{"id":"https://openalex.org/W3209010693","doi":"https://doi.org/10.1109/icspcc52875.2021.9564817","title":"An Implementaion of the CNN-Based MVDR Beamforming For Speech Enhancement","display_name":"An Implementaion of the CNN-Based MVDR Beamforming For Speech Enhancement","publication_year":2021,"publication_date":"2021-08-17","ids":{"openalex":"https://openalex.org/W3209010693","doi":"https://doi.org/10.1109/icspcc52875.2021.9564817","mag":"3209010693"},"language":"en","primary_location":{"id":"doi:10.1109/icspcc52875.2021.9564817","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icspcc52875.2021.9564817","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)","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/A5101508034","display_name":"Yuchen Liang","orcid":"https://orcid.org/0000-0001-7128-3712"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchen Liang","raw_affiliation_strings":["Speech and Audio Signal Processing Laboratory, Faculty of Information Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Audio Signal Processing Laboratory, Faculty of Information Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070475244","display_name":"Changchun Bao","orcid":"https://orcid.org/0000-0002-5606-5343"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changchun Bao","raw_affiliation_strings":["Speech and Audio Signal Processing Laboratory, Faculty of Information Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Audio Signal Processing Laboratory, Faculty of Information Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104107032","display_name":"Jing Zhou","orcid":"https://orcid.org/0009-0004-6586-0762"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Zhou","raw_affiliation_strings":["Speech and Audio Signal Processing Laboratory, Faculty of Information Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Audio Signal Processing Laboratory, Faculty of Information Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I37796252"],"apc_list":null,"apc_paid":null,"fwci":0.3626,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.53257869,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9977999925613403,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9919999837875366,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7294847369194031},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.6925619840621948},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6845077276229858},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6693090796470642},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.6041473746299744},{"id":"https://openalex.org/keywords/covariance-matrix","display_name":"Covariance matrix","score":0.5512052774429321},{"id":"https://openalex.org/keywords/minimum-variance-unbiased-estimator","display_name":"Minimum-variance unbiased estimator","score":0.5314886569976807},{"id":"https://openalex.org/keywords/minimum-mean-square-error","display_name":"Minimum mean square error","score":0.46729376912117004},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.461318701505661},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.4582892656326294},{"id":"https://openalex.org/keywords/direction-of-arrival","display_name":"Direction of arrival","score":0.45651623606681824},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3389522433280945},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32312434911727905},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2561717629432678},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2078128457069397},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.18392258882522583},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.14481189846992493},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12924647331237793},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1195426881313324}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7294847369194031},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.6925619840621948},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6845077276229858},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6693090796470642},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.6041473746299744},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.5512052774429321},{"id":"https://openalex.org/C165646398","wikidata":"https://www.wikidata.org/wiki/Q3755281","display_name":"Minimum-variance unbiased estimator","level":3,"score":0.5314886569976807},{"id":"https://openalex.org/C90652560","wikidata":"https://www.wikidata.org/wiki/Q11091747","display_name":"Minimum mean square error","level":3,"score":0.46729376912117004},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.461318701505661},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.4582892656326294},{"id":"https://openalex.org/C172051844","wikidata":"https://www.wikidata.org/wiki/Q5280438","display_name":"Direction of arrival","level":3,"score":0.45651623606681824},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3389522433280945},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32312434911727905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2561717629432678},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2078128457069397},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.18392258882522583},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.14481189846992493},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12924647331237793},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1195426881313324},{"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/C21822782","wikidata":"https://www.wikidata.org/wiki/Q131214","display_name":"Antenna (radio)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icspcc52875.2021.9564817","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icspcc52875.2021.9564817","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G3909335432","display_name":"\u590d\u6742\u573a\u666f\u58f0\u4fe1\u53f7\u83b7\u53d6\u548c\u8bc6\u522b\u57fa\u7840\u7406\u8bba\u4e0e\u65b9\u6cd5\u7814\u7a76: \u591a\u901a\u9053\u58f0\u4fe1\u53f7\u83b7\u53d6\u3001\u4f20\u8f93\u4e0e\u91cd\u6784","funder_award_id":"61831019","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1495679096","https://openalex.org/W1885823700","https://openalex.org/W1968939597","https://openalex.org/W1999846783","https://openalex.org/W2066218102","https://openalex.org/W2072128103","https://openalex.org/W2128653836","https://openalex.org/W2130432819","https://openalex.org/W2144244295","https://openalex.org/W2168729028","https://openalex.org/W2541431757","https://openalex.org/W2714487941","https://openalex.org/W2900381824","https://openalex.org/W2914926710","https://openalex.org/W2991015288","https://openalex.org/W3007541473","https://openalex.org/W3030781580","https://openalex.org/W4247773827","https://openalex.org/W4253928870","https://openalex.org/W6729100659"],"related_works":["https://openalex.org/W2361247493","https://openalex.org/W2157330024","https://openalex.org/W2380771148","https://openalex.org/W2008532365","https://openalex.org/W2952979007","https://openalex.org/W1998374630","https://openalex.org/W2348931051","https://openalex.org/W2109356272","https://openalex.org/W2132495960","https://openalex.org/W2528250906"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1,25],"is":[2,57,71,87,116,135,146,157],"a":[3,12,39,141],"challenge":[4],"that":[5,164],"has":[6,43],"not":[7],"been":[8,44],"well":[9],"solved":[10],"for":[11],"long":[13],"time.":[14],"The":[15,160],"current":[16],"research":[17],"attempts":[18],"to":[19,59,73,117,148],"improve":[20],"the":[21,30,52,61,78,81,84,99,110,113,119,125,132,138,153,165,173],"performance":[22,41,174],"of":[23,65,93,97,101,107,175],"speech":[24,67,127,144,151],"by":[26],"microphone":[27,142],"array,":[28],"where":[29],"minimum":[31],"variance":[32],"and":[33,42,47,68,128,131,152],"distortionless":[34],"response":[35],"(MVDR)":[36],"beamformer":[37],"shows":[38],"good":[40],"widely":[45],"studied":[46],"applied.":[48],"In":[49,109],"this":[50],"paper,":[51],"convolutional":[53],"neural":[54],"network":[55,111],"(CNN)":[56],"used":[58,147],"estimate":[60],"time-frequency":[62],"(T-F)":[63],"masking":[64],"target":[66],"noise,":[69],"which":[70],"intended":[72],"obtain":[74],"covariance":[75,94],"matrix":[76],"in":[77],"MVDR.":[79],"On":[80],"other":[82],"hand,":[83],"steering":[85],"vector":[86],"estimated":[88],"through":[89],"main":[90],"feature":[91],"pattern":[92],"matrix,":[95],"instead":[96],"estimating":[98],"direction":[100],"arrival":[102],"angle":[103],"or":[104],"time":[105],"difference":[106],"arrival.":[108],"training,":[112],"training":[114],"goal":[115],"minimize":[118],"mean":[120],"square":[121],"error":[122],"(MSE)":[123],"between":[124],"enhanced":[126],"real":[129],"speech,":[130],"loss":[133],"function":[134],"constructed":[136],"with":[137],"MSE.":[139],"Finally,":[140],"array":[143],"simulator":[145],"generate":[149],"multi-channel":[150],"related":[154],"simulation":[155],"experiment":[156],"carried":[158],"out.":[159],"experimental":[161],"results":[162],"show":[163],"CNN":[166],"-based":[167],"MVDR":[168],"Beamforming":[169],"method":[170],"really":[171],"improved":[172],"general":[176],"MVDR-based":[177],"beamformer.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}