{"id":"https://openalex.org/W4415433689","doi":"https://doi.org/10.21437/interspeech.2025-694","title":"Regularizing Learnable Feature Extraction for Automatic Speech Recognition","display_name":"Regularizing Learnable Feature Extraction for Automatic Speech Recognition","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433689","doi":"https://doi.org/10.21437/interspeech.2025-694"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-694","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-694","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.09804","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055945494","display_name":"Peter Vieting","orcid":"https://orcid.org/0000-0002-3582-5382"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peter Vieting","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120093906","display_name":"Maximilian Kannen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maximilian Kannen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034025445","display_name":"Benedikt Hilmes","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Benedikt Hilmes","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088968292","display_name":"Ralf Schl\u00fcter","orcid":"https://orcid.org/0000-0003-2839-9247"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ralf Schl\u00fcter","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5112501010","display_name":"Hermann Ney","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hermann Ney","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14193062,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4943","last_page":"4947"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.944599986076355,"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":0.944599986076355,"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/feature-extraction","display_name":"Feature extraction","score":0.6238999962806702},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5365999937057495},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5242999792098999},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.41429999470710754},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.38370001316070557},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.37700000405311584},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3646000027656555},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.3384000062942505},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.32679998874664307}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6816999912261963},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6664000153541565},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6238999962806702},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5365999937057495},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5242999792098999},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5054000020027161},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.41429999470710754},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.38370001316070557},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.37700000405311584},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3646000027656555},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3384000062942505},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.32679998874664307},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.3075999915599823},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2996000051498413},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.29429998993873596},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.28859999775886536},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.2687000036239624},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.2662000060081482}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-694","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-694","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.09804","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.09804","pdf_url":"https://arxiv.org/pdf/2506.09804","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.09804","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.09804","pdf_url":"https://arxiv.org/pdf/2506.09804","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Neural":[0],"front-ends":[1,97],"are":[2],"an":[3],"appealing":[4],"alternative":[5],"to":[6,24,36,45,49,114],"traditional,":[7],"fixed":[8],"feature":[9,63],"extraction":[10,64],"pipelines":[11],"for":[12,57,81,95],"automatic":[13],"speech":[14],"recognition":[15],"(ASR)":[16],"systems":[17],"since":[18],"they":[19],"can":[20,78],"be":[21,79],"directly":[22],"trained":[23],"fit":[25],"the":[26,90,102,125],"acoustic":[27],"model.":[28],"However,":[29],"their":[30,46],"performance":[31,126],"often":[32],"falls":[33],"short":[34,103],"compared":[35],"classical":[37],"methods,":[38],"which":[39],"we":[40,67,85],"show":[41,73],"is":[42],"largely":[43],"due":[44],"increased":[47],"susceptibility":[48],"overfitting.":[50],"This":[51],"work":[52],"therefore":[53],"investigates":[54],"regularization":[55,121],"methods":[56,71],"training":[58],"ASR":[59],"models":[60],"with":[61],"learnable":[62,82,131],"front-ends.":[65],"First,":[66],"examine":[68],"audio":[69],"perturbation":[70],"and":[72,98,130],"that":[74],"larger":[75],"relative":[76],"improvements":[77],"obtained":[80],"features.":[83,132],"Additionally,":[84],"identify":[86],"two":[87],"limitations":[88],"in":[89,101],"standard":[91],"use":[92],"of":[93],"SpecAugment":[94],"these":[96,116],"propose":[99],"masking":[100],"time":[104],"Fourier":[105],"transform":[106],"(STFT)-domain":[107],"as":[108],"a":[109],"simple":[110],"but":[111],"effective":[112],"modification":[113],"address":[115],"challenges.":[117],"Finally,":[118],"integrating":[119],"both":[120],"approaches":[122],"effectively":[123],"closes":[124],"gap":[127],"between":[128],"traditional":[129]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-23T00:00:00"}