{"id":"https://openalex.org/W4408858407","doi":"https://doi.org/10.1109/tim.2025.3554853","title":"Enhancing Speech Activity Detection in Air Traffic Control Communication via Push-to-Talk Event Identification","display_name":"Enhancing Speech Activity Detection in Air Traffic Control Communication via Push-to-Talk Event Identification","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4408858407","doi":"https://doi.org/10.1109/tim.2025.3554853"},"language":"en","primary_location":{"id":"doi:10.1109/tim.2025.3554853","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tim.2025.3554853","pdf_url":null,"source":{"id":"https://openalex.org/S10892749","display_name":"IEEE Transactions on Instrumentation and Measurement","issn_l":"0018-9456","issn":["0018-9456","1557-9662"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Instrumentation and Measurement","raw_type":"journal-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/A5057805812","display_name":"Dongyue Guo","orcid":"https://orcid.org/0000-0003-0393-5197"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]},{"id":"https://openalex.org/I4210125143","display_name":"Chengdu University","ror":"https://ror.org/034z67559","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210125143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongyue Guo","raw_affiliation_strings":["College of Computer Science, Sichuan University, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0003-0393-5197","affiliations":[{"raw_affiliation_string":"College of Computer Science, Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I4210125143","https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058175236","display_name":"X. Y. You","orcid":"https://orcid.org/0009-0000-7439-1401"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]},{"id":"https://openalex.org/I4210125143","display_name":"Chengdu University","ror":"https://ror.org/034z67559","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210125143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuehang You","raw_affiliation_strings":["College of Computer Science, Sichuan University, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0000-7439-1401","affiliations":[{"raw_affiliation_string":"College of Computer Science, Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I4210125143","https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wang Yue","orcid":"https://orcid.org/0009-0000-3467-0270"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]},{"id":"https://openalex.org/I4210125143","display_name":"Chengdu University","ror":"https://ror.org/034z67559","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210125143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang Yue","raw_affiliation_strings":["College of Computer Science, Sichuan University, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0000-3467-0270","affiliations":[{"raw_affiliation_string":"College of Computer Science, Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I4210125143","https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chunpeng Wang","orcid":"https://orcid.org/0009-0000-1961-4596"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]},{"id":"https://openalex.org/I4210125143","display_name":"Chengdu University","ror":"https://ror.org/034z67559","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210125143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunpeng Wang","raw_affiliation_strings":["College of Computer Science, Sichuan University, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0000-1961-4596","affiliations":[{"raw_affiliation_string":"College of Computer Science, Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I4210125143","https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100326967","display_name":"Jianwei Zhang","orcid":"https://orcid.org/0000-0002-5491-1745"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]},{"id":"https://openalex.org/I4210125143","display_name":"Chengdu University","ror":"https://ror.org/034z67559","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210125143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianwei Zhang","raw_affiliation_strings":["College of Computer Science, Sichuan University, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-5491-1745","affiliations":[{"raw_affiliation_string":"College of Computer Science, Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I4210125143","https://openalex.org/I24185976"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066617875","display_name":"Yi Lin","orcid":"https://orcid.org/0000-0002-7194-5023"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]},{"id":"https://openalex.org/I4210125143","display_name":"Chengdu University","ror":"https://ror.org/034z67559","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210125143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Lin","raw_affiliation_strings":["College of Computer Science, Sichuan University, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-7194-5023","affiliations":[{"raw_affiliation_string":"College of Computer Science, Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I4210125143","https://openalex.org/I24185976"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02291709,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"74","issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9684000015258789,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9684000015258789,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9527999758720398,"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/T12031","display_name":"Speech and dialogue systems","score":0.9524999856948853,"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/voice-activity-detection","display_name":"Voice activity detection","score":0.6380592584609985},{"id":"https://openalex.org/keywords/air-traffic-control","display_name":"Air traffic control","score":0.5954587459564209},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5680975914001465},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5576444268226624},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5400595664978027},{"id":"https://openalex.org/keywords/speech-communication","display_name":"Speech communication","score":0.48540911078453064},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47995880246162415},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.377977579832077},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.3180100917816162},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10597345232963562},{"id":"https://openalex.org/keywords/aerospace-engineering","display_name":"Aerospace engineering","score":0.1056724488735199}],"concepts":[{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6380592584609985},{"id":"https://openalex.org/C166961238","wikidata":"https://www.wikidata.org/wiki/Q221395","display_name":"Air traffic