mandel","raw_affiliation_strings":["Brooklyn College, CUNY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brooklyn College, CUNY, USA","institution_ids":["https://openalex.org/I83041322"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"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":"Dong Yu","raw_affiliation_strings":["Microsoft Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":204,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"2016","issue":null,"first_page":"5745","last_page":"5749"},"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":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.7754061222076416},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7743728160858154},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.716187596321106},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5612695217132568},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5234983563423157},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5067234635353088},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.5042716264724731},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.502145528793335},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.4615687429904938},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4610430896282196},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4449743330478668},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4414162337779999},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.4300786256790161},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.42041927576065063},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4180668592453003},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.39749136567115784},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3907521069049835},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.18392562866210938},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.18254831433296204},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.14166757464408875}],"concepts":[{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.7754061222076416},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7743728160858154},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.716187596321106},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5612695217132568},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5234983563423157},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5067234635353088},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.5042716264724731},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.502145528793335},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.4615687429904938},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4610430896282196},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4449743330478668},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4414162337779999},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.4300786256790161},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.42041927576065063},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4180668592453003},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.39749136567115784},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3907521069049835},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.18392562866210938},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.18254831433296204},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.14166757464408875},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp.2016.7472778","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472778","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/bee88512-f139-4fd9-bab3-8143d5cfd0f3","is_oa":true,"landing_page_url":null,"pdf_url":"http://hdl.handle.net/20.500.11820/bee88512-f139-4fd9-bab3-8143d5cfd0f3","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:pure.ed.ac.uk:publications/bee88512-f139-4fd9-bab3-8143d5cfd0f3","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/bee88512-f139-4fd9-bab3-8143d5cfd0f3","pdf_url":"http://hdl.handle.net/20.500.11820/bee88512-f139-4fd9-bab3-8143d5cfd0f3","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Xiao, X, Watanabe, S, Erdogan, H, Lu, L, Hershey, J, Seltzer, M L, Chen, G, Zhang, Y, Mandel, M & Yu, D 2016, Deep Beamforming Networks for Multi-channel Speech Recognition. in 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, pp. 5745 - 5749, 41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016, Shanghai, China, 20/03/16. https://doi.org/10.1109/ICASSP.2016.7472778","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/bee88512-f139-4fd9-bab3-8143d5cfd0f3","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/bee88512-f139-4fd9-bab3-8143d5cfd0f3","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Xiao, X, Watanabe, S, Erdogan, H, Lu, L, Hershey, J, Seltzer, M L, Chen, G, Zhang, Y, Mandel, M & Yu, D 2016, Deep Beamforming Networks for Multi-channel Speech Recognition. in 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, pp. 5745 - 5749, 41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016, Shanghai, China, 20/03/16. https://doi.org/10.1109/ICASSP.2016.7472778","raw_type":"contributionToPeriodical"},{"id":"mag:2749912134","is_oa":false,"landing_page_url":"http://jglobal.jst.go.jp/en/public/20090422/201602236498513586","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/bee88512-f139-4fd9-bab3-8143d5cfd0f3","is_oa":true,"landing_page_url":null,"pdf_url":"http://hdl.handle.net/20.500.11820/bee88512-f139-4fd9-bab3-8143d5cfd0f3","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},"sustainable_development_goals":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2398972335.pdf"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W102482883","https://openalex.org/W1524333225","https://openalex.org/W1542280630","https://openalex.org/W1603075283","https://openalex.org/W1935589317","https://openalex.org/W1985368711","https://openalex.org/W1989314204","https://openalex.org/W2005679925","https://openalex.org/W2037769258","https://openalex.org/W2046317813","https://openalex.org/W2061074721","https://openalex.org/W2101045344","https://openalex.org/W2103088716","https://openalex.org/W2117678320","https://openalex.org/W2126149694","https://openalex.org/W2130361043","https://openalex.org/W2130722890","https://openalex.org/W2131342762","https://openalex.org/W2143612262","https://openalex.org/W2148613904","https://openalex.org/W2153773386","https://openalex.org/W2160815625","https://openalex.org/W2181607856","https://openalex.org/W2289912446","https://openalex.org/W3141933106","https://openalex.org/W4206633762","https://openalex.org/W6631362777","https://openalex.org/W6679429981","https://openalex.org/W6686045668"],"related_works":["https://openalex.org/W4389082013","https://openalex.org/W2380771148","https://openalex.org/W2348931051","https://openalex.org/W2109356272","https://openalex.org/W2120771489","https://openalex.org/W2389562147","https://openalex.org/W2538903081","https://openalex.org/W4386746628","https://openalex.org/W2390706155","https://openalex.org/W2955597484"],"abstract_inverted_index":{"Despite":[0],"the":[1,39,47,85,95,127,147],"significant":[2],"progress":[3],"in":[4,15,38],"speech":[5,25,41],"recognition":[6,26],"enabled":[7],"by":[8,77,154],"deep":[9],"neural":[10],"networks,":[11],"poor":[12],"performance":[13],"persists":[14],"some":[16],"scenarios.":[17],"In":[18,144],"this":[19,109],"work,":[20],"we":[21,151],"focus":[22],"on":[23,81,146],"far-field":[24],"which":[27],"remains":[28],"challenging":[29],"due":[30],"to":[31,45,94,98,113,181],"high":[32],"levels":[33],"of":[34,49,62,70,125,166,185],"noise":[35],"and":[36,56,111,129],"reverberation":[37],"captured":[40],"signals.":[42],"We":[43],"propose":[44],"represent":[46],"stages":[48],"acoustic":[50,57,119,130],"processing":[51,187],"including":[52],"beamforming,":[53],"feature":[54],"extraction,":[55],"modeling,":[58],"as":[59],"three":[60],"components":[61],"a":[63,71,78,114,139,159,173,182],"single":[64],"unified":[65],"computational":[66],"network.":[67],"The":[68,123,169],"parameters":[69,124],"frequency-domain":[72],"beam-former":[73],"are":[74,91,105,133],"first":[75],"estimated":[76],"network":[79,116],"based":[80],"features":[82,104],"derived":[83],"from":[84,108],"microphone":[86],"channels.":[87],"These":[88],"filter":[89],"coefficients":[90],"then":[92,106],"applied":[93],"array":[96],"signals":[97],"form":[99],"an":[100],"enhanced":[101],"signal.":[102],"Conventional":[103],"extracted":[107],"signal":[110],"passed":[112],"second":[115],"that":[117],"performs":[118],"modeling":[120,131],"for":[121],"classification.":[122],"both":[126,167],"beamforming":[128],"networks":[132],"trained":[134],"jointly":[135],"using":[136],"back-propagation":[137],"with":[138,158],"common":[140],"cross-entropy":[141],"objective":[142,161],"function.":[143],"experiments":[145],"AMI":[148],"meeting":[149],"corpus,":[150],"observed":[152],"improvements":[153],"pre-training":[155],"each":[156],"sub-network":[157],"network-specific":[160],"function":[162],"before":[163],"joint":[164],"training":[165],"networks.":[168],"proposed":[170],"method":[171],"obtained":[172],"3.2%":[174],"absolute":[175],"word":[176],"error":[177],"rate":[178],"reduction":[179],"compared":[180],"conventional":[183],"pipeline":[184],"independent":[186],"stages.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":24},{"year":2021,"cited_by_count":27},{"year":2020,"cited_by_count":29},{"year":2019,"cited_by_count":27},{"year":2018,"cited_by_count":25},{"year":2017,"cited_by_count":23},{"year":2016,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}