{"id":"https://openalex.org/W4309857275","doi":"https://doi.org/10.1145/3572792","title":"A Comparative Study of Speaker Role Identification in Air Traffic Communication Using Deep Learning Approaches","display_name":"A Comparative Study of Speaker Role Identification in Air Traffic Communication Using Deep Learning Approaches","publication_year":2022,"publication_date":"2022-11-24","ids":{"openalex":"https://openalex.org/W4309857275","doi":"https://doi.org/10.1145/3572792"},"language":"en","primary_location":{"id":"doi:10.1145/3572792","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3572792","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongyue Guo","raw_affiliation_strings":["National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0003-0393-5197","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University, Chengdu, China","institution_ids":["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":"middle","author":{"id":"https://openalex.org/A5067325797","display_name":"Bo Yang","orcid":"https://orcid.org/0000-0002-5866-6492"},"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":"Bo Yang","raw_affiliation_strings":["College of Computer Science, Sichuan University, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-5866-6492","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":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.081,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.89000168,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"22","issue":"4","first_page":"1","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9966999888420105,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9901000261306763,"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":0.7884901762008667},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5327755212783813},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5087776780128479},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4742128849029541},{"id":"https://openalex.org/keywords/air-traffic-control","display_name":"Air traffic control","score":0.4700946509838104},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.467949777841568},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4472297132015228},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4460664987564087},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4343530535697937},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.42251673340797424},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4196595549583435},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4153469204902649},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.2115785777568817},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10403725504875183}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7884901762008667},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5327755212783813},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5087776780128479},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4742128849029541},{"id":"https://openalex.org/C166961238","wikidata":"https://www.wikidata.org/wiki/Q221395","display_name":"Air traffic control","level":2,"score":0.4700946509838104},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.467949777841568},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4472297132015228},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4460664987564087},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4343530535697937},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.42251673340797424},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4196595549583435},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4153469204902649},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.2115785777568817},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10403725504875183},{"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},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3572792","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3572792","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G457508573","display_name":null,"funder_award_id":"62001315 and U20A20161","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8425271570","display_name":null,"funder_award_id":"2021SCU12050","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1832693441","https://openalex.org/W2041493454","https://openalex.org/W2056119007","https://openalex.org/W2112796928","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2233435981","https://openalex.org/W2251189452","https://openalex.org/W2354870669","https://openalex.org/W2410860376","https://openalex.org/W2517194566","https://openalex.org/W2525579820","https://openalex.org/W2526050071","https://openalex.org/W2591013610","https://openalex.org/W2592549418","https://openalex.org/W2603150165","https://openalex.org/W2606429533","https://openalex.org/W2619383789","https://openalex.org/W2626699878","https://openalex.org/W2730845691","https://openalex.org/W2744227074","https://openalex.org/W2777468850","https://openalex.org/W2890964092","https://openalex.org/W2894676449","https://openalex.org/W2901907199","https://openalex.org/W2903799412","https://openalex.org/W2914275764","https://openalex.org/W2916984808","https://openalex.org/W2937142395","https://openalex.org/W2963241825","https://openalex.org/W2963341956","https://openalex.org/W2963355447","https://openalex.org/W2963383024","https://openalex.org/W2963723765","https://openalex.org/W2964052309","https://openalex.org/W2972909277","https://openalex.org/W2976884277","https://openalex.org/W2978223337","https://openalex.org/W2980708516","https://openalex.org/W2991082564","https://openalex.org/W3015777882","https://openalex.org/W3081285175","https://openalex.org/W3084552125","https://openalex.org/W3096806943","https://openalex.org/W3098670224","https://openalex.org/W3103314642","https://openalex.org/W3131114805","https://openalex.org/W3133953372","https://openalex.org/W3177525997","https://openalex.org/W3197163313","https://openalex.org/W3198853881","https://openalex.org/W3212070308","https://openalex.org/W4236377898","https://openalex.org/W4289157532","https://openalex.org/W4293565051"],"related_works":["https://openalex.org/W4391621807","https://openalex.org/W4388561773","https://openalex.org/W2123753634","https://openalex.org/W4321487865","https://openalex.org/W4313906399","https://openalex.org/W4391621790","https://openalex.org/W4239306820","https://openalex.org/W4391266461","https://openalex.org/W2590798552","https://openalex.org/W3202613528"],"abstract_inverted_index":{"Automatic":[0],"spoken":[1],"instruction":[2],"understanding":[3,43],"(SIU)":[4],"of":[5,23,31,36,63,86,94,109],"the":[6,10,19,24,29,32,37,41,60,72,87,92,95,107,127,133,143,167,173,188,193,197,207],"controller-pilot":[7,64],"conversations":[8],"in":[9,45],"air":[11,46],"traffic":[12,47],"control":[13],"(ATC)":[14],"requires":[15],"not":[16],"only":[17],"recognizing":[18],"words":[20],"and":[21,75,111,135,151,154,161,196,203,213,218],"semantics":[22],"speech":[25,134],"but":[26],"also":[27],"determining":[28],"role":[30,52,119],"speaker.":[33],"However,":[34],"few":[35],"published":[38],"works":[39],"on":[40,50,172,210],"automatic":[42],"systems":[44],"communication":[48,65],"focus":[49],"speaker":[51,118],"identification":[53,120],"(SRI).":[54],"In":[55],"this":[56],"article,":[57],"we":[58],"formulate":[59],"SRI":[61,88,128,194],"task":[62,129],"as":[66],"a":[67,83,116,178],"binary":[68],"classification":[69],"problem.":[70],"Furthermore,":[71],"text-based,":[73],"speech-based,":[74],"speech-and-text-based":[76],"multi-modal":[77,117],"methods":[78,209],"are":[79,103,170],"proposed":[80,148,198],"to":[81,105,125,149],"achieve":[82,126],"comprehensive":[84],"comparison":[85],"task.":[89],"To":[90,139],"ablate":[91],"impacts":[93],"comparative":[96,168,189],"approaches,":[97],"various":[98],"advanced":[99],"neural":[100],"network":[101,121],"architectures":[102],"applied":[104],"optimize":[106],"implementation":[108],"text-based":[110],"speech-based":[112],"methods.":[113],"Most":[114],"importantly,":[115],"(MMSRINet)":[122],"is":[123,147],"designed":[124],"by":[130,157],"considering":[131],"both":[132,211],"textual":[136,155],"modality":[137,141],"features.":[138],"aggregate":[140],"features,":[142],"modal":[144,158],"fusion":[145],"module":[146],"fuse":[150],"squeeze":[152],"acoustic":[153],"representations":[156],"attention":[159],"mechanism":[160],"self-attention":[162],"pooling":[163],"layer,":[164],"respectively.":[165,221],"Finally,":[166],"approaches":[169,190],"validated":[171],"ATCSpeech":[174],"corpus":[175],"collected":[176],"from":[177],"real-world":[179],"ATC":[180],"environment.":[181],"The":[182],"experimental":[183],"results":[184],"demonstrate":[185],"that":[186],"all":[187],"worked":[191],"for":[192],"task,":[195],"MMSRINet":[199],"shows":[200],"competitive":[201],"performance":[202],"robustness":[204],"compared":[205],"with":[206],"other":[208],"seen":[212],"unseen":[214],"data,":[215],"achieving":[216],"98.56%":[217],"98.08%":[219],"accuracy,":[220]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}