{"id":"https://openalex.org/W2891759647","doi":"https://doi.org/10.1109/access.2018.2870758","title":"Robust Beamforming for Speech Recognition Using DNN-Based Time-Frequency Masks Estimation","display_name":"Robust Beamforming for Speech Recognition Using DNN-Based Time-Frequency Masks Estimation","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2891759647","doi":"https://doi.org/10.1109/access.2018.2870758","mag":"2891759647"},"language":"en","primary_location":{"id":"doi:10.1109/access.2018.2870758","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2018.2870758","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2018.2870758","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101900435","display_name":"Wenbin Jiang","orcid":"https://orcid.org/0000-0002-4063-8952"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbin Jiang","raw_affiliation_strings":["Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4063-8952","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034251794","display_name":"Fei Wen","orcid":"https://orcid.org/0000-0002-3083-9611"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Wen","raw_affiliation_strings":["Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-3083-9611","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032986088","display_name":"Peilin Liu","orcid":"https://orcid.org/0000-0002-5321-2336"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peilin Liu","raw_affiliation_strings":["Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.829,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.86501988,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"6","issue":null,"first_page":"52385","last_page":"52392"},"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/T11309","display_name":"Music and Audio Processing","score":0.998199999332428,"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":0.9952999949455261,"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":0.7637944221496582},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.7414745688438416},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.7147412300109863},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6430132389068604},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5869663953781128},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5724046230316162},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5379700064659119},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5159559845924377},{"id":"https://openalex.org/keywords/covariance-matrix","display_name":"Covariance matrix","score":0.5055282115936279},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4111535847187042},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4070877730846405},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.29014480113983154},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.25968700647354126},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1640787124633789},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08464846014976501},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07522466778755188}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7637944221496582},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.7414745688438416},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.7147412300109863},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6430132389068604},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5869663953781128},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5724046230316162},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5379700064659119},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5159559845924377},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.5055282115936279},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4111535847187042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4070877730846405},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29014480113983154},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.25968700647354126},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1640787124633789},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08464846014976501},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07522466778755188},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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":2,"locations":[{"id":"doi:10.1109/access.2018.2870758","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2018.2870758","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:2a71146b10cf4b60b0176593e6bab8ee","is_oa":true,"landing_page_url":"https://doaj.org/article/2a71146b10cf4b60b0176593e6bab8ee","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 6, Pp 52385-52392 (2018)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2018.2870758","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2018.2870758","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5299999713897705}],"awards":[{"id":"https://openalex.org/G137382540","display_name":null,"funder_award_id":"61401501","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G316964183","display_name":"\u57fa\u4e8e\u975e\u51f8\u6b63\u5219\u5316\u7684\u9ad8\u7ef4\u534f\u65b9\u5dee\u77e9\u9635\u4f30\u8ba1\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61871265","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1495679096","https://openalex.org/W1516630152","https://openalex.org/W1524333225","https://openalex.org/W1533861849","https://openalex.org/W1544785557","https://openalex.org/W1836465849","https://openalex.org/W2043216213","https://openalex.org/W2069681747","https://openalex.org/W2091432990","https://openalex.org/W2094035326","https://openalex.org/W2095705004","https://openalex.org/W2099984896","https://openalex.org/W2127851351","https://openalex.org/W2141411743","https://openalex.org/W2141998673","https://openalex.org/W2143027228","https://openalex.org/W2144404214","https://openalex.org/W2148613904","https://openalex.org/W2158143227","https://openalex.org/W2168729028","https://openalex.org/W2170222430","https://openalex.org/W2271840356","https://openalex.org/W2289394825","https://openalex.org/W2291877678","https://openalex.org/W2398042854","https://openalex.org/W2398972335","https://openalex.org/W2400339399","https://openalex.org/W2408744528","https://openalex.org/W2517616541","https://openalex.org/W2621044834","https://openalex.org/W2640461821","https://openalex.org/W2962866211","https://openalex.org/W2964121744","https://openalex.org/W4253928870","https://openalex.org/W6631362777","https://openalex.org/W6638667902","https://openalex.org/W6661582794","https://openalex.org/W6674330103"],"related_works":["https://openalex.org/W2896203542","https://openalex.org/W201299990","https://openalex.org/W876328409","https://openalex.org/W4319068615","https://openalex.org/W1879255185","https://openalex.org/W2148473678","https://openalex.org/W3004719695","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W1980506188"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,20,32,36,44,72,76,85,89,107,114,123,135,140,143,146],"robust":[4,61],"beamforming":[5],"problem":[6],"for":[7,60],"speech":[8,38,116,157,160],"recognition":[9,161],"using":[10,23,93],"a":[11,24,65,98,102],"novel":[12],"time-frequency":[13,21],"mask":[14,22,67,82,100,104],"estimator.":[15],"The":[16,80],"beamformer":[17,45],"first":[18],"estimates":[19],"deep":[25],"neural":[26],"network":[27],"(DNN)":[28],"based":[29],"on":[30,127],"which":[31,69],"covariance":[33,57,111],"matrices":[34,112],"of":[35,75,88,113,155],"target":[37,115],"and":[39,101,117,139,159],"noise":[40,118],"are":[41,47],"computed.":[42],"Then,":[43],"coefficients":[46],"directly":[48],"obtained":[49,121],"via":[50],"generalized":[51],"eigenvector":[52],"decomposition.":[53],"To":[54],"achieve":[55],"accurate":[56,110],"matrix":[58],"estimation":[59],"beamforming,":[62],"we":[63],"propose":[64],"DNN-based":[66],"estimator":[68,83],"can":[70,119],"exploit":[71],"spatial":[73,86],"features":[74],"multi-channel":[77,94],"microphone":[78,90],"signals.":[79],"proposed":[81,147],"leverages":[84],"information":[87],"array":[91],"by":[92],"signals":[95],"to":[96],"estimate":[97],"speech-aware":[99],"noise-aware":[103],"simultaneously.":[105],"Using":[106],"target-specified":[108],"masks,":[109],"be":[120],"from":[122],"observation":[124],"independently.":[125],"Experiments":[126],"CHiME4":[128],"data":[129],"sets":[130],"demonstrate":[131],"that,":[132],"compared":[133],"with":[134],"baseline":[136],"toolkit":[137],"(BeamformIt)":[138],"winner":[141],"in":[142,153],"CHiME3":[144],"challenge,":[145],"method":[148],"achieves":[149],"better":[150],"results":[151],"both":[152],"terms":[154],"perceptual":[156],"quality":[158],"error":[162],"rate.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}