{"id":"https://openalex.org/W4408354858","doi":"https://doi.org/10.1109/icassp49660.2025.10890175","title":"Better Exploiting Spatial Separability in Multichannel Speech Enhancement with an Align-and-Filter Network","display_name":"Better Exploiting Spatial Separability in Multichannel Speech Enhancement with an Align-and-Filter Network","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354858","doi":"https://doi.org/10.1109/icassp49660.2025.10890175"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890175","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890175","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ching-Hua Lee","raw_affiliation_strings":["Samsung Electronics,AI Center-Mountain View"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Electronics,AI Center-Mountain View","institution_ids":["https://openalex.org/I2250650973"]}]},{"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/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chouchang Yang","raw_affiliation_strings":["Samsung Electronics,AI Center-Mountain View"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Electronics,AI Center-Mountain View","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040083798","display_name":"Yashas Malur Saidutta","orcid":"https://orcid.org/0000-0002-8487-0219"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yashas Malur Saidutta","raw_affiliation_strings":["Samsung Electronics,AI Center-Mountain View"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Electronics,AI Center-Mountain View","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039893379","display_name":"Rakshith Sharma Srinivasa","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Rakshith Sharma Srinivasa","raw_affiliation_strings":["Samsung Electronics,AI Center-Mountain View"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Electronics,AI Center-Mountain View","institution_ids":["https://openalex.org/I2250650973"]}]},{"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/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yilin Shen","raw_affiliation_strings":["Samsung Electronics,AI Center-Mountain View"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Electronics,AI Center-Mountain View","institution_ids":["https://openalex.org/I2250650973"]}]},{"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/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hongxia Jin","raw_affiliation_strings":["Samsung Electronics,AI Center-Mountain View"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Electronics,AI Center-Mountain View","institution_ids":["https://openalex.org/I2250650973"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2250650973"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"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":0.9994000196456909,"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":0.9994000196456909,"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":0.9699000120162964,"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":0.7449085116386414},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5879327058792114},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5592632293701172},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5376582741737366},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3838081955909729},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.16419696807861328}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7449085116386414},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5879327058792114},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5592632293701172},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5376582741737366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3838081955909729},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.16419696807861328}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890175","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890175","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1536252645","https://openalex.org/W1559975096","https://openalex.org/W1978752674","https://openalex.org/W1981284917","https://openalex.org/W2106272332","https://openalex.org/W2115969105","https://openalex.org/W2141998673","https://openalex.org/W2144404214","https://openalex.org/W2147665979","https://openalex.org/W2231821870","https://openalex.org/W2289394825","https://openalex.org/W2517616541","https://openalex.org/W2589857635","https://openalex.org/W2763188033","https://openalex.org/W2891219041","https://openalex.org/W2945191446","https://openalex.org/W2952218014","https://openalex.org/W2963902628","https://openalex.org/W2972754898","https://openalex.org/W3009032512","https://openalex.org/W3015372568","https://openalex.org/W3015791598","https://openalex.org/W3016257794","https://openalex.org/W3032514799","https://openalex.org/W3151596526","https://openalex.org/W3191448984","https://openalex.org/W3196940724","https://openalex.org/W3209472002","https://openalex.org/W4221164004","https://openalex.org/W4221165117","https://openalex.org/W4289665794","https://openalex.org/W4292975136","https://openalex.org/W4321608474","https://openalex.org/W4372267870","https://openalex.org/W4375869372","https://openalex.org/W4386902890","https://openalex.org/W4391621214","https://openalex.org/W4392902607","https://openalex.org/W4392903047","https://openalex.org/W4392904014","https://openalex.org/W4392904666","https://openalex.org/W6757632829","https://openalex.org/W6804452642"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W3096184950","https://openalex.org/W4231424160"],"abstract_inverted_index":{"Multichannel":[0],"speech":[1,12,23,42,72],"enhancement":[2],"(SE)":[3],"techniques":[4],"combine":[5],"multiple":[6],"microphone":[7],"signals":[8,67],"to":[9,70,79,115,150],"extract":[10],"clean":[11],"from":[13,26,37,109],"noisy":[14],"mixtures":[15],"based":[16],"on":[17,62],"spatial":[18,125,142,153],"filtering.":[19],"As":[20],"the":[21,58,65,71,76,97,106,117,139],"target":[22],"may":[24],"come":[25],"arbitrary,":[27],"unknown":[28],"directions,":[29],"current":[30],"deep":[31,92],"learning-based":[32,93],"SE":[33,94,160],"systems":[34],"could":[35],"suffer":[36],"performance":[38],"bottleneck":[39],"in":[40],"denoising":[41,99],"within":[43],"one":[44],"stage.":[45],"In":[46,83],"contrast,":[47],"conventional":[48],"signal":[49,110],"processing":[50],"algorithms":[51],"often":[52],"feature":[53],"a":[54,128],"two-stage":[55],"design,":[56],"where":[57],"first":[59],"stage":[60,78],"focuses":[61],"spatially":[63],"aligning":[64],"received":[66],"with":[68],"respect":[69],"source,":[73],"followed":[74],"by":[75,137],"second":[77],"filter":[80],"out":[81],"noise.":[82],"this":[84],"paper,":[85],"we":[86],"introduce":[87],"Align-and-Filter":[88],"network":[89],"(AFnet)":[90],"for":[91,158],"that":[95,122,136],"decouples":[96],"primal":[98],"problem":[100],"into":[101],"two":[102],"sub-problems,":[103],"which":[104],"imitates":[105],"alignment-followed-by-filtering":[107],"wisdom":[108],"processing.":[111],"The":[112],"key":[113],"is":[114],"leverage":[116],"relative":[118],"transfer":[119],"functions":[120],"(RTFs)":[121],"encode":[123],"meaningful":[124],"information":[126],"via":[127],"tactically":[129],"designed":[130],"alignment":[131,143],"strategy.":[132],"Experimental":[133],"results":[134],"show":[135],"leveraging":[138],"proposed":[140],"RTF-based":[141],"supervision,":[144],"AFnet":[145],"learns":[146],"interpretable":[147],"directional":[148],"features":[149],"better":[151],"exploit":[152],"separability":[154],"of":[155],"sound":[156],"sources":[157],"improved":[159],"performance.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}