{"id":"https://openalex.org/W4392903305","doi":"https://doi.org/10.1109/icassp48485.2024.10446084","title":"Phase Continuity-Aware Self-Attentive Recurrent Network with Adaptive Feature Selection for Robust VAD","display_name":"Phase Continuity-Aware Self-Attentive Recurrent Network with Adaptive Feature Selection for Robust VAD","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903305","doi":"https://doi.org/10.1109/icassp48485.2024.10446084"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446084","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446084","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":"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/A5102603651","display_name":"Minjie Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minjie Tang","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China","School of Computer Science and Technology, Xinjiang University, Urumqi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024772368","display_name":"Hao Huang","orcid":"https://orcid.org/0000-0001-6604-0951"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Huang","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China","School of Computer Science and Technology, Xinjiang University, Urumqi, China","Xinjiang Key Laboratory of Multi-Lingual Information Technology, Urumqi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Xinjiang Key Laboratory of Multi-Lingual Information Technology, Urumqi, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100398476","display_name":"Wenbo Zhang","orcid":"https://orcid.org/0009-0007-2549-2549"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbo Zhang","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China","School of Computer Science and Technology, Xinjiang University, Urumqi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049944728","display_name":"Liang He","orcid":"https://orcid.org/0000-0003-4076-7479"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang He","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China","Department of Electronic Engineering, Tsinghua University, China","School of Computer Science and Technology, Xinjiang University, Urumqi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7651,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.65196128,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"11506","last_page":"11510"},"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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":0.9980000257492065,"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/computer-science","display_name":"Computer science","score":0.7946599125862122},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7499855756759644},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5924763679504395},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5729008316993713},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4865261912345886},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48635298013687134},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.4698841869831085},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45827603340148926},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4516125023365021},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4403376579284668},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33285021781921387},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.28029537200927734}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7946599125862122},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7499855756759644},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5924763679504395},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5729008316993713},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4865261912345886},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48635298013687134},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.4698841869831085},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45827603340148926},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4516125023365021},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4403376579284668},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33285021781921387},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.28029537200927734},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446084","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446084","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":[],"awards":[{"id":"https://openalex.org/G6861194883","display_name":"\u57fa\u4e8e\u65e0\u76d1\u7763\u5b66\u4e60\u65b9\u6cd5\u7684\u53e3\u8bed\u7406\u89e3\u4e0e\u4eba\u673a\u5bf9\u8bdd\u884c\u4e3a\u7814\u7a76","funder_award_id":"61663044","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1563939609","https://openalex.org/W1999454387","https://openalex.org/W2000916836","https://openalex.org/W2045956438","https://openalex.org/W2048497537","https://openalex.org/W2108148744","https://openalex.org/W2115717467","https://openalex.org/W2119125873","https://openalex.org/W2129120544","https://openalex.org/W2151484683","https://openalex.org/W2197404611","https://openalex.org/W2240641835","https://openalex.org/W2284628133","https://openalex.org/W2408468399","https://openalex.org/W2510670092","https://openalex.org/W2513345070","https://openalex.org/W2535438430","https://openalex.org/W2791616807","https://openalex.org/W2954930777","https://openalex.org/W2991324852","https://openalex.org/W2995588677","https://openalex.org/W3034728336","https://openalex.org/W3160984956","https://openalex.org/W3165776651","https://openalex.org/W3170088519","https://openalex.org/W4221158470","https://openalex.org/W4224933355","https://openalex.org/W4372269163","https://openalex.org/W4385245566","https://openalex.org/W4385823058","https://openalex.org/W6695553435","https://openalex.org/W6703482877","https://openalex.org/W6770514768"],"related_works":["https://openalex.org/W4225394202","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W1847088711","https://openalex.org/W3036642985","https://openalex.org/W3032952384","https://openalex.org/W3017902212","https://openalex.org/W2964335273","https://openalex.org/W4386564352","https://openalex.org/W2952668426"],"abstract_inverted_index":{"Deep":[0],"neural":[1,115],"network":[2,67,104,116],"(DNN)":[3],"applications":[4],"have":[5],"significantly":[6],"progressed":[7],"in":[8,23],"voice":[9],"activity":[10],"detection":[11],"(VAD).":[12],"Most":[13],"current":[14],"DNN-based":[15],"VAD":[16,57,130,149],"methods":[17],"ignore":[18],"the":[19,24,46,70,110,121,147],"rich":[20],"audio":[21],"information":[22,31,127],"phase":[25,63],"domain.":[26],"Therefore,":[27],"applying":[28],"this":[29,52],"auxiliary":[30],"rationally":[32],"and":[33,86,113,125,143],"coping":[34],"with":[35,99],"low":[36],"signal-to-noise":[37],"ratio":[38],"(SNR)":[39],"background":[40],"noise":[41,61],"environments":[42],"remains":[43],"one":[44],"of":[45,72],"challenges":[47],"for":[48],"VAD.":[49],"To":[50],"address":[51],"problem,":[53],"we":[54,74],"propose":[55],"a":[56],"model":[58],"robust":[59],"to":[60,95,128,146],"called":[62],"continuity-aware":[64],"self-attentive":[65],"recurrent":[66,114],"(PC-ARN).":[68],"For":[69],"input":[71],"PC-ARN,":[73],"draw":[75],"inspiration":[76],"from":[77],"recent":[78],"speech":[79],"enhancement":[80],"research":[81],"by":[82],"introducing":[83],"phase-related":[84],"features":[85,98],"further":[87],"employing":[88],"an":[89,106],"adaptive":[90],"feature":[91],"selection":[92],"module":[93,108],"(AFSM)":[94],"combine":[96],"magnitude":[97],"it":[100],"efficiently.":[101],"The":[102],"backbone":[103],"is":[105],"ARN":[107],"combining":[109],"attention":[111],"mechanism":[112],"(RNN),":[117],"which":[118],"can":[119],"consider":[120],"relationship":[122],"between":[123],"local":[124],"global":[126],"improve":[129],"performance":[131],"competently.":[132],"Experimental":[133],"results":[134],"show":[135],"that":[136],"our":[137],"method":[138],"has":[139],"remarkable":[140],"generalization":[141],"ability":[142],"robustness":[144],"compared":[145],"traditional":[148],"techniques.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}