{"id":"https://openalex.org/W3160071434","doi":"https://doi.org/10.1109/icassp39728.2021.9414445","title":"Speech Enhancement Aided End-To-End Multi-Task Learning for Voice Activity Detection","display_name":"Speech Enhancement Aided End-To-End Multi-Task Learning for Voice Activity Detection","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160071434","doi":"https://doi.org/10.1109/icassp39728.2021.9414445","mag":"3160071434"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414445","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5101522533","display_name":"Xu Tan","orcid":"https://orcid.org/0000-0002-6457-5407"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Tan","raw_affiliation_strings":["CIAIC, School of Marine Science and Technology, Northwestern Polytechnical University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CIAIC, School of Marine Science and Technology, Northwestern Polytechnical University, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100450091","display_name":"Xiao-Lei Zhang","orcid":"https://orcid.org/0000-0001-7694-193X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao-Lei Zhang","raw_affiliation_strings":["CIAIC, School of Marine Science and Technology, Northwestern Polytechnical University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CIAIC, School of Marine Science and Technology, Northwestern Polytechnical University, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6823","last_page":"6827"},"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9983000159263611,"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":0.7873955965042114},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7656749486923218},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.7619941830635071},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7116954922676086},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6329935789108276},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5502082705497742},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5364530682563782},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4378427565097809},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3442382514476776},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3057050406932831},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.24153760075569153},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08381414413452148},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07365906238555908}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7873955965042114},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7656749486923218},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.7619941830635071},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7116954922676086},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6329935789108276},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5502082705497742},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5364530682563782},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4378427565097809},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3442382514476776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3057050406932831},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.24153760075569153},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08381414413452148},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07365906238555908},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414445","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320329139","display_name":"Communication University of China","ror":"https://ror.org/04facbs33"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1974387177","https://openalex.org/W1985242443","https://openalex.org/W1989364685","https://openalex.org/W2024490156","https://openalex.org/W2048497537","https://openalex.org/W2059203007","https://openalex.org/W2067295501","https://openalex.org/W2098265087","https://openalex.org/W2109000787","https://openalex.org/W2197404611","https://openalex.org/W2289394825","https://openalex.org/W2396495723","https://openalex.org/W2513345070","https://openalex.org/W2612770767","https://openalex.org/W2791616807","https://openalex.org/W2797121075","https://openalex.org/W2889224635","https://openalex.org/W2892300106","https://openalex.org/W2917987043","https://openalex.org/W2952218014","https://openalex.org/W2964058413","https://openalex.org/W2964121744","https://openalex.org/W2972861996","https://openalex.org/W3011405319","https://openalex.org/W3022404557","https://openalex.org/W3036462239","https://openalex.org/W3099330747","https://openalex.org/W3099628266","https://openalex.org/W6631190155","https://openalex.org/W6646535293","https://openalex.org/W6687509687","https://openalex.org/W6737356976","https://openalex.org/W6779634177","https://openalex.org/W6785075119"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W2294333436","https://openalex.org/W2653598178","https://openalex.org/W2373767407","https://openalex.org/W3110551121","https://openalex.org/W2131486661","https://openalex.org/W4252682934","https://openalex.org/W4200596008"],"abstract_inverted_index":{"Robust":[0],"voice":[1],"activity":[2],"detection":[3],"(VAD)":[4],"is":[5,20,28],"a":[6,37,89],"challenging":[7],"task":[8],"in":[9,111,164],"low":[10],"signal-to-noise":[11],"(SNR)":[12],"environments.":[13],"Recent":[14],"studies":[15],"show":[16,149],"that":[17,75,150],"speech":[18,38,53,68,83,108,120],"enhancement":[19,39,54,84,109,121],"helpful":[21],"to":[22,102],"VAD,":[23],"but":[24,134],"the":[25,56,64,72,104,107,112,117,128,137,151,165],"performance":[26],"improvement":[27],"limited.":[29],"To":[30],"address":[31],"this":[32],"issue,":[33],"here":[34,86],"we":[35,87],"propose":[36,88],"aided":[40],"end-to-end":[41],"multi-task":[42,152,167],"model":[43,47],"for":[44,52,58,80],"VAD.":[45,59],"The":[46,60],"has":[48],"two":[49,61,77],"decoders,":[50],"one":[51],"and":[55,67,82,119,131],"other":[57],"decoders":[62],"share":[63],"same":[65,166],"encoder":[66,130],"separation":[69,132],"network.":[70],"Unlike":[71],"direct":[73],"thought":[74],"takes":[76],"separated":[78],"objectives":[79],"VAD":[81,100,118,158],"respectively,":[85],"new":[90],"joint":[91],"optimization":[92],"objective\u2014VAD-masked":[93],"scale-invariant":[94],"source-to-distortion":[95],"ratio":[96],"(mSI-SDR).":[97],"mSI-SDR":[98,161],"uses":[99],"information":[101],"mask":[103],"output":[105],"of":[106],"decoder":[110],"training":[113],"process.":[114],"It":[115,140],"makes":[116],"tasks":[122],"jointly":[123],"optimized":[124],"not":[125],"only":[126],"at":[127,136],"shared":[129],"network,":[133],"also":[135,141],"objective":[138],"level.":[139],"satisfies":[142],"real-time":[143],"working":[144],"requirement":[145],"theoretically.":[146],"Experimental":[147],"results":[148],"method":[153],"significantly":[154],"outperforms":[155,162],"its":[156],"single-task":[157],"counterpart.":[159],"Moreover,":[160],"SI-SDR":[163],"setting.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}