{"id":"https://openalex.org/W4386078174","doi":"https://doi.org/10.1109/taslp.2023.3307219","title":"Towards Recognition for Radio-Echo Speech in Air Traffic Control: Dataset and a Contrastive Learning Approach","display_name":"Towards Recognition for Radio-Echo Speech in Air Traffic Control: Dataset and a Contrastive Learning Approach","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386078174","doi":"https://doi.org/10.1109/taslp.2023.3307219"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3307219","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3307219","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language 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/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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100776177","display_name":"Qingyang Wang","orcid":"https://orcid.org/0009-0007-9040-7312"},"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":"Qingyang Wang","raw_affiliation_strings":["College of Computer Science, Sichuan University, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0007-9040-7312","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/A5068622093","display_name":"Xincheng Yu","orcid":"https://orcid.org/0009-0004-6071-1872"},"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":"Xincheng Yu","raw_affiliation_strings":["College of Computer Science, Sichuan University, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0004-6071-1872","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/A5100739122","display_name":"Zichen Zhang","orcid":"https://orcid.org/0009-0002-5836-7377"},"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":"Zichen Zhang","raw_affiliation_strings":["College of Computer Science, Sichuan University, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0002-5836-7377","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/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":"last","author":{"id":"https://openalex.org/A5003270633","display_name":"Jizhe Zhou","orcid":"https://orcid.org/0000-0002-2447-1806"},"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":"Jizhe Zhou","raw_affiliation_strings":["College of Computer Science, Sichuan University, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-2447-1806","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":0.979,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80602032,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"31","issue":null,"first_page":"3249","last_page":"3262"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9995999932289124,"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":0.9822999835014343,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8073086142539978},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5671765804290771},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5303683280944824},{"id":"https://openalex.org/keywords/echo","display_name":"Echo (communications protocol)","score":0.5254047513008118},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4753406047821045},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4293127655982971},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41925758123397827}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8073086142539978},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5671765804290771},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5303683280944824},{"id":"https://openalex.org/C2779426996","wikidata":"https://www.wikidata.org/wiki/Q18389128","display_name":"Echo (communications protocol)","level":2,"score":0.5254047513008118},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4753406047821045},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4293127655982971},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41925758123397827},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3307219","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3307219","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"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/G709856560","display_name":null,"funder_award_id":"62001315","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1600744878","https://openalex.org/W1990005915","https://openalex.org/W1993882792","https://openalex.org/W1996809249","https://openalex.org/W2002363211","https://openalex.org/W2005708641","https://openalex.org/W2028528924","https://openalex.org/W2036242736","https://openalex.org/W2096733369","https://openalex.org/W2101346879","https://openalex.org/W2125838338","https://openalex.org/W2127141656","https://openalex.org/W2139780242","https://openalex.org/W2160815625","https://openalex.org/W2193413348","https://openalex.org/W2327501763","https://openalex.org/W2510616059","https://openalex.org/W2563053575","https://openalex.org/W2726599793","https://openalex.org/W2744227074","https://openalex.org/W2798991696","https://openalex.org/W2884585870","https://openalex.org/W2888008122","https://openalex.org/W2892009249","https://openalex.org/W2899396049","https://openalex.org/W2914275764","https://openalex.org/W2962780374","https://openalex.org/W2963341071","https://openalex.org/W2963677766","https://openalex.org/W2972389417","https://openalex.org/W2972451902","https://openalex.org/W2973215447","https://openalex.org/W2976884277","https://openalex.org/W2991082564","https://openalex.org/W3005680577","https://openalex.org/W3035524453","https://openalex.org/W3036601975","https://openalex.org/W3081285175","https://openalex.org/W3108655343","https://openalex.org/W3114632476","https://openalex.org/W3129824274","https://openalex.org/W3133953372","https://openalex.org/W3174448166","https://openalex.org/W3197163313","https://openalex.org/W3198608154","https://openalex.org/W3198853881","https://openalex.org/W3212070308","https://openalex.org/W4207024570","https://openalex.org/W4231592584","https://openalex.org/W4283659485","https://openalex.org/W4297808394","https://openalex.org/W4309857275","https://openalex.org/W6640025879","https://openalex.org/W6650759579","https://openalex.org/W6680864898","https://openalex.org/W6687566353","https://openalex.org/W6774314701","https://openalex.org/W6780218876","https://openalex.org/W6803074281","https://openalex.org/W6839738141","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W2309273277","https://openalex.org/W2061937230","https://openalex.org/W1574295218","https://openalex.org/W2547793174","https://openalex.org/W2132658536","https://openalex.org/W2070212102","https://openalex.org/W2544241817","https://openalex.org/W2158882055","https://openalex.org/W2914603036","https://openalex.org/W2124470186"],"abstract_inverted_index":{"In":[0,37],"the":[1,48,52,69,73,90,105,119,134,141,149,160,168,176,189,196,214,220,239],"air":[2],"traffic":[3],"control":[4],"(ATC)":[5],"domain,":[6],"automatic":[7],"speech":[8,14,50,87,138],"recognition":[9],"(ASR)":[10],"suffers":[11],"from":[12],"radio":[13,35],"echo,":[15],"which":[16,159,229],"cannot":[17],"be":[18],"addressed":[19],"by":[20,33,154,225],"existing":[21],"echo":[22],"cancellation":[23],"due":[24],"to":[25,46,82,117,121,166,187,238],"auditory-oriented":[26],"optimization":[27],"and":[28,62,85,110,126,136,185],"poor":[29],"generalization":[30],"ability":[31],"caused":[32],"volatile":[34],"transmission.":[36],"this":[38],"work,":[39],"a":[40,76,94,98,108,155,172,180,208],"contrastive":[41,147,230],"learning-based":[42],"framework":[43],"is":[44,80,114,152,183],"proposed":[45,150,177,190,197,221],"tackle":[47],"radio-echo":[49],"for":[51],"ASR":[53,169],"task":[54],"based":[55],"on":[56,123,213],"convolution":[57],"networks":[58],"with":[59,140,203,232],"multiple":[60],"paths":[61],"recurrent":[63],"neural":[64],"networks.":[65],"1)":[66],"By":[67,145],"analyzing":[68],"communication":[70],"mechanism":[71],"of":[72],"ATC":[74,100],"speech,":[75],"novel":[77],"transmission":[78,178],"method":[79],"designed":[81,116,226],"collect":[83],"clean":[84,135],"noisy":[86,137],"samples":[88],"(with":[89],"same":[91,142],"texts)":[92],"via":[93],"bypass":[95],"device":[96],"in":[97,158,171,228],"real-world":[99,181],"environment.":[101],"2)":[102],"To":[103],"enhance":[104,167],"model":[106,120],"capacity,":[107],"temporal":[109],"frequency":[111],"attention":[112],"block":[113],"innovatively":[115],"guide":[118],"focus":[122],"informative":[124],"frames":[125],"frequencies,":[127],"aiming":[128],"at":[129],"learning":[130,231],"shared":[131],"representations":[132],"between":[133],"signals":[139],"texts.":[143],"3)":[144],"incorporating":[146],"loss,":[148],"approach":[151,198],"implemented":[153],"multi-objective":[156,234],"optimization,":[157],"loss":[161,235],"weights":[162,236],"are":[163,223],"dynamically":[164],"determined":[165],"performance":[170,241],"learnable":[173,233],"manner.":[174],"With":[175],"method,":[179],"dataset":[182],"collected":[184],"annotated":[186],"validate":[188],"approach.":[191],"Experimental":[192],"results":[193],"demonstrate":[194],"that":[195],"outperforms":[199],"other":[200],"comparative":[201],"baselines":[202],"different":[204],"technical":[205],"frameworks,":[206],"achieving":[207],"6.76%":[209],"character":[210],"error":[211],"rate":[212],"test":[215],"dataset.":[216],"Most":[217],"importantly,":[218],"all":[219],"improvements":[222],"confirmed":[224],"experiments,":[227],"contributes":[237],"primary":[240],"improvement.":[242]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
