{"id":"https://openalex.org/W3151596526","doi":"https://doi.org/10.1109/slt48900.2021.9383522","title":"Sequential Multi-Frame Neural Beamforming for Speech Separation and Enhancement","display_name":"Sequential Multi-Frame Neural Beamforming for Speech Separation and Enhancement","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3151596526","doi":"https://doi.org/10.1109/slt48900.2021.9383522","mag":"3151596526"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383522","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383522","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"article","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/A5101607498","display_name":"Zhong-Qiu Wang","orcid":"https://orcid.org/0000-0002-4204-9430"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhong-Qiu Wang","raw_affiliation_strings":["Google Research, Cambridge, MA","MERL, Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"Google Research, Cambridge, MA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"MERL, Cambridge, MA","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/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hakan Erdogan","raw_affiliation_strings":["Google Research, Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"Google Research, Cambridge, MA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053447215","display_name":"Scott Wisdom","orcid":"https://orcid.org/0000-0001-6671-1428"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Wisdom","raw_affiliation_strings":["Google Research, Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"Google Research, Cambridge, MA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087313939","display_name":"Kevin Wilson","orcid":"https://orcid.org/0000-0001-9141-2219"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Wilson","raw_affiliation_strings":["Google Research, Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"Google Research, Cambridge, MA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004777817","display_name":"Desh Raj","orcid":"https://orcid.org/0000-0002-5038-9400"},"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":"Desh Raj","raw_affiliation_strings":["Johns Hopkins University, Baltimore, MD"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"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":"Shinji Watanabe","raw_affiliation_strings":["Johns Hopkins University, Baltimore, MD"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345092","display_name":"Zhuo Chen","orcid":"https://orcid.org/0000-0002-9011-7928"},"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":"Zhuo Chen","raw_affiliation_strings":["Microsoft, Seattle, WA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Seattle, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112763337","display_name":"John R. Hershey","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John R. Hershey","raw_affiliation_strings":["Google Research, Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"Google Research, Cambridge, MA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5101607498"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":5.7096,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.96894867,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"905","last_page":"911"},"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":0.9988999962806702,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.998199999332428,"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/beamforming","display_name":"Beamforming","score":0.7913868427276611},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6665620803833008},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5428592562675476},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5295658707618713},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.47748538851737976},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45132720470428467},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.44368281960487366},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43130651116371155},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40725284814834595},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.366781085729599},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.3651670217514038},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24165433645248413},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08584961295127869}],"concepts":[{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.7913868427276611},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6665620803833008},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5428592562675476},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5295658707618713},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.47748538851737976},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45132720470428467},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.44368281960487366},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43130651116371155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40725284814834595},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.366781085729599},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3651670217514038},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24165433645248413},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08584961295127869},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt48900.2021.9383522","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383522","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W2037117129","https://openalex.org/W2095933505","https://openalex.org/W2127851351","https://openalex.org/W2143027228","https://openalex.org/W2168729028","https://openalex.org/W2172491908","https://openalex.org/W2289480995","https://openalex.org/W2398042854","https://openalex.org/W2400339399","https://openalex.org/W2517616541","https://openalex.org/W2559809918","https://openalex.org/W2593116425","https://openalex.org/W2718052359","https://openalex.org/W2803322398","https://openalex.org/W2803583024","https://openalex.org/W2891833136","https://openalex.org/W2892163332","https://openalex.org/W2900893004","https://openalex.org/W2901243971","https://openalex.org/W2905402910","https://openalex.org/W2909607850","https://openalex.org/W2923728956","https://openalex.org/W2938386503","https://openalex.org/W2939246703","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2963189033","https://openalex.org/W2963317762","https://openalex.org/W2963382687","https://openalex.org/W2972359262","https://openalex.org/W2973062255","https://openalex.org/W2995181338","https://openalex.org/W2998657200","https://openalex.org/W3003231992","https://openalex.org/W3016232124","https://openalex.org/W3016400019","https://openalex.org/W3020336359","https://openalex.org/W3094831814","https://openalex.org/W3098052090","https://openalex.org/W3099330747","https://openalex.org/W3121132363","https://openalex.org/W3123318516","https://openalex.org/W4289665794","https://openalex.org/W4297752165","https://openalex.org/W6630442970","https://openalex.org/W6756579876","https://openalex.org/W6784900337"],"related_works":["https://openalex.org/W2963170046","https://openalex.org/W2376244802","https://openalex.org/W4311414679","https://openalex.org/W2923631784","https://openalex.org/W818226659","https://openalex.org/W2158075901","https://openalex.org/W2567141277","https://openalex.org/W3124036039","https://openalex.org/W2130785056","https://openalex.org/W2727286692"],"abstract_inverted_index":{"This":[0],"work":[1],"introduces":[2],"sequential":[3],"neural":[4,9,20,118],"beamforming,":[5,39],"which":[6,78],"alternates":[7],"between":[8],"network":[10],"based":[11,16,189],"spectral":[12],"separation":[13,23,119,155,162],"and":[14,59,94,103,120,126,138,154,176],"beamforming":[15,76,89,124],"spatial":[17,52,62,123],"separation.":[18],"Our":[19,110],"networks":[21],"for":[22,107],"use":[24,159],"an":[25,128],"advanced":[26],"convolutional":[27],"architecture":[28],"trained":[29],"with":[30],"a":[31,55,60,74,114,143,178,186],"novel":[32],"stabilized":[33],"signal-to-noise":[34,136],"ratio":[35,137],"loss":[36],"function.":[37],"For":[38],"we":[40,72],"explore":[41],"multiple":[42],"ways":[43],"of":[44,98,116,131],"computing":[45],"time-varying":[46,56],"covariance":[47,53],"matrices,":[48],"including":[49],"factorizing":[50],"the":[51,80,88,96,169],"into":[54,173],"amplitude":[57],"component":[58],"time-invariant":[61,122],"component,":[63],"as":[64,66,183],"well":[65],"using":[67],"block-based":[68],"techniques.":[69],"In":[70],"addition,":[71],"introduce":[73],"multi-frame":[75,104,121],"method":[77,112],"improves":[79],"results":[81],"significantly":[82],"by":[83],"adding":[84],"contextual":[85],"frames":[86],"to":[87,164,185],"formulations.":[90],"We":[91,157],"extensively":[92],"evaluate":[93],"analyze":[95],"effects":[97],"window":[99],"size,":[100,102],"block":[101],"context":[105],"size":[106],"these":[108],"methods.":[109],"best":[111],"utilizes":[113],"sequence":[115],"three":[117],"stages,":[125],"demonstrates":[127],"average":[129],"improvement":[130],"2.75":[132],"dB":[133],"in":[134,142,168],"scale-invariant":[135],"14.2%":[139],"absolute":[140],"reduction":[141],"comparative":[144],"speech":[145,152],"recognition":[146],"metric":[147],"across":[148],"four":[149],"challenging":[150],"reverberant":[151],"enhancement":[153],"tasks.":[156],"also":[158],"our":[160],"three-speaker":[161],"model":[163],"separate":[165],"real":[166],"recordings":[167],"LibriCSS":[170],"evaluation":[171],"set":[172],"non-overlapping":[174],"tracks,":[175],"achieve":[177],"better":[179],"word":[180],"error":[181],"rate":[182],"compared":[184],"baseline":[187],"mask":[188],"beamformer.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":3}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}