{"id":"https://openalex.org/W4392903047","doi":"https://doi.org/10.1109/icassp48485.2024.10446087","title":"Decoupled Spatial and Temporal Processing for Resource Efficient Multichannel Speech Enhancement","display_name":"Decoupled Spatial and Temporal Processing for Resource Efficient Multichannel Speech Enhancement","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903047","doi":"https://doi.org/10.1109/icassp48485.2024.10446087"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashutosh Pandey","raw_affiliation_strings":["Meta Reality Labs Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs Research","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040562171","display_name":"Buye Xu","orcid":"https://orcid.org/0000-0002-3027-7567"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Buye Xu","raw_affiliation_strings":["Meta Reality Labs Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs Research","institution_ids":["https://openalex.org/I4210128585"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210128585"],"apc_list":null,"apc_paid":null,"fwci":1.7968,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.84639831,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"12206","last_page":"12210"},"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":0.9993000030517578,"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":0.9976999759674072,"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":0.7833254337310791},{"id":"https://openalex.org/keywords/spatial-filter","display_name":"Spatial filter","score":0.5300706624984741},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5072869658470154},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5040392279624939},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.47051897644996643},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46748703718185425},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42405420541763306},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41697052121162415},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.379529744386673},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22194647789001465}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7833254337310791},{"id":"https://openalex.org/C121475858","wikidata":"https://www.wikidata.org/wiki/Q2735911","display_name":"Spatial filter","level":2,"score":0.5300706624984741},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5072869658470154},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5040392279624939},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.47051897644996643},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46748703718185425},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42405420541763306},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41697052121162415},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.379529744386673},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22194647789001465},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1677182931","https://openalex.org/W2141998673","https://openalex.org/W2398042854","https://openalex.org/W2517616541","https://openalex.org/W2568308529","https://openalex.org/W2774389566","https://openalex.org/W2892163332","https://openalex.org/W2900893004","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2963828919","https://openalex.org/W3009032512","https://openalex.org/W3015372568","https://openalex.org/W3015791598","https://openalex.org/W3016094953","https://openalex.org/W3099330747","https://openalex.org/W3134695619","https://openalex.org/W3205004157","https://openalex.org/W3209472002","https://openalex.org/W4210402803","https://openalex.org/W4224919782","https://openalex.org/W4286896457","https://openalex.org/W4311187069","https://openalex.org/W4321608474","https://openalex.org/W4372189495","https://openalex.org/W4372271367","https://openalex.org/W4372346673","https://openalex.org/W4385756463","https://openalex.org/W4385822774","https://openalex.org/W6631190155","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W2012531322","https://openalex.org/W2402761219","https://openalex.org/W4231775656","https://openalex.org/W2046435967","https://openalex.org/W2785900585","https://openalex.org/W2353730437","https://openalex.org/W2490303674","https://openalex.org/W2609066826","https://openalex.org/W2810752900","https://openalex.org/W2062544115"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,16,64,73,82,116],"novel":[3],"model":[4,28,129],"designed":[5],"for":[6],"resource-efficient":[7,117],"multichannel":[8,44,65],"speech":[9],"enhancement":[10],"in":[11,63,115],"the":[12,59,78,91,100],"time":[13],"domain,":[14],"with":[15],"focus":[17],"on":[18],"low":[19,23],"latency,":[20],"lightweight,":[21],"and":[22,32,111,140],"computational":[24],"requirements.":[25],"The":[26,67,88],"proposed":[27,128],"incorporates":[29],"explicit":[30,107],"spatial":[31,47,60,79,101,110],"temporal":[33,68,92,112],"processing":[34,69,80,93,113],"within":[35],"deep":[36],"neural":[37],"network":[38,118],"(DNN)":[39],"layers.":[40],"Inspired":[41],"by":[42],"frequency-dependent":[43],"filtering,":[45],"our":[46,123,127],"filtering":[48],"process":[49],"applies":[50],"multiple":[51],"trainable":[52],"filters":[53],"to":[54],"each":[55],"hidden":[56],"unit":[57],"across":[58],"dimension,":[61],"resulting":[62],"output.":[66],"is":[70,95],"applied":[71],"over":[72],"single-channel":[74],"output":[75,89],"stream":[76],"from":[77,90,122],"using":[81],"Long":[83],"Short-Term":[84],"Memory":[85],"(LSTM)":[86],"network.":[87],"stage":[94],"then":[96],"further":[97],"integrated":[98],"into":[99],"dimension":[102],"through":[103],"elementwise":[104],"multiplication.":[105],"This":[106],"separation":[108],"of":[109,148],"results":[114],"design.":[119],"Empirical":[120],"findings":[121],"experiments":[124],"show":[125],"that":[126],"significantly":[130],"outperforms":[131],"robust":[132],"baseline":[133],"models":[134],"while":[135,142],"demanding":[136],"far":[137],"fewer":[138],"parameters":[139],"computations,":[141],"achieving":[143],"an":[144],"ultra-low":[145],"algorithmic":[146],"latency":[147],"just":[149],"2":[150],"milliseconds.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}