{"id":"https://openalex.org/W3097231682","doi":"https://doi.org/10.21437/interspeech.2020-2392","title":"MLNET: An Adaptive Multiple Receptive-Field Attention Neural Network for Voice Activity Detection","display_name":"MLNET: An Adaptive Multiple Receptive-Field Attention Neural Network for Voice Activity Detection","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3097231682","doi":"https://doi.org/10.21437/interspeech.2020-2392","mag":"3097231682"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2392","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2392","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5048092245","display_name":"Zhenpeng Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105511","display_name":"Beacon Tech (Israel)","ror":"https://ror.org/00zbjch89","country_code":"IL","type":"company","lineage":["https://openalex.org/I4210105511"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Zhenpeng Zheng","raw_affiliation_strings":["An Technology (Shenzhen) Co., Ltd"],"affiliations":[{"raw_affiliation_string":"An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4210105511"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074472751","display_name":"Jianzong Wang","orcid":"https://orcid.org/0000-0002-9237-4231"},"institutions":[{"id":"https://openalex.org/I4210105511","display_name":"Beacon Tech (Israel)","ror":"https://ror.org/00zbjch89","country_code":"IL","type":"company","lineage":["https://openalex.org/I4210105511"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Jianzong Wang","raw_affiliation_strings":["An Technology (Shenzhen) Co., Ltd"],"affiliations":[{"raw_affiliation_string":"An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4210105511"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101977180","display_name":"Ning Cheng","orcid":"https://orcid.org/0000-0002-0988-5023"},"institutions":[{"id":"https://openalex.org/I4210105511","display_name":"Beacon Tech (Israel)","ror":"https://ror.org/00zbjch89","country_code":"IL","type":"company","lineage":["https://openalex.org/I4210105511"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ning Cheng","raw_affiliation_strings":["An Technology (Shenzhen) Co., Ltd"],"affiliations":[{"raw_affiliation_string":"An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4210105511"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076982760","display_name":"Jian Luo","orcid":"https://orcid.org/0000-0002-9756-3066"},"institutions":[{"id":"https://openalex.org/I4210105511","display_name":"Beacon Tech (Israel)","ror":"https://ror.org/00zbjch89","country_code":"IL","type":"company","lineage":["https://openalex.org/I4210105511"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Jian Luo","raw_affiliation_strings":["An Technology (Shenzhen) Co., Ltd"],"affiliations":[{"raw_affiliation_string":"An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4210105511"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016038454","display_name":"Jing Xiao","orcid":"https://orcid.org/0000-0001-9615-4749"},"institutions":[{"id":"https://openalex.org/I4210105511","display_name":"Beacon Tech (Israel)","ror":"https://ror.org/00zbjch89","country_code":"IL","type":"company","lineage":["https://openalex.org/I4210105511"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Jing Xiao","raw_affiliation_strings":["An Technology (Shenzhen) Co., Ltd"],"affiliations":[{"raw_affiliation_string":"An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4210105511"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5048092245"],"corresponding_institution_ids":["https://openalex.org/I4210105511"],"apc_list":null,"apc_paid":null,"fwci":0.4564,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.62770394,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9767000079154968,"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":0.9767000079154968,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9595999717712402,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/receptive-field","display_name":"Receptive field","score":0.7941225171089172},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7023059725761414},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5850826501846313},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5685166120529175},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4865380823612213},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3223470449447632}],"concepts":[{"id":"https://openalex.org/C19071747","wikidata":"https://www.wikidata.org/wiki/Q1755207","display_name":"Receptive field","level":2,"score":0.7941225171089172},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7023059725761414},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5850826501846313},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5685166120529175},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4865380823612213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3223470449447632},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-2392","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2392","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G466649759","display_name":null,"funder_award_id":"2017Y","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G4678737013","display_name":null,"funder_award_id":"2017YFB140","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5138959851","display_name":null,"funder_award_id":"2018YFB1003500","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7027044845","display_name":null,"funder_award_id":"2017YFB1401202","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7429600474","display_name":null,"funder_award_id":"2017YFB1","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8340078520","display_name":null,"funder_award_id":"2017YF","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8823009050","display_name":null,"funder_award_id":"2017YFB","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1563939609","https://openalex.org/W1985242443","https://openalex.org/W1994244061","https://openalex.org/W2032362923","https://openalex.org/W2048497537","https://openalex.org/W2081671587","https://openalex.org/W2101357962","https://openalex.org/W2147362992","https://openalex.org/W2197404611","https://openalex.org/W2240641835","https://openalex.org/W2284628133","https://openalex.org/W2403186097","https://openalex.org/W2408468399","https://openalex.org/W2423557781","https://openalex.org/W2791616807","https://openalex.org/W2884585870","https://openalex.org/W2889224635","https://openalex.org/W2892300106","https://openalex.org/W2917987043","https://openalex.org/W2928746352","https://openalex.org/W2939777153","https://openalex.org/W2954461214","https://openalex.org/W2972643142","https://openalex.org/W2972861996","https://openalex.org/W2982265383","https://openalex.org/W3015305007","https://openalex.org/W3015820460","https://openalex.org/W4309845474"],"related_works":["https://openalex.org/W2079003682","https://openalex.org/W2089544495","https://openalex.org/W1964918325","https://openalex.org/W2913266608","https://openalex.org/W2799648451","https://openalex.org/W1970258141","https://openalex.org/W2189496153","https://openalex.org/W2186491718","https://openalex.org/W1555021777","https://openalex.org/W2089930126"],"abstract_inverted_index":{"Voice":[0],"activity":[1],"detection":[2],"(VAD)":[3],"makes":[4],"a":[5,41],"distinction":[6],"between":[7],"speech":[8,19,50,63,75,108],"and":[9,11,71,110],"non-speech":[10],"its":[12],"performance":[13,30,55],"is":[14],"of":[15,47,56,61,122],"crucial":[16,120],"importance":[17],"for":[18,125],"based":[20],"services.Recently,":[21],"deep":[22],"neural":[23,93],"network":[24],"(DNN)-based":[25],"VADs":[26],"have":[27],"achieved":[28],"better":[29],"than":[31],"conventional":[32],"signal":[33],"processing":[34],"methods.The":[35],"existed":[36],"DNNbased":[37],"models":[38],"always":[39],"handcrafted":[40],"fixed":[42,59],"window":[43,60],"to":[44,52,77,81,97,104,116],"make":[45],"use":[46],"the":[48,54,58,73,118,123,133],"contextual":[49,62,107],"information":[51,64,76,109],"improve":[53],"VAD.However,":[57],"can't":[65],"handle":[66],"various":[67],"unpredictable":[68],"noise":[69],"environments":[70],"highlight":[72],"critical":[74],"VAD":[78,99],"task.In":[79],"order":[80],"solve":[82],"this":[83,85],"problem,":[84],"paper":[86],"proposed":[87,134],"an":[88,112],"adaptive":[89],"multiple":[90,106],"receptive-field":[91],"attention":[92,114],"network,":[94],"called":[95],"MLNET,":[96],"finish":[98],"task.The":[100],"MLNET":[101],"leveraged":[102],"multi-branches":[103],"extract":[105],"investigated":[111],"effective":[113],"block":[115],"weight":[117],"most":[119],"parts":[121],"context":[124],"final":[126],"classification.Experiments":[127],"in":[128],"real-world":[129],"scenarios":[130],"demonstrated":[131],"that":[132],"MLNET-based":[135],"model":[136],"outperformed":[137],"other":[138],"baselines.":[139]},"counts_by_year":[{"year":2023,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}