{"id":"https://openalex.org/W4362456643","doi":"https://doi.org/10.1587/transinf.2022edp7151","title":"Speech Recognition for Air Traffic Control via Feature Learning and End-to-End Training","display_name":"Speech Recognition for Air Traffic Control via Feature Learning and End-to-End Training","publication_year":2023,"publication_date":"2023-03-31","ids":{"openalex":"https://openalex.org/W4362456643","doi":"https://doi.org/10.1587/transinf.2022edp7151"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2022edp7151","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2022edp7151","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E106.D/4/E106.D_2022EDP7151/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E106.D/4/E106.D_2022EDP7151/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Peng FAN","orcid":null},"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":true,"raw_author_name":"Peng FAN","raw_affiliation_strings":["National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076368122","display_name":"Xiyao Hua","orcid":null},"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":"Xiyao HUA","raw_affiliation_strings":["College of Computer Science, Sichuan University"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Sichuan University","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi LIN","raw_affiliation_strings":["College of Computer Science, Sichuan University"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Sichuan University","institution_ids":["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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo YANG","raw_affiliation_strings":["College of Computer Science, Sichuan University"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Sichuan University","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004051958","display_name":"Jianwei ZHANG","orcid":null},"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":"Jianwei ZHANG","raw_affiliation_strings":["College of Computer Science, Sichuan University"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Sichuan University","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000497500","display_name":"Wenyi Ge","orcid":"https://orcid.org/0009-0006-2731-6074"},"institutions":[{"id":"https://openalex.org/I24201400","display_name":"Chengdu University of Information Technology","ror":"https://ror.org/01yxwrh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I24201400"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenyi GE","raw_affiliation_strings":["College of Computer Science, Chengdu University of Information Technology"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Chengdu University of Information Technology","institution_ids":["https://openalex.org/I24201400"]}]},{"author_position":"last","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"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University","institution_ids":["https://openalex.org/I24185976"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24185976"],"apc_list":null,"apc_paid":null,"fwci":1.1991,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.82495137,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"E106.D","issue":"4","first_page":"538","last_page":"544"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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":0.9965000152587891,"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":0.8637874126434326},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6841001510620117},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5949654579162598},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5715398192405701},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5477792024612427},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5378415584564209},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5365005135536194},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.49569737911224365},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.49531927704811096},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.45593398809432983},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.44800856709480286},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.38566407561302185},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33239084482192993}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8637874126434326},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6841001510620117},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5949654579162598},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5715398192405701},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5477792024612427},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5378415584564209},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5365005135536194},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.49569737911224365},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.49531927704811096},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.45593398809432983},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.44800856709480286},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.38566407561302185},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33239084482192993},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2022edp7151","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2022edp7151","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E106.D/4/E106.D_2022EDP7151/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2022edp7151","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2022edp7151","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E106.D/4/E106.D_2022EDP7151/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6399999856948853,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G4792687924","display_name":null,"funder_award_id":"20161","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G5802907242","display_name":null,"funder_award_id":"2021SCU1205","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G6854498392","display_name":null,"funder_award_id":"FZ2021KF04","funder_id":"https://openalex.org/F4320324522","funder_display_name":"Civil Aviation Administration 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/F4320324522","display_name":"Civil Aviation Administration of China","ror":"https://ror.org/05gfwht30"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4362456643.pdf"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1600744878","https://openalex.org/W2074788634","https://openalex.org/W2127141656","https://openalex.org/W2193413348","https://openalex.org/W2526425061","https://openalex.org/W2545177271","https://openalex.org/W2901616798","https://openalex.org/W2953190524","https://openalex.org/W2964052309","https://openalex.org/W2973049979","https://openalex.org/W2973215447","https://openalex.org/W2976884277","https://openalex.org/W2991082564","https://openalex.org/W3015579786","https://openalex.org/W3036877952","https://openalex.org/W3081285175","https://openalex.org/W3096631876","https://openalex.org/W3097777922","https://openalex.org/W3122931219","https://openalex.org/W3124414150","https://openalex.org/W3129824274","https://openalex.org/W3133953372","https://openalex.org/W3155427814","https://openalex.org/W3198744226","https://openalex.org/W3212070308","https://openalex.org/W4224918898","https://openalex.org/W4296068432","https://openalex.org/W4297841858","https://openalex.org/W4309857275"],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W1732468982","https://openalex.org/W1761388607","https://openalex.org/W1997922073","https://openalex.org/W350032239","https://openalex.org/W2604685715","https://openalex.org/W2412160900","https://openalex.org/W2136453575","https://openalex.org/W1596913645"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3],"propose":[4],"a":[5,62,120,147,162,180],"new":[6],"automatic":[7],"speech":[8],"recognition":[9],"(ASR)":[10],"system":[11],"based":[12],"on":[13,161],"feature":[14,32],"learning":[15,33,63],"and":[16,39,80,153,167],"an":[17,46],"end-to-end":[18,47,122],"training":[19],"procedure":[20],"for":[21,74,99],"air":[22],"traffic":[23],"control":[24],"(ATC)":[25],"systems.":[26],"The":[27,156],"proposed":[28,114,157,174],"model":[29,115],"integrates":[30],"the":[31,51,59,78,88,96,100,105,113,130,134,142,168,173],"block,":[34],"recurrent":[35],"neural":[36],"network":[37],"(RNN),":[38],"connectionist":[40],"temporal":[41,101],"classification":[42],"loss":[43],"to":[44,67,86,95,104,107,127,140],"build":[45],"ASR":[48,143],"model.":[49],"Facing":[50],"complex":[52],"environments":[53],"of":[54,58,150],"ATC":[55,135],"speech,":[56],"instead":[57],"handcrafted":[60],"features,":[61],"block":[64],"is":[65,137,159],"designed":[66],"extract":[68],"informative":[69],"features":[70],"from":[71,110,125],"raw":[72,89,111],"waveforms":[73],"acoustic":[75],"modeling.":[76,102],"Both":[77],"SincNet":[79],"1D":[81],"convolution":[82],"blocks":[83],"are":[84,93],"applied":[85],"process":[87],"waveforms,":[90,112],"whose":[91],"outputs":[92],"concatenated":[94],"RNN":[97],"layers":[98],"Thanks":[103],"ability":[106],"learn":[108],"representations":[109],"can":[116],"be":[117],"optimized":[118],"in":[119,133],"complete":[121],"manner,":[123],"i.e.,":[124],"waveform":[126],"text.":[128],"Finally,":[129],"multilingual":[131,163],"issue":[132],"domain":[136],"also":[138],"considered":[139],"achieve":[141],"task":[144],"by":[145],"constructing":[146],"combined":[148],"vocabulary":[149],"Chinese":[151],"characters":[152],"English":[154],"letters.":[155],"approach":[158,175],"validated":[160],"real-world":[164],"corpus":[165],"(ATCSpeech),":[166],"experimental":[169],"results":[170],"demonstrate":[171],"that":[172],"outperforms":[176],"other":[177],"baselines,":[178],"achieving":[179],"6.9%":[181],"character":[182],"error":[183],"rate.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
