{"id":"https://openalex.org/W4375869372","doi":"https://doi.org/10.1109/icassp49357.2023.10096213","title":"Improved Mask-Based Neural Beamforming for Multichannel Speech Enhancement by Snapshot Matching Masking","display_name":"Improved Mask-Based Neural Beamforming for Multichannel Speech Enhancement by Snapshot Matching Masking","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869372","doi":"https://doi.org/10.1109/icassp49357.2023.10096213"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096213","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096213","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":"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/A5028862537","display_name":"Ching-Hua Lee","orcid":"https://orcid.org/0000-0001-6116-3653"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]},{"id":"https://openalex.org/I4210133173","display_name":"Research!America (United States)","ror":"https://ror.org/044pgyv50","country_code":"US","type":"company","lineage":["https://openalex.org/I4210133173"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ching-Hua Lee","raw_affiliation_strings":["Samsung Research America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research America","institution_ids":["https://openalex.org/I4210101778","https://openalex.org/I4210133173"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071383028","display_name":"Chouchang Yang","orcid":"https://orcid.org/0009-0007-3506-6121"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]},{"id":"https://openalex.org/I4210133173","display_name":"Research!America (United States)","ror":"https://ror.org/044pgyv50","country_code":"US","type":"company","lineage":["https://openalex.org/I4210133173"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chouchang Yang","raw_affiliation_strings":["Samsung Research America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research America","institution_ids":["https://openalex.org/I4210101778","https://openalex.org/I4210133173"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058974318","display_name":"Yilin Shen","orcid":"https://orcid.org/0000-0002-1955-1529"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]},{"id":"https://openalex.org/I4210133173","display_name":"Research!America (United States)","ror":"https://ror.org/044pgyv50","country_code":"US","type":"company","lineage":["https://openalex.org/I4210133173"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yilin Shen","raw_affiliation_strings":["Samsung Research America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research America","institution_ids":["https://openalex.org/I4210101778","https://openalex.org/I4210133173"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044205212","display_name":"Hongxia Jin","orcid":"https://orcid.org/0009-0000-0222-4217"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]},{"id":"https://openalex.org/I4210133173","display_name":"Research!America (United States)","ror":"https://ror.org/044pgyv50","country_code":"US","type":"company","lineage":["https://openalex.org/I4210133173"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongxia Jin","raw_affiliation_strings":["Samsung Research America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research America","institution_ids":["https://openalex.org/I4210101778","https://openalex.org/I4210133173"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9988999962806702,"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":0.9966999888420105,"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":0.748942494392395},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.705866813659668},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6578218340873718},{"id":"https://openalex.org/keywords/snapshot","display_name":"Snapshot (computer storage)","score":0.5797262191772461},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5647225975990295},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.504611611366272},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4669521749019623},{"id":"https://openalex.org/keywords/spectral-density","display_name":"Spectral density","score":0.44134944677352905},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.395205557346344},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.3517500162124634},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3432469367980957},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1119275689125061}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.748942494392395},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.705866813659668},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6578218340873718},{"id":"https://openalex.org/C55282118","wikidata":"https://www.wikidata.org/wiki/Q252683","display_name":"Snapshot (computer storage)","level":2,"score":0.5797262191772461},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5647225975990295},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.504611611366272},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4669521749019623},{"id":"https://openalex.org/C168110828","wikidata":"https://www.wikidata.org/wiki/Q1331626","display_name":"Spectral density","level":2,"score":0.44134944677352905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.395205557346344},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3517500162124634},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3432469367980957},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1119275689125061},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096213","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096213","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":[{"score":0.6100000143051147,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1996304098","https://openalex.org/W2106272332","https://openalex.org/W2141998673","https://openalex.org/W2168729028","https://openalex.org/W2289394825","https://openalex.org/W2398042854","https://openalex.org/W2398972335","https://openalex.org/W2403555780","https://openalex.org/W2506203739","https://openalex.org/W2507780144","https://openalex.org/W2517616541","https://openalex.org/W2589857635","https://openalex.org/W2636483419","https://openalex.org/W2763188033","https://openalex.org/W2767071179","https://openalex.org/W2889411318","https://openalex.org/W2890489755","https://openalex.org/W2891219041","https://openalex.org/W2945191446","https://openalex.org/W2949756029","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2963902628","https://openalex.org/W2982471419","https://openalex.org/W3015372568","https://openalex.org/W3099330747","https://openalex.org/W3191448984","https://openalex.org/W4245919820","https://openalex.org/W4289665794","https://openalex.org/W6639824700","https://openalex.org/W6757632829"],"related_works":["https://openalex.org/W2542847180","https://openalex.org/W3034994054","https://openalex.org/W2155226960","https://openalex.org/W2805712290","https://openalex.org/W2909129499","https://openalex.org/W2761598930","https://openalex.org/W2392087771","https://openalex.org/W2963170046","https://openalex.org/W2553994394","https://openalex.org/W2376244802"],"abstract_inverted_index":{"In":[0,86],"multichannel":[1],"speech":[2,23,36],"enhancement":[3],"(SE),":[4],"time-frequency":[5],"(T-F)":[6],"mask-based":[7,138],"neural":[8,15,139],"beamforming":[9,140],"algorithms":[10],"take":[11],"advantage":[12],"of":[13,127],"deep":[14],"networks":[16,59],"to":[17,33,62,82,95,104,146],"predict":[18,96],"T-F":[19],"masks":[20,29],"that":[21,78,102],"represent":[22],"and":[24,37,73,111,133],"noise":[25,38],"dominance.":[26],"The":[27],"predicted":[28,110],"are":[30,60],"subsequently":[31],"leveraged":[32],"estimate":[34,63],"the":[35,46,56,68,83,97,106,109,112,118,151],"power":[39],"spectral":[40],"density":[41],"(PSD)":[42],"matrices":[43,120],"for":[44,137,150],"computing":[45],"beamformer":[47],"filter":[48],"weights":[49],"based":[50],"on":[51,143],"signal":[52,114],"statistics.":[53],"However,":[54],"in":[55,121],"literature":[57],"most":[58],"trained":[61],"some":[64],"pre-defined":[65],"masks,":[66],"e.g.,":[67],"ideal":[69,74],"binary":[70],"mask":[71,76],"(IBM)":[72],"ratio":[75],"(IRM)":[77],"lack":[79],"direct":[80],"connection":[81],"PSD":[84,119,135],"estimation.":[85],"this":[87],"paper,":[88],"we":[89],"propose":[90],"a":[91,122],"new":[92],"masking":[93],"strategy":[94],"Snapshot":[98],"Matching":[99],"Mask":[100],"(SMM)":[101],"aims":[103],"minimize":[105],"distance":[107],"between":[108],"true":[113],"snapshots,":[115],"thereby":[116],"estimating":[117],"more":[123],"systematic":[124],"way.":[125],"Performance":[126],"SMM":[128],"compared":[129],"with":[130],"existing":[131],"IBM-":[132],"IRM-based":[134],"estimation":[136],"is":[141],"presented":[142],"several":[144],"datasets":[145],"demonstrate":[147],"its":[148],"effectiveness":[149],"SE":[152],"task.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}