{"id":"https://openalex.org/W4375869228","doi":"https://doi.org/10.1109/icassp49357.2023.10096974","title":"Deep Neural Mel-Subband Beamformer for in-Car Speech Separation","display_name":"Deep Neural Mel-Subband Beamformer for in-Car Speech Separation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869228","doi":"https://doi.org/10.1109/icassp49357.2023.10096974"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096974","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096974","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5047630225","display_name":"Vinay Kothapally","orcid":"https://orcid.org/0000-0002-2111-3333"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Vinay Kothapally","raw_affiliation_strings":["Tencent AI Lab,Bellevue,WA,USA","Tencent AI Lab, Bellevue, WA, USA"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Bellevue,WA,USA","institution_ids":["https://openalex.org/I4210108985"]},{"raw_affiliation_string":"Tencent AI Lab, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101467338","display_name":"Yong Xu","orcid":"https://orcid.org/0000-0003-4944-6890"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yong Xu","raw_affiliation_strings":["Tencent AI Lab,Bellevue,WA,USA","Tencent AI Lab, Bellevue, WA, USA"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Bellevue,WA,USA","institution_ids":["https://openalex.org/I4210108985"]},{"raw_affiliation_string":"Tencent AI Lab, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106407019","display_name":"Meng Yu","orcid":"https://orcid.org/0000-0002-0031-9156"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Meng Yu","raw_affiliation_strings":["Tencent AI Lab,Bellevue,WA,USA","Tencent AI Lab, Bellevue, WA, USA"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Bellevue,WA,USA","institution_ids":["https://openalex.org/I4210108985"]},{"raw_affiliation_string":"Tencent AI Lab, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101785327","display_name":"Shi-Xiong Zhang","orcid":"https://orcid.org/0009-0007-7803-2407"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shi-Xiong Zhang","raw_affiliation_strings":["Tencent AI Lab,Bellevue,WA,USA","Tencent AI Lab, Bellevue, WA, USA"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Bellevue,WA,USA","institution_ids":["https://openalex.org/I4210108985"]},{"raw_affiliation_string":"Tencent AI Lab, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"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/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab,Bellevue,WA,USA","Tencent AI Lab, Bellevue, WA, USA"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Bellevue,WA,USA","institution_ids":["https://openalex.org/I4210108985"]},{"raw_affiliation_string":"Tencent AI Lab, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5047630225"],"corresponding_institution_ids":["https://openalex.org/I4210108985"],"apc_list":null,"apc_paid":null,"fwci":1.6302,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.84137715,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"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":0.9976000189781189,"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"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":0.7212319374084473},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.6824464201927185},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6532083749771118},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.621179461479187},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.6084280014038086},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4901150166988373},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4834343194961548},{"id":"https://openalex.org/keywords/loudspeaker","display_name":"Loudspeaker","score":0.44167160987854004},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.44090530276298523},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.42320355772972107},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.41013067960739136},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33231931924819946},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3306216597557068},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2615174651145935},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.19253137707710266},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.18368959426879883},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1010698676109314}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7212319374084473},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.6824464201927185},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6532083749771118},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.621179461479187},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.6084280014038086},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4901150166988373},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4834343194961548},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.44167160987854004},