{"id":"https://openalex.org/W4225282374","doi":"https://doi.org/10.1109/icassp43922.2022.9746070","title":"A Training Framework for Stereo-Aware Speech Enhancement Using Deep Neural Networks","display_name":"A Training Framework for Stereo-Aware Speech Enhancement Using Deep Neural Networks","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225282374","doi":"https://doi.org/10.1109/icassp43922.2022.9746070"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746070","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746070","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":"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/A5039183732","display_name":"Bahareh Toloosham","orcid":null},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bahareh Toloosham","raw_affiliation_strings":["Harvard University,School of Engineering and Applied Sciences,Cambridge,MA","School of Engineering and Applied Sciences, Harvard University, Cambridge, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University,School of Engineering and Applied Sciences,Cambridge,MA","institution_ids":["https://openalex.org/I2801851002"]},{"raw_affiliation_string":"School of Engineering and Applied Sciences, Harvard University, Cambridge, MA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084879161","display_name":"Kazuhito Koishida","orcid":"https://orcid.org/0000-0002-3111-5375"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kazuhito Koishida","raw_affiliation_strings":["Microsoft Corporation,One Microsoft Way,Redmond,WA","One Microsoft Way, Microsoft Corporation, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation,One Microsoft Way,Redmond,WA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"One Microsoft Way, Microsoft Corporation, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"61","issue":null,"first_page":"6962","last_page":"6966"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9980999827384949,"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"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9977999925613403,"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/speech-enhancement","display_name":"Speech enhancement","score":0.8211052417755127},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8193270564079285},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6636582612991333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5744064450263977},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5528190732002258},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5469262599945068},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47105714678764343},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4636491537094116},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.43727242946624756},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.23452749848365784}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.8211052417755127},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8193270564079285},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6636582612991333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5744064450263977},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5528190732002258},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5469262599945068},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47105714678764343},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4636491537094116},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.43727242946624756},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.23452749848365784},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746070","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746070","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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W233059834","https://openalex.org/W1552314771","https://openalex.org/W1897240248","https://openalex.org/W1901129140","https://openalex.org/W1910234244","https://openalex.org/W1929548479","https://openalex.org/W2050758723","https://openalex.org/W2119255827","https://openalex.org/W2121973264","https://openalex.org/W2141532435","https://openalex.org/W2141998673","https://openalex.org/W2166223512","https://openalex.org/W2241211221","https://openalex.org/W2291877678","https://openalex.org/W2747756448","https://openalex.org/W2802304149","https://openalex.org/W2889411318","https://openalex.org/W2900381824","https://openalex.org/W2944972166","https://openalex.org/W2962866211","https://openalex.org/W2973188947","https://openalex.org/W2975955714","https://openalex.org/W2991015288","https://openalex.org/W2998616931","https://openalex.org/W3015278429","https://openalex.org/W3015279216","https://openalex.org/W3015791598","https://openalex.org/W3140604720","https://openalex.org/W3163296124","https://openalex.org/W3197042120","https://openalex.org/W6639824700","https://openalex.org/W6751445809","https://openalex.org/W6762182681","https://openalex.org/W6792361873","https://openalex.org/W6982644159"],"related_works":["https://openalex.org/W2396048001","https://openalex.org/W2905188205","https://openalex.org/W1559044324","https://openalex.org/W4377865163","https://openalex.org/W3193857078","https://openalex.org/W2888956734","https://openalex.org/W3000197790","https://openalex.org/W4315865067","https://openalex.org/W2979433843","https://openalex.org/W3208304128"],"abstract_inverted_index":{"Deep":[0],"learning-based":[1,98],"speech":[2,15,90,99,165],"enhancement":[3,16,62,100],"has":[4,44],"shown":[5],"unprecedented":[6],"performance":[7,63,156],"in":[8,61,79],"recent":[9],"years.":[10],"The":[11,111],"most":[12],"popular":[13],"mono":[14,65],"frameworks":[17],"are":[18],"end-to-end":[19],"networks":[20],"mapping":[21],"the":[22,29,67,80,103,108,137,154,160,164],"noisy":[23],"mixture":[24],"into":[25],"an":[26,59,130,150],"estimate":[27],"of":[28,38,64,136,163],"clean":[30],"speech.":[31],"With":[32],"growing":[33],"computational":[34],"power":[35],"and":[36,71,133,159],"availability":[37],"multichannel":[39],"microphone":[40],"recordings,":[41],"prior":[42],"work":[43],"aimed":[45],"to":[46,54,101,122],"incorporate":[47],"spatial":[48,68,104],"statistics":[49],"along":[50],"with":[51],"spectral":[52],"information":[53],"boost":[55],"up":[56],"performance.":[57],"Despite":[58],"improvement":[60],"output,":[66],"image":[69,105,151],"preservation":[70,152],"subjective":[72,134],"evaluations":[73],"have":[74],"not":[75],"gained":[76],"much":[77],"attention":[78],"literature.":[81],"This":[82],"paper":[83],"proposes":[84],"a":[85,93,141],"novel":[86],"stereo-aware":[87],"framework":[88,113],"for":[89,96,149],"enhancement,":[91],"i.e.,":[92],"training":[94],"loss":[95],"deep":[97,124],"preserve":[102],"while":[106],"enhancing":[107],"stereo":[109,161],"mixture.":[110],"proposed":[112],"is":[114,157,166],"model":[115],"independent,":[116],"hence":[117],"it":[118],"can":[119],"be":[120],"applied":[121],"any":[123],"learning":[125],"based":[126],"architecture.":[127],"We":[128,144],"provide":[129],"extensive":[131],"objective":[132],"evaluation":[135],"trained":[138],"models":[139],"through":[140],"listening":[142],"test.":[143],"show":[145],"that":[146],"by":[147],"regularizing":[148],"loss,":[153],"overall":[155],"improved,":[158],"aspect":[162],"better":[167],"preserved.":[168]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}