{"id":"https://openalex.org/W4400525349","doi":"https://doi.org/10.1109/taslp.2024.3423652","title":"ROSE: A Recognition-Oriented Speech Enhancement Framework in Air Traffic Control Using Multi-Objective Learning","display_name":"ROSE: A Recognition-Oriented Speech Enhancement Framework in Air Traffic Control Using Multi-Objective Learning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4400525349","doi":"https://doi.org/10.1109/taslp.2024.3423652"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3423652","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3423652","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/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/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/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":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0572,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.92347236,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"3365","last_page":"3378"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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/T12031","display_name":"Speech and dialogue systems","score":0.9868999719619751,"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/air-traffic-control","display_name":"Air traffic control","score":0.5824198126792908},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5584953427314758},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5316795706748962},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5208219289779663},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5077341794967651},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37499767541885376},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2234731912612915}],"concepts":[{"id":"https://openalex.org/C166961238","wikidata":"https://www.wikidata.org/wiki/Q221395","display_name":"Air traffic control","level":2,"score":0.5824198126792908},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5584953427314758},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5316795706748962},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5208219289779663},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5077341794967651},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37499767541885376},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2234731912612915},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3423652","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3423652","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/G6307433967","display_name":null,"funder_award_id":"U2333209","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W1956021273","https://openalex.org/W1983812858","https://openalex.org/W1989034586","https://openalex.org/W1995536493","https://openalex.org/W2116593694","https://openalex.org/W2128653836","https://openalex.org/W2141998673","https://openalex.org/W2144404214","https://openalex.org/W2187302915","https://openalex.org/W2290318471","https://openalex.org/W2603567530","https://openalex.org/W2744227074","https://openalex.org/W2752782242","https://openalex.org/W2755177320","https://openalex.org/W2888008122","https://openalex.org/W2888169323","https://openalex.org/W2889134433","https://openalex.org/W2914275764","https://openalex.org/W2940275453","https://openalex.org/W2963341071","https://openalex.org/W2972436155","https://openalex.org/W2973133192","https://openalex.org/W2976884277","https://openalex.org/W2991082564","https://openalex.org/W2998161426","https://openalex.org/W3015338123","https://openalex.org/W3081285175","https://openalex.org/W3095913803","https://openalex.org/W3096008106","https://openalex.org/W3096408984","https://openalex.org/W3097906045","https://openalex.org/W3097945073","https://openalex.org/W3103913581","https://openalex.org/W3129824274","https://openalex.org/W3142252347","https://openalex.org/W3161950572","https://openalex.org/W3174448166","https://openalex.org/W3195797672","https://openalex.org/W3197163313","https://openalex.org/W3197729725","https://openalex.org/W3197912330","https://openalex.org/W3198853881","https://openalex.org/W3206531472","https://openalex.org/W3206809722","https://openalex.org/W3212070308","https://openalex.org/W3213188934","https://openalex.org/W4221144097","https://openalex.org/W4221149546","https://openalex.org/W4231592584","https://openalex.org/W4232282348","https://openalex.org/W4293170326","https://openalex.org/W4296069272","https://openalex.org/W4297841790","https://openalex.org/W4312257080","https://openalex.org/W4312570973","https://openalex.org/W4366667317","https://openalex.org/W4372266577","https://openalex.org/W4385756463","https://openalex.org/W4385822305","https://openalex.org/W4386078174","https://openalex.org/W4392910606","https://openalex.org/W6686932946","https://openalex.org/W6762114000","https://openalex.org/W6798721538","https://openalex.org/W6799474351","https://openalex.org/W6842294372"],"related_works":["https://openalex.org/W4388561773","https://openalex.org/W2123753634","https://openalex.org/W1630865680","https://openalex.org/W4214692512","https://openalex.org/W597539240","https://openalex.org/W2173790754","https://openalex.org/W2107258857","https://openalex.org/W2951616407","https://openalex.org/W3096184950","https://openalex.org/W4231424160"],"abstract_inverted_index":{"Radio":[0],"speech":[1,16,22,32,40],"echo":[2],"is":[3,36,83,113,174],"a":[4,29,56,177],"specific":[5],"phenomenon":[6],"in":[7,59,125,156,176,209],"the":[8,69,75,97,102,118,133,138,144,157,168,186,195,204,212,222,228],"air":[9],"traffic":[10],"control":[11],"(ATC)":[12],"domain,":[13],"which":[14,53,95,210],"degrades":[15],"quality":[17],"and":[18,42,62,108,136,170,206],"further":[19],"impacts":[20],"automatic":[21],"recognition":[23,154],"(ASR)":[24],"accuracy.":[25],"In":[26,74,220],"this":[27],"work,":[28],"time-domain":[30],"recognition-oriented":[31],"enhancement":[33],"(ROSE)":[34],"framework":[35],"proposed":[37,213,223],"to":[38,85,99,116,120,131,152,227],"improve":[39,153],"intelligibility":[41],"also":[43],"advance":[44],"ASR":[45,70,207],"accuracy":[46],"based":[47],"on":[48,122,143,232],"convolutional":[49],"encoder-decoder-based":[50],"U-Net":[51,76],"framework,":[52],"serves":[54],"as":[55],"plug-and-play":[57],"tool":[58],"ATC":[60,158],"scenarios":[61],"does":[63],"not":[64],"require":[65],"additional":[66],"retraining":[67],"of":[68],"model.":[71],"Specifically,":[72],"1)":[73],"architecture,":[77],"an":[78,92],"attention-based":[79],"skip-fusion":[80],"(ABSF)":[81],"module":[82,112],"applied":[84],"mine":[86],"shared":[87,183],"features":[88,124],"from":[89],"encoders":[90],"using":[91],"attention":[93,110,128],"mask,":[94],"enables":[96],"model":[98,119],"effectively":[100],"fuse":[101],"hierarchical":[103],"features.":[104],"2)":[105],"A":[106],"channel":[107],"sequence":[109],"(CSAtt)":[111],"innovatively":[114],"designed":[115,151,218],"guide":[117],"focus":[121],"informative":[123],"dual":[126],"parallel":[127],"paths,":[129],"aiming":[130],"enhance":[132],"effective":[134],"representations":[135,184],"suppress":[137],"interference":[139],"noises.":[140],"3)":[141],"Based":[142],"handcrafted":[145],"features,":[146],"ASR-oriented":[147,171],"optimization":[148],"targets":[149],"are":[150,215],"performance":[155,230],"environment":[159],"by":[160,181,217],"learning":[161,179],"robust":[162],"feature":[163],"representations.":[164],"By":[165],"incorporating":[166],"both":[167,203],"SE-oriented":[169],"losses,":[172],"ROSE":[173,196],"implemented":[175],"multi-objective":[178],"manner":[180],"optimizing":[182],"across":[185],"two":[187],"task":[188],"objectives.":[189],"The":[190],"experimental":[191],"results":[192],"show":[193],"that":[194],"significantly":[197],"outperforms":[198],"other":[199],"state-of-the-art":[200],"methods":[201],"for":[202],"SE":[205],"tasks,":[208],"all":[211],"improvements":[214,231],"confirmed":[216],"experiments.":[219],"addition,":[221],"approach":[224],"can":[225],"contribute":[226],"desired":[229],"public":[233],"datasets.":[234]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}