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.44090530276298523},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.42320355772972107},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.41013067960739136},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33231931924819946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3306216597557068},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2615174651145935},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.19253137707710266},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.18368959426879883},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1010698676109314},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"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/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/icassp49357.2023.10096974","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096974","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2014857913","https://openalex.org/W2054634052","https://openalex.org/W2099648314","https://openalex.org/W2111880697","https://openalex.org/W2517616541","https://openalex.org/W2547916733","https://openalex.org/W2746626166","https://openalex.org/W2889048668","https://openalex.org/W2889411318","https://openalex.org/W2890553422","https://openalex.org/W2944972166","https://openalex.org/W2952218014","https://openalex.org/W2972992323","https://openalex.org/W2974407961","https://openalex.org/W2990433241","https://openalex.org/W3015791598","https://openalex.org/W3095913803","https://openalex.org/W3099330747","https://openalex.org/W3101330598","https://openalex.org/W3160394811","https://openalex.org/W3162341667","https://openalex.org/W3163591408","https://openalex.org/W3196360884","https://openalex.org/W3198680319","https://openalex.org/W3205567090","https://openalex.org/W3214359009","https://openalex.org/W3216920799","https://openalex.org/W4214921663","https://openalex.org/W4223583411","https://openalex.org/W4226066599","https://openalex.org/W4232282348","https://openalex.org/W4297841507","https://openalex.org/W4297841762","https://openalex.org/W4312792499","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6754473786","https://openalex.org/W6762182681","https://openalex.org/W6770796734","https://openalex.org/W6793006967","https://openalex.org/W6803813215"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2089240210","https://openalex.org/W2131486661","https://openalex.org/W2161396743","https://openalex.org/W2386453889","https://openalex.org/W3134790285","https://openalex.org/W2345063900"],"abstract_inverted_index":{"While":[0],"current":[1],"deep":[2],"learning":[3],"(DL)-based":[4],"beamforming":[5,106],"techniques":[6,160,201],"have":[7],"been":[8],"proved":[9],"effective":[10],"in":[11,26,52,114,161],"speech":[12,50,89,121,164],"separation,":[13],"they":[14],"are":[15,108],"often":[16],"designed":[17],"to":[18,48,65,152,198],"process":[19],"narrow-band":[20],"(NB)":[21],"frequencies":[22,86],"independently":[23],"which":[24,79],"results":[25],"higher":[27,98],"computational":[28],"costs":[29],"and":[30,60,94,122,131,156,166,175,191,194],"inference":[31,61],"times,":[32],"making":[33],"them":[34],"unsuitable":[35],"for":[36,84,97,110],"real-world":[37,176],"use.":[38],"In":[39,100],"this":[40],"paper,":[41],"we":[42,178],"propose":[43],"DL-based":[44],"mel-subband":[45],"spatio-temporal":[46],"beamformer":[47],"perform":[49],"separation":[51,186],"a":[53,73,81,101,115],"car":[54,116],"environment":[55],"with":[56],"reduced":[57],"computation":[58],"cost":[59],"time.":[62],"As":[63],"opposed":[64],"conventional":[66],"subband":[67,76,120],"(SB)":[68],"approaches,":[69],"our":[70,149,181],"framework":[71,128,151,183],"uses":[72],"mel-scale":[74],"based":[75],"selection":[77],"strategy":[78],"ensures":[80],"fine-grained":[82],"processing":[83,96,159,200],"lower":[85,204],"where":[87],"most":[88],"formant":[90],"structure":[91],"is":[92],"present,":[93],"coarse-grained":[95],"frequencies.":[99],"recursive":[102],"way,":[103],"robust":[104],"frame-level":[105],"weights":[107],"determined":[109],"each":[111],"speaker":[112],"location/zone":[113],"from":[117,135],"the":[118,136,140,146],"estimated":[119],"noise":[123],"covariance":[124],"matrices.":[125],"Furthermore,":[126],"proposed":[127,150,182],"also":[129],"estimates":[130],"suppresses":[132],"any":[133],"echoes":[134],"loudspeaker(s)":[137],"by":[138],"using":[139],"echo":[141],"reference":[142],"signals.":[143],"We":[144],"compare":[145],"performance":[147,187,196],"of":[148,163],"several":[153],"NB,":[154],"SB,":[155],"full-band":[157],"(FB)":[158],"terms":[162],"quality":[165],"recognition":[167],"metrics.":[168],"Based":[169],"on":[170,173],"experimental":[171],"evaluations":[172],"simulated":[174],"recordings,":[177],"find":[179],"that":[180],"achieves":[184,195],"better":[185],"over":[188],"all":[189],"SB":[190],"FB":[192],"approaches":[193],"closer":[197],"NB":[199],"while":[202],"requiring":[203],"computing":[205],"cost.":[206]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}