{"id":"https://openalex.org/W3200314169","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533390","title":"Controlling the Noise Robustness of End-to-End Automatic Speech Recognition Systems","display_name":"Controlling the Noise Robustness of End-to-End Automatic Speech Recognition Systems","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3200314169","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533390","mag":"3200314169"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9533390","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533390","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","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/A5102772282","display_name":"Matthias M\u00f6ller","orcid":"https://orcid.org/0009-0006-8156-4079"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]},{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Matthias M\u00f6ller","raw_affiliation_strings":["Knowledge Technology, University of Hamburg, Germany,Department of Informatics,Hamburg,Germany","Knowledge Technology, University of Hamburg, Germany, Hamburg, Germany"],"affiliations":[{"raw_affiliation_string":"Knowledge Technology, University of Hamburg, Germany,Department of Informatics,Hamburg,Germany","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]},{"raw_affiliation_string":"Knowledge Technology, University of Hamburg, Germany, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040807269","display_name":"Johannes Twiefel","orcid":null},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]},{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Johannes Twiefel","raw_affiliation_strings":["Knowledge Technology, University of Hamburg, Germany,Department of Informatics,Hamburg,Germany","Knowledge Technology, University of Hamburg, Germany, Hamburg, Germany"],"affiliations":[{"raw_affiliation_string":"Knowledge Technology, University of Hamburg, Germany,Department of Informatics,Hamburg,Germany","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]},{"raw_affiliation_string":"Knowledge Technology, University of Hamburg, Germany, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102025003","display_name":"Cornelius Weber","orcid":"https://orcid.org/0000-0001-5163-938X"},"institutions":[{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]},{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Cornelius Weber","raw_affiliation_strings":["Knowledge Technology, University of Hamburg, Germany,Department of Informatics,Hamburg,Germany","Knowledge Technology, University of Hamburg, Germany, Hamburg, Germany"],"affiliations":[{"raw_affiliation_string":"Knowledge Technology, University of Hamburg, Germany,Department of Informatics,Hamburg,Germany","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]},{"raw_affiliation_string":"Knowledge Technology, University of Hamburg, Germany, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033486668","display_name":"Stefan Wermter","orcid":"https://orcid.org/0000-0003-1343-4775"},"institutions":[{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]},{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Wermter","raw_affiliation_strings":["Knowledge Technology, University of Hamburg, Germany,Department of Informatics,Hamburg,Germany","Knowledge Technology, University of Hamburg, Germany, Hamburg, Germany"],"affiliations":[{"raw_affiliation_string":"Knowledge Technology, University of Hamburg, Germany,Department of Informatics,Hamburg,Germany","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]},{"raw_affiliation_string":"Knowledge Technology, University of Hamburg, Germany, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102772282"],"corresponding_institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"],"apc_list":null,"apc_paid":null,"fwci":0.136,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.5513539,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9998999834060669,"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/computer-science","display_name":"Computer science","score":0.7750140428543091},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7567973732948303},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.705273449420929},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6839886903762817},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5550596117973328},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5233989357948303},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5193544626235962},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.4773126542568207},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4458004832267761},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.40466734766960144},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3811527490615845},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3287246823310852}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7750140428543091},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7567973732948303},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.705273449420929},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6839886903762817},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5550596117973328},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5233989357948303},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5193544626235962},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.4773126542568207},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4458004832267761},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.40466734766960144},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3811527490615845},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3287246823310852},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9533390","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533390","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7799999713897705}],"awards":[{"id":"https://openalex.org/G7226905331","display_name":null,"funder_award_id":"TRR-169","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1836465849","https://openalex.org/W1922655562","https://openalex.org/W1938755728","https://openalex.org/W1971243715","https://openalex.org/W1980274578","https://openalex.org/W1983108229","https://openalex.org/W2059450962","https://openalex.org/W2094721231","https://openalex.org/W2514828952","https://openalex.org/W2520160253","https://openalex.org/W2603567530","https://openalex.org/W2757519008","https://openalex.org/W2781384251","https://openalex.org/W2888493875","https://openalex.org/W2904818793","https://openalex.org/W2945697643","https://openalex.org/W2949117887","https://openalex.org/W2951559648","https://openalex.org/W2963321191","https://openalex.org/W2963609956","https://openalex.org/W2973215447","https://openalex.org/W3015412285","https://openalex.org/W3204950929","https://openalex.org/W4232282348","https://openalex.org/W4297818305","https://openalex.org/W6638667902","https://openalex.org/W6640090968","https://openalex.org/W6640598943","https://openalex.org/W6727336983","https://openalex.org/W6747270024","https://openalex.org/W6757424787","https://openalex.org/W6762625080","https://openalex.org/W6770686167","https://openalex.org/W6780493881"],"related_works":["https://openalex.org/W4396816926","https://openalex.org/W2593532750","https://openalex.org/W2642467014","https://openalex.org/W2889523925","https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W3126788496","https://openalex.org/W284174822"],"abstract_inverted_index":{"In":[0],"this":[1,32,43],"work,":[2],"we":[3,116,178],"propose":[4],"a":[5,52,61,99,164],"novel":[6],"training":[7,14,181],"scheme":[8,15,44],"to":[9,27,45,101,152],"modularize":[10],"end-to-end":[11,25],"systems.":[12],"Our":[13,79,96],"aims":[16],"at":[17],"altering":[18],"the":[19,29,47,106,110,119,125,141,194],"flow":[20],"of":[21,31,109,193],"information":[22],"in":[23,121,128,140,174,189,197],"an":[24,85,190],"system":[26,33,36,58,87,112,167,184,196],"use":[28],"kernels":[30],"for":[34],"another":[35,39,182],"that":[37,157,180],"fulfills":[38],"task.":[40],"We":[41,155],"apply":[42],"extract":[46],"noise":[48],"reduction":[49],"capabilities":[50],"from":[51,64,71],"noise-robust":[53],"automatic":[54],"speech":[55,62,103,153,172,213],"recognition":[56,173],"(ASR)":[57],"and":[59,74,92,124,170],"implement":[60],"enhancer":[63,67,80],"it.":[65],"This":[66],"receives":[68],"spectral":[69,77,132,142],"representations":[70,133],"unfiltered":[72],"audio":[73],"outputs":[75],"cleaned":[76],"representations.":[78],"can":[81,160],"be":[82,161],"integrated":[83],"into":[84],"ASR":[86,111,166,183,195,205],"as":[88,168,199,201],"front-end,":[89],"is":[90,208],"trainable,":[91],"reduces":[93],"background":[94,136],"noise.":[95,137],"front-end":[97,159,187],"uses":[98],"decoder":[100,123],"clean":[102],"based":[104],"on":[105,211],"hidden":[107],"activations":[108],"Jasper.":[113,129],"While":[114],"training,":[115],"exclusively":[117],"adapt":[118],"weights":[120],"our":[122,158,186],"batch":[126],"normalization":[127],"The":[130,204],"resulting":[131],"show":[134,179],"less":[135],"Further,":[138,177],"areas":[139],"features":[143],"are":[144],"not":[145,150],"reconstructed":[146],"if":[147],"they":[148],"do":[149],"contribute":[151],"recognition.":[154],"demonstrate":[156],"combined":[162],"with":[163,185],"pre-trained":[165],"back-end":[169],"supports":[171],"noisy":[175,198],"conditions.":[176,203],"results":[188],"increased":[191],"performance":[192,207],"well":[200],"noiseless":[202],"system's":[206],"especially":[209],"improved":[210],"challenging":[212],"datasets.":[214]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
