{"id":"https://openalex.org/W4386939203","doi":"https://doi.org/10.1007/978-3-031-44195-0_31","title":"Bring the\u00a0Noise: Introducing Noise Robustness to\u00a0Pretrained Automatic Speech Recognition","display_name":"Bring the\u00a0Noise: Introducing Noise Robustness to\u00a0Pretrained Automatic Speech Recognition","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386939203","doi":"https://doi.org/10.1007/978-3-031-44195-0_31"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-44195-0_31","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-44195-0_31","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-44195-0_31.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-44195-0_31.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014174745","display_name":"Patrick Eickhoff","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":true,"raw_author_name":"Patrick Eickhoff","raw_affiliation_strings":["Knowledge Technology, Department of Informatics, University of Hamburg, Vogt-Koelln-Str. 30, 22527, Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Knowledge Technology, Department of Informatics, University of Hamburg, Vogt-Koelln-Str. 30, 22527, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102772282","display_name":"Matthias M\u00f6ller","orcid":"https://orcid.org/0009-0006-8156-4079"},"institutions":[{"id":"https://openalex.org/I26437253","display_name":"\u00d6rebro University","ror":"https://ror.org/05kytsw45","country_code":"SE","type":"education","lineage":["https://openalex.org/I26437253"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Matthias M\u00f6ller","raw_affiliation_strings":["Centre for Applied Autonomous Sensor Systems (AASS), \u00d6rebro University, \u00d6rebro, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Applied Autonomous Sensor Systems (AASS), \u00d6rebro University, \u00d6rebro, Sweden","institution_ids":["https://openalex.org/I26437253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092489723","display_name":"Theresa Pekarek Rosin","orcid":"https://orcid.org/0000-0002-2847-5097"},"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":"Theresa Pekarek Rosin","raw_affiliation_strings":["Knowledge Technology, Department of Informatics, University of Hamburg, Vogt-Koelln-Str. 30, 22527, Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Knowledge Technology, Department of Informatics, University of Hamburg, Vogt-Koelln-Str. 30, 22527, 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/I4210123704","display_name":"NXP (Germany)","ror":"https://ror.org/0268h4j55","country_code":"DE","type":"company","lineage":["https://openalex.org/I109147379","https://openalex.org/I4210123704"]},{"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, Department of Informatics, University of Hamburg, Vogt-Koelln-Str. 30, 22527, Hamburg, Germany","exXxa GmbH, Vogt-Koelln-Str. 30, 22527, Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Knowledge Technology, Department of Informatics, University of Hamburg, Vogt-Koelln-Str. 30, 22527, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]},{"raw_affiliation_string":"exXxa GmbH, Vogt-Koelln-Str. 30, 22527, Hamburg, Germany","institution_ids":["https://openalex.org/I4210123704"]}]},{"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/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":"Stefan Wermter","raw_affiliation_strings":["Knowledge Technology, Department of Informatics, University of Hamburg, Vogt-Koelln-Str. 30, 22527, Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Knowledge Technology, Department of Informatics, University of Hamburg, Vogt-Koelln-Str. 30, 22527, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5014174745"],"corresponding_institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":1.5163,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.84594686,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"376","last_page":"388"},"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":0.9990000128746033,"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":0.8453480005264282},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7011867761611938},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6851071119308472},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6645945310592651},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5885889530181885},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5670981407165527},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.540371298789978},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49160367250442505},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4879307448863983},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4499174952507019},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3725716471672058},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07635977864265442}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8453480005264282},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7011867761611938},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6851071119308472},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6645945310592651},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5885889530181885},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5670981407165527},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.540371298789978},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49160367250442505},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4879307448863983},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4499174952507019},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3725716471672058},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07635977864265442},{"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-44195-0_31","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-44195-0_31","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-44195-0_31.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.1007/978-3-031-44195-0_31","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-44195-0_31","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-44195-0_31.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4386939203.pdf"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2094721231","https://openalex.org/W2141411743","https://openalex.org/W2398042854","https://openalex.org/W2603567530","https://openalex.org/W2801554275","https://openalex.org/W2937769560","https://openalex.org/W2973215447","https://openalex.org/W3015412285","https://openalex.org/W3097777922","https://openalex.org/W3197580070","https://openalex.org/W3200314169","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4226033575","https://openalex.org/W4372346318","https://openalex.org/W4375869194","https://openalex.org/W6605946209","https://openalex.org/W6739901393","https://openalex.org/W6818723395"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W2011227383","https://openalex.org/W4375868962","https://openalex.org/W2088854863","https://openalex.org/W1976719989","https://openalex.org/W2942893872","https://openalex.org/W2065606036","https://openalex.org/W3179495260","https://openalex.org/W3127543252","https://openalex.org/W2016904525"],"abstract_inverted_index":{"Abstract":[0],"In":[1,81],"recent":[2],"research,":[3],"in":[4,197],"the":[5,49,71,91,104,113,132,174,187,194],"domain":[6],"of":[7,52,193],"speech":[8,182],"processing,":[9],"large":[10],"End-to-End":[11],"(E2E)":[12],"systems":[13,27],"for":[14,66,200],"Automatic":[15],"Speech":[16,134],"Recognition":[17],"(ASR)":[18],"have":[19],"reported":[20],"state-of-the-art":[21],"performance":[22],"on":[23,131],"various":[24],"benchmarks.":[25],"These":[26],"intrinsically":[28],"learn":[29],"how":[30],"to":[31,47,76,89,98,120,123,137,152,163,178],"handle":[32],"and":[33,117,183],"remove":[34],"noise":[35,180],"conditions":[36,199],"from":[37,112,141,169,181],"speech.":[38],"Previous":[39],"research":[40],"has":[41],"shown,":[42],"that":[43,94,108,173,184],"it":[44,185],"is":[45,176],"possible":[46],"extract":[48,90],"denoising":[50,92],"capabilities":[51],"these":[53],"models":[54,168],"into":[55],"a":[56,64,86,121,150,153,161],"preprocessor":[57,106,130],"network,":[58],"which":[59],"can":[60,95],"be":[61,96],"used":[62],"as":[63,149,158,160],"frontend":[65,151,162],"downstream":[67,195],"ASR":[68,115,156,167],"models.":[69],"However,":[70],"proposed":[72],"methods":[73],"were":[74],"limited":[75],"specific":[77],"fully":[78],"convolutional":[79],"architectures.":[80],"this":[82],"work,":[83],"we":[84,145],"propose":[85,103],"novel":[87],"method":[88],"capabilities,":[93],"applied":[97],"any":[99],"encoder-decoder":[100],"architecture.":[101],"We":[102,127,171],"Cleancoder":[105,175],"architecture":[107],"extracts":[109],"hidden":[110],"activations":[111],"Conformer":[114,155,166],"model":[116,148,157,196],"feeds":[118],"them":[119],"decoder":[122],"predict":[124],"denoised":[125,139],"spectrograms.":[126],"train":[128,164],"our":[129,147],"Noisy":[133],"Database":[135],"(NSD)":[136],"reconstruct":[138],"spectrograms":[140],"noisy":[142,198],"inputs.":[143],"Then,":[144],"evaluate":[146],"pretrained":[154],"well":[159],"smaller":[165],"scratch.":[170],"show":[172],"able":[177],"filter":[179],"improves":[186],"total":[188],"Word":[189],"Error":[190],"Rate":[191],"(WER)":[192],"both":[201],"applications.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}