{"id":"https://openalex.org/W2714487941","doi":"https://doi.org/10.1109/icassp.2017.7952756","title":"On time-frequency mask estimation for MVDR beamforming with application in robust speech recognition","display_name":"On time-frequency mask estimation for MVDR beamforming with application in robust speech recognition","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2714487941","doi":"https://doi.org/10.1109/icassp.2017.7952756","mag":"2714487941"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7952756","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952756","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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/A5101602536","display_name":"Xiong Xiao","orcid":"https://orcid.org/0009-0001-5128-6518"},"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":["Temasek Laboratories, Nanyang Technological University (NTU), Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Temasek Laboratories, Nanyang Technological University (NTU), Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103758307","display_name":"Shengkui Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108443","display_name":"Advanced Digital Sciences Center","ror":"https://ror.org/01xaqx887","country_code":"SG","type":"facility","lineage":["https://openalex.org/I4210108443"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shengkui Zhao","raw_affiliation_strings":["Advanced Digital Sciences Center, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Digital Sciences Center, Singapore","institution_ids":["https://openalex.org/I4210108443"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105462806","display_name":"Douglas L. Jones","orcid":"https://orcid.org/0000-0002-7817-7629"},"institutions":[{"id":"https://openalex.org/I4210108443","display_name":"Advanced Digital Sciences Center","ror":"https://ror.org/01xaqx887","country_code":"SG","type":"facility","lineage":["https://openalex.org/I4210108443"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Douglas L. Jones","raw_affiliation_strings":["Advanced Digital Sciences Center, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Digital Sciences Center, Singapore","institution_ids":["https://openalex.org/I4210108443"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"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":"Eng Siong Chng","raw_affiliation_strings":["Temasek Laboratories, Nanyang Technological University (NTU), Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Temasek Laboratories, Nanyang Technological University (NTU), Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"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":"Haizhou Li","raw_affiliation_strings":["Department of ECE, National University of Singapore, Singapore","School of Computer Science and Engineering, NTU, Singapore","Temasek Laboratories, Nanyang Technological University (NTU), Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of ECE, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"School of Computer Science and Engineering, NTU, Singapore","institution_ids":[]},{"raw_affiliation_string":"Temasek Laboratories, Nanyang Technological University (NTU), Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"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":96,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3246","last_page":"3250"},"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":0.9983999729156494,"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":0.9983000159263611,"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/computer-science","display_name":"Computer science","score":0.8051112294197083},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.7639185190200806},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7116237282752991},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5271819829940796},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.49048087000846863},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4899241328239441},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.4573909044265747},{"id":"https://openalex.org/keywords/minimum-variance-unbiased-estimator","display_name":"Minimum-variance unbiased estimator","score":0.42346712946891785},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.42233550548553467},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39366841316223145},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3925705850124359},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.20392447710037231},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1711997091770172},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10717460513114929},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10464990139007568},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07140415906906128}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8051112294197083},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.7639185190200806},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7116237282752991},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5271819829940796},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.49048087000846863},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4899241328239441},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.4573909044265747},{"id":"https://openalex.org/C165646398","wikidata":"https://www.wikidata.org/wiki/Q3755281","display_name":"Minimum-variance unbiased estimator","level":3,"score":0.42346712946891785},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.42233550548553467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39366841316223145},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3925705850124359},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.20392447710037231},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1711997091770172},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10717460513114929},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10464990139007568},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07140415906906128},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7952756","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952756","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1989314204","https://openalex.org/W2003203076","https://openalex.org/W2060108923","https://openalex.org/W2066218102","https://openalex.org/W2101609516","https://openalex.org/W2112469598","https://openalex.org/W2125336414","https://openalex.org/W2148613904","https://openalex.org/W2160815625","https://openalex.org/W2168729028","https://openalex.org/W2184045248","https://openalex.org/W2288645994","https://openalex.org/W2289394825","https://openalex.org/W2289480995","https://openalex.org/W2289731793","https://openalex.org/W2290075840","https://openalex.org/W2398042854","https://openalex.org/W2398972335","https://openalex.org/W2517616541","https://openalex.org/W2559260703","https://openalex.org/W2577993889","https://openalex.org/W6678809451","https://openalex.org/W6743356167"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W2769861442","https://openalex.org/W2120442551","https://openalex.org/W1980506188","https://openalex.org/W2380771148","https://openalex.org/W2396048001","https://openalex.org/W4240587264","https://openalex.org/W2348931051","https://openalex.org/W2011788874","https://openalex.org/W2109356272"],"abstract_inverted_index":{"Acoustic":[0],"beamforming":[1,59],"has":[2],"played":[3],"a":[4,145],"key":[5],"role":[6],"in":[7,60],"the":[8,18,31,46,49,54,57,69,83,87,94,98,110,122,129,133,162],"robust":[9],"automatic":[10],"speech":[11,19,88],"recognition":[12],"(ASR)":[13],"applications.":[14],"Accurate":[15],"estimates":[16],"of":[17,40,48,56,149],"and":[20,51,89,103,119,137],"noise":[21,90],"spatial":[22],"covariance":[23],"matrices":[24],"(SCM)":[25],"are":[26,116],"crucial":[27],"for":[28],"successfully":[29],"applying":[30],"minimum":[32],"variance":[33],"distortionless":[34],"response":[35],"(MVDR)":[36],"beamforming.":[37],"Reliable":[38],"estimation":[39,47,72],"time-frequency":[41],"(TF)":[42],"masks":[43,91],"can":[44],"improve":[45,53,109,132],"SCMs":[50],"significantly":[52],"performance":[55,135,143],"MVDR":[58,164],"ASR":[61,99,134],"tasks.":[62],"In":[63],"this":[64],"paper,":[65],"we":[66],"focus":[67],"on":[68,121],"TF":[70],"mask":[71,111],"using":[73],"recurrent":[74],"neural":[75],"networks":[76],"(RNN).":[77],"Specifically,":[78],"our":[79],"methods":[80,115,131],"include":[81],"training":[82,93],"RNN":[84,95],"to":[85,96,107],"estimate":[86],"independently,":[92],"minimize":[97],"cost":[100],"function":[101],"directly,":[102],"performing":[104],"multiple":[105],"passes":[106],"iteratively":[108],"estimation.":[112],"The":[113,125,141],"proposed":[114,130],"evaluated":[117],"individually":[118,136],"overally":[120],"CHiME-4":[123],"challenge.":[124],"results":[126],"show":[127],"that":[128],"also":[138],"work":[139],"complementarily.":[140],"overall":[142],"achieves":[144],"word":[146],"error":[147],"rate":[148],"8.9%":[150],"with":[151,161],"6-microphone":[152],"configuration,":[153],"which":[154],"is":[155],"much":[156],"better":[157],"than":[158],"12.0%":[159],"achieved":[160],"state-of-the-art":[163],"implementation.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":17},{"year":2017,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}