{"id":"https://openalex.org/W3209472002","doi":"https://doi.org/10.1109/icassp43922.2022.9746704","title":"Multichannel Speech Enhancement Without Beamforming","display_name":"Multichannel Speech Enhancement Without Beamforming","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3209472002","doi":"https://doi.org/10.1109/icassp43922.2022.9746704","mag":"3209472002"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746704","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5050492887","display_name":"Ashutosh Pandey","orcid":"https://orcid.org/0000-0002-3352-7453"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashutosh Pandey","raw_affiliation_strings":["Facebook Reality Labs Research,USA","Facebook Reality Labs Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook Reality Labs Research,USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook Reality Labs Research, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040562171","display_name":"Buye Xu","orcid":"https://orcid.org/0000-0002-3027-7567"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Buye Xu","raw_affiliation_strings":["Facebook Reality Labs Research,USA","Facebook Reality Labs Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook Reality Labs Research,USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook Reality Labs Research, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080751032","display_name":"Anurag Kumar","orcid":"https://orcid.org/0000-0002-1164-144X"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anurag Kumar","raw_affiliation_strings":["Facebook Reality Labs Research,USA","Facebook Reality Labs Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook Reality Labs Research,USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook Reality Labs Research, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055065049","display_name":"Jacob Donley","orcid":"https://orcid.org/0000-0002-8401-798X"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacob Donley","raw_affiliation_strings":["Facebook Reality Labs Research,USA","Facebook Reality Labs Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook Reality Labs Research,USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook Reality Labs Research, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004601228","display_name":"Paul Calamia","orcid":"https://orcid.org/0000-0002-0401-6996"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul Calamia","raw_affiliation_strings":["Facebook Reality Labs Research,USA","Facebook Reality Labs Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook Reality Labs Research,USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook Reality Labs Research, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["The Ohio State University,Department of Computer Science and Engineering,USA","Department of Computer Science and Engineering, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University,Department of Computer Science and Engineering,USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1787,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.90116462,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6502","last_page":"6506"},"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":0.9976000189781189,"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":0.996999979019165,"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":0.7650272250175476},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6488462686538696},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6025456190109253},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.5855534672737122},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.5061978697776794},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5052588582038879},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.48749470710754395},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4561119079589844},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.42927467823028564},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3796052038669586},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.10251912474632263},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08122411370277405},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07536083459854126},{"id":"https://openalex.org/keywords/radar","display_name":"Radar","score":0.07290926575660706}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7650272250175476},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6488462686538696},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6025456190109253},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.5855534672737122},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.5061978697776794},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5052588582038879},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.48749470710754395},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4561119079589844},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.42927467823028564},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3796052038669586},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.10251912474632263},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08122411370277405},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07536083459854126},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.07290926575660706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746704","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1509088290","https://openalex.org/W1552314771","https://openalex.org/W2061074721","https://openalex.org/W2130722890","https://openalex.org/W2141998673","https://openalex.org/W2242685705","https://openalex.org/W2398042854","https://openalex.org/W2517616541","https://openalex.org/W2568308529","https://openalex.org/W2889411318","https://openalex.org/W2892163332","https://openalex.org/W2900893004","https://openalex.org/W2962866211","https://openalex.org/W3007256793","https://openalex.org/W3015372568","https://openalex.org/W3015679215","https://openalex.org/W3015791598","https://openalex.org/W3030102521","https://openalex.org/W3032514799","https://openalex.org/W3097906045","https://openalex.org/W3134695619","https://openalex.org/W3162341667","https://openalex.org/W3163591408","https://openalex.org/W3171278394","https://openalex.org/W3205004157","https://openalex.org/W3209317203","https://openalex.org/W6630309668","https://openalex.org/W6756579876","https://openalex.org/W6802684955","https://openalex.org/W6802884974"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W2011227383","https://openalex.org/W4375868962","https://openalex.org/W2088854863","https://openalex.org/W1976719989","https://openalex.org/W2942893872","https://openalex.org/W2065606036","https://openalex.org/W3179495260","https://openalex.org/W3127543252","https://openalex.org/W2016904525"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"are":[3],"often":[4],"coupled":[5],"with":[6,31,98,149],"traditional":[7,33,63,153],"spatial":[8,17],"filters,":[9],"such":[10],"as":[11],"MVDR":[12],"beamformers":[13],"for":[14,54,65,78,107],"effectively":[15],"exploiting":[16],"information.":[18],"Even":[19],"though":[20],"single-stage":[21,92],"end-to-end":[22],"supervised":[23],"models":[24,144],"can":[25],"obtain":[26],"impressive":[27],"enhancement,":[28],"combining":[29],"them":[30],"a":[32,36,40,51,62,71,99,127,146,152],"beamformer":[34,64],"and":[35,81,124,150],"DNN-based":[37],"post-filter":[38],"in":[39,121,130,145],"multistage":[41],"processing":[42],"provides":[43],"additional":[44,66],"improvements.":[45],"In":[46],"this":[47],"work,":[48],"we":[49,69,95],"propose":[50,70],"two-stage":[52,147],"strategy":[53,113,140],"multi-channel":[55],"speech":[56],"enhancement":[57],"that":[58],"does":[59],"not":[60],"require":[61],"performance.":[67],"First,":[68],"novel":[72],"attentive":[73,103],"dense":[74],"convolutional":[75],"network":[76,105],"(ADCN)":[77],"estimating":[79,108],"real":[80],"imaginary":[82],"parts":[83],"of":[84,138],"complex":[85],"spectrogram.":[86],"ADCN":[87,97],"obtains":[88],"state-of-the-art":[89],"results":[90],"among":[91],"models.":[93],"Next,":[94],"use":[96],"recently":[100],"proposed":[101,112],"triple-path":[102],"recurrent":[104],"(TPARN)":[106],"waveform":[109],"samples.":[110],"The":[111],"uses":[114],"two":[115,122],"insights;":[116],"first,":[117],"using":[118,126],"different":[119],"approaches":[120],"stages;":[123],"second,":[125],"stronger":[128],"model":[129],"the":[131,136],"first":[132],"stage.":[133],"We":[134],"illustrate":[135],"efficacy":[137],"our":[139],"by":[141],"evaluating":[142],"multiple":[143],"approach":[148],"without":[151],"beamformer.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}