control","level":2,"score":0.5954587459564209},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5680975914001465},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5576444268226624},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5400595664978027},{"id":"https://openalex.org/C2989496772","wikidata":"https://www.wikidata.org/wiki/Q52946","display_name":"Speech communication","level":2,"score":0.48540911078453064},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47995880246162415},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.377977579832077},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3180100917816162},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10597345232963562},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.1056724488735199},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tim.2025.3554853","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tim.2025.3554853","pdf_url":null,"source":{"id":"https://openalex.org/S10892749","display_name":"IEEE Transactions on Instrumentation and Measurement","issn_l":"0018-9456","issn":["0018-9456","1557-9662"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Instrumentation and Measurement","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"awards":[{"id":"https://openalex.org/G1370497161","display_name":null,"funder_award_id":"62371323","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3924646768","display_name":null,"funder_award_id":"62401380","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4293690897","display_name":null,"funder_award_id":"GY2024-01A","funder_id":"https://openalex.org/F4320327727","funder_display_name":"Open Fund of Key Laboratory of Sediment Research"},{"id":"https://openalex.org/G5325585407","display_name":null,"funder_award_id":"U2433217","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6307433967","display_name":null,"funder_award_id":"U2333209","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7240477631","display_name":null,"funder_award_id":"2025ZNSFSC1476","funder_id":"https://openalex.org/F4320329861","funder_display_name":"Natural Science Foundation of Sichuan Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327727","display_name":"Open Fund of Key Laboratory of Sediment Research","ror":null},{"id":"https://openalex.org/F4320329861","display_name":"Natural Science Foundation of Sichuan Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W182487737","https://openalex.org/W2008514512","https://openalex.org/W2008716258","https://openalex.org/W2020760458","https://openalex.org/W2032474878","https://openalex.org/W2059203007","https://openalex.org/W2096733369","https://openalex.org/W2097036989","https://openalex.org/W2104835909","https://openalex.org/W2105770808","https://openalex.org/W2119393553","https://openalex.org/W2143448557","https://openalex.org/W2148128296","https://openalex.org/W2152395643","https://openalex.org/W2158146178","https://openalex.org/W2159531755","https://openalex.org/W2294745040","https://openalex.org/W2401364490","https://openalex.org/W2513345070","https://openalex.org/W2914275764","https://openalex.org/W2954930777","https://openalex.org/W2963308316","https://openalex.org/W2964052309","https://openalex.org/W2976884277","https://openalex.org/W2991531480","https://openalex.org/W3081285175","https://openalex.org/W3153215492","https://openalex.org/W3160984956","https://openalex.org/W3198853881","https://openalex.org/W3216938937","https://openalex.org/W4214550350","https://openalex.org/W4224293426","https://openalex.org/W4285150968","https://openalex.org/W4309857275","https://openalex.org/W4312899222","https://openalex.org/W4366667317","https://openalex.org/W4385245566","https://openalex.org/W4389495045","https://openalex.org/W4392904154","https://openalex.org/W6631190155","https://openalex.org/W6640172592","https://openalex.org/W6762718338"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W4294771049","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W1523214805","https://openalex.org/W2168417340","https://openalex.org/W4229451372","https://openalex.org/W2113211312","https://openalex.org/W1510046822"],"abstract_inverted_index":{"Speech":[0],"activity":[1],"detection":[2],"(SAD)":[3],"serves":[4],"as":[5,86,213],"a":[6,60,136,225],"foundational":[7],"and":[8,15,29,103,152,242],"critical":[9],"component":[10],"for":[11,132],"automatic":[12],"speech":[13,38,102,123],"recognition":[14],"understanding":[16],"(ASRU)":[17],"applications":[18],"in":[19,48,57,72,244],"the":[20,34,44,49,68,77,81,91,95,109,113,122,133,146,166,170,181,185,194,197,218,230],"air":[21],"traffic":[22],"control":[23],"(ATC)":[24],"domain.":[25],"However,":[26],"mid-speech":[27],"clipping":[28],"hangover":[30],"problems":[31],"caused":[32],"by":[33,75],"inaccurate":[35],"identification":[36],"of":[37,70,80,196,232],"endpoints":[39],"bring":[40],"significant":[41],"challenges":[42],"to":[43,66,90,111,144,164,179,192,202,216],"existing":[45],"SAD":[46,71,93,134],"approaches":[47],"ATC":[50,73,227,246],"communication":[51,74,247],"environments.":[52],"To":[53,125],"address":[54],"these":[55],"challenges,":[56],"this":[58],"article,":[59],"novel":[61],"ATC-SAD":[62,220],"framework":[63,97,235],"is":[64,142,162,177,190],"proposed":[65,96,178,219,234],"improve":[67,193],"accuracy":[69,241],"measuring":[76],"release":[78],"event":[79],"push-to-talk":[82],"(PTT)":[83],"switch":[84],"(denoted":[85],"PTT":[87,114],"event).":[88],"Compared":[89],"conventional":[92],"approaches,":[94],"can":[98],"not":[99],"only":[100],"distinguish":[101],"nonspeech":[104],"signals":[105,131],"but":[106],"also":[107],"has":[108],"ability":[110],"detect":[112],"events":[115],"from":[116,129,149],"audio":[117,130],"streams,":[118],"thereby":[119],"effectively":[120],"identifying":[121],"endpoints.":[124],"mine":[126],"informative":[127],"features":[128,148,168,183],"tasks,":[135],"multiview":[137],"feature":[138,158],"learning":[139,175],"(MFL)":[140],"module":[141,161,176],"designed":[143,163],"extract":[145],"acoustic":[147,167],"time,":[150],"frequency,":[151],"cepstrum":[153],"domains.":[154],"Furthermore,":[155],"an":[156],"attention-based":[157],"aggregation":[159],"(AFA)":[160],"project":[165],"into":[169],"embedding":[171],"space.":[172],"A":[173],"contrastive":[174],"learn":[180],"discriminative":[182],"among":[184],"three":[186],"distinct":[187],"classes,":[188],"which":[189],"expected":[191],"performance":[195],"classification":[198],"task.":[199],"In":[200],"addition,":[201],"explore":[203],"more":[204],"effective":[205],"neural":[206,210],"architectures,":[207],"four":[208],"classical":[209],"networks":[211,215],"serve":[212],"backbone":[214],"conduct":[217],"framework.":[221],"Experimental":[222],"results":[223],"on":[224],"real-world":[226],"dataset":[228],"demonstrate":[229],"superiority":[231],"our":[233],"over":[236],"competitive":[237],"baselines,":[238],"achieving":[239],"high":[240],"robustness":[243],"challenging":[245],"scenarios.":[248]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
