{"id":"https://openalex.org/W4375869028","doi":"https://doi.org/10.1109/icassp49357.2023.10094732","title":"Noise-Aware Target Extension with Self-Distillation for Robust Speech Recognition","display_name":"Noise-Aware Target Extension with Self-Distillation for Robust Speech Recognition","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869028","doi":"https://doi.org/10.1109/icassp49357.2023.10094732"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094732","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10094732","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5007337599","display_name":"Ju-Seok Seong","orcid":null},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ju-Seok Seong","raw_affiliation_strings":["Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea","Department of Electronic Engineering, Hanyang University, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4575257"]},{"raw_affiliation_string":"Department of Electronic Engineering, Hanyang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101610186","display_name":"Jeong-Hwan Choi","orcid":"https://orcid.org/0000-0002-3937-2333"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jeong-Hwan Choi","raw_affiliation_strings":["Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea","Department of Electronic Engineering, Hanyang University, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4575257"]},{"raw_affiliation_string":"Department of Electronic Engineering, Hanyang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039146575","display_name":"Jehyun Kyung","orcid":null},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jehyun Kyung","raw_affiliation_strings":["Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea","Department of Electronic Engineering, Hanyang University, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4575257"]},{"raw_affiliation_string":"Department of Electronic Engineering, Hanyang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090642537","display_name":"Ye-Rin Jeoung","orcid":null},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ye-Rin Jeoung","raw_affiliation_strings":["Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea","Department of Electronic Engineering, Hanyang University, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4575257"]},{"raw_affiliation_string":"Department of Electronic Engineering, Hanyang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002418613","display_name":"Joon\u2010Hyuk Chang","orcid":"https://orcid.org/0000-0003-2610-2323"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon-Hyuk Chang","raw_affiliation_strings":["Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea","Department of Electronic Engineering, Hanyang University, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4575257"]},{"raw_affiliation_string":"Department of Electronic Engineering, Hanyang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4575257"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04153936,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"31","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9998000264167786,"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":0.9991000294685364,"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/noise","display_name":"Noise (video)","score":0.772929310798645},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7183412909507751},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6592097878456116},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6314718127250671},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5966364741325378},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5465578436851501},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.5457836389541626},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.5411393642425537},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47835463285446167},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.4356180429458618},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3835179805755615},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.25981664657592773}],"concepts":[{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.772929310798645},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7183412909507751},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6592097878456116},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6314718127250671},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5966364741325378},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5465578436851501},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.5457836389541626},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.5411393642425537},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47835463285446167},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.4356180429458618},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3835179805755615},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.25981664657592773},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094732","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10094732","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.41999998688697815,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1821462560","https://openalex.org/W1922655562","https://openalex.org/W2024490156","https://openalex.org/W2096653978","https://openalex.org/W2193413348","https://openalex.org/W2219249508","https://openalex.org/W2402146185","https://openalex.org/W2407080277","https://openalex.org/W2510867321","https://openalex.org/W2696967604","https://openalex.org/W2797583228","https://openalex.org/W2807912816","https://openalex.org/W2885724687","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2987861506","https://openalex.org/W3034368386","https://openalex.org/W3138154797","https://openalex.org/W4288093001","https://openalex.org/W6631362777","https://openalex.org/W6638523607","https://openalex.org/W6640090968","https://openalex.org/W6687566353","https://openalex.org/W6688816777","https://openalex.org/W6750665317","https://openalex.org/W6779702771"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175"],"abstract_inverted_index":{"Data":[0],"augmentation":[1],"using":[2],"additive":[3],"noise":[4,17,28,68,76,95],"is":[5,90,137],"a":[6,34,56,78],"framework":[7],"for":[8],"robustly":[9],"training":[10,128],"automatic":[11],"speech":[12],"recognition":[13],"models.":[14],"To":[15],"utilize":[16],"information":[18],"efficiently,":[19],"previous":[20,158],"studies":[21],"used":[22],"an":[23],"additional":[24],"branch":[25,32,47],"to":[26,66,100,116],"classify":[27],"conditions.":[29],"This":[30],"added":[31],"has":[33],"limited":[35],"effect":[36],"on":[37,139],"the":[38,45,63,73,82,85,88,94,102,118,125,134,140,157],"ASR":[39,46],"because":[40],"it":[41],"performs":[42],"independently":[43],"of":[44,87,127,133],"that":[48,61],"classifies":[49],"senones.":[50],"In":[51,81,106],"this":[52],"paper,":[53],"we":[54,108],"propose":[55],"noise-aware":[57],"target":[58,65],"extension":[59],"(NATE)":[60],"extends":[62],"senone":[64,74,103],"contain":[67],"awareness":[69],"by":[70,93],"jointly":[71],"classifying":[72],"and":[75,97,121,129,144,147],"in":[77,153],"single":[79],"branch.":[80],"inference":[83],"stage,":[84],"output":[86],"model":[89,119],"processed":[91],"separately":[92],"condition":[96],"then":[98],"aggregated":[99],"match":[101],"posterior":[104],"distribution.":[105],"addition,":[107],"combine":[109],"NATE":[110,135],"with":[111],"self-distillation":[112],"(NATE<inf":[113],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[114],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">sd</inf>)":[115],"reduce":[117],"parameters":[120],"avoid":[122],"discrepancies":[123],"between":[124],"outputs":[126],"inference.":[130],"The":[131],"effectiveness":[132],"method":[136],"validated":[138],"two":[141],"benchmark":[142],"development":[143],"evaluation":[145],"sets":[146],"simulated":[148],"noisy":[149],"test":[150],"sets,":[151],"resulting":[152],"significant":[154],"improvements":[155],"over":[156],"methods.":[159]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}