{"id":"https://openalex.org/W7148485077","doi":"https://doi.org/10.1109/asru65441.2025.11434661","title":"DeCRED: Decoder-Centric Regularization for Encoder-Decoder Based Speech Recognition","display_name":"DeCRED: Decoder-Centric Regularization for Encoder-Decoder Based Speech Recognition","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148485077","doi":"https://doi.org/10.1109/asru65441.2025.11434661"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434661","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434661","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5114369422","display_name":"Alexander Polok","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":true,"raw_author_name":"Alexander Polok","raw_affiliation_strings":["Brno University of Technology,Brno,Czech Republic"],"affiliations":[{"raw_affiliation_string":"Brno University of Technology,Brno,Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008468618","display_name":"Santosh Kesiraju","orcid":"https://orcid.org/0000-0002-3725-742X"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Santosh Kesiraju","raw_affiliation_strings":["Brno University of Technology,Brno,Czech Republic"],"affiliations":[{"raw_affiliation_string":"Brno University of Technology,Brno,Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056785364","display_name":"Karel Bene\u0161","orcid":"https://orcid.org/0000-0002-0805-1860"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Karel Bene\u0161","raw_affiliation_strings":["Brno University of Technology,Brno,Czech Republic"],"affiliations":[{"raw_affiliation_string":"Brno University of Technology,Brno,Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007614006","display_name":"Bolaji Yusuf","orcid":"https://orcid.org/0000-0001-9852-3456"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Bolaji Yusuf","raw_affiliation_strings":["Brno University of Technology,Brno,Czech Republic"],"affiliations":[{"raw_affiliation_string":"Brno University of Technology,Brno,Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122120306","display_name":"Luk\u00e1\u0161 Burget","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Luk\u00e1\u0161 Burget","raw_affiliation_strings":["Brno University of Technology,Brno,Czech Republic"],"affiliations":[{"raw_affiliation_string":"Brno University of Technology,Brno,Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132804916","display_name":"Jan \u010cernock\u00fd","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan \u010cernock\u00fd","raw_affiliation_strings":["Brno University of Technology,Brno,Czech Republic"],"affiliations":[{"raw_affiliation_string":"Brno University of Technology,Brno,Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5114369422"],"corresponding_institution_ids":["https://openalex.org/I60587646"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87359212,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8858000040054321,"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":0.8858000040054321,"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":0.08560000360012054,"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/T10863","display_name":"Voice and Speech Disorders","score":0.00800000037997961,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.7038999795913696},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6743999719619751},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.48429998755455017},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.3903000056743622},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3718000054359436},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3628999888896942}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.7038999795913696},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6743999719619751},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6085000038146973},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5424000024795532},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.48429998755455017},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46070000529289246},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.3903000056743622},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3718000054359436},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3628999888896942},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3179999887943268},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C141718189","wikidata":"https://www.wikidata.org/wiki/Q7309628","display_name":"Regularization perspectives on support vector machines","level":4,"score":0.31540000438690186},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2590999901294708}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434661","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434661","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311649","display_name":"Ministry of Education","ror":"https://ror.org/036nq5137"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2083751884","https://openalex.org/W2127141656","https://openalex.org/W2166637769","https://openalex.org/W2799473636","https://openalex.org/W2962780374","https://openalex.org/W2963122170","https://openalex.org/W2963250244","https://openalex.org/W2964038834","https://openalex.org/W2964110616","https://openalex.org/W3016234571","https://openalex.org/W3019321633","https://openalex.org/W3097777922","https://openalex.org/W3152221657","https://openalex.org/W3162249256","https://openalex.org/W3197140813","https://openalex.org/W3198439131","https://openalex.org/W3198638539","https://openalex.org/W3198694222","https://openalex.org/W4224934179","https://openalex.org/W4319862255","https://openalex.org/W4319862635","https://openalex.org/W4391021675","https://openalex.org/W4402111558","https://openalex.org/W4402112192","https://openalex.org/W4408356075"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3],"simple":[4],"yet":[5],"effective":[6],"regularization":[7,118],"for":[8],"the":[9,15,44,56,77,113],"internal":[10,58],"language":[11],"model":[12],"induced":[13],"by":[14,62,119],"decoder":[16],"in":[17,26,37,79],"encoder-decoder":[18],"ASR":[19],"models,":[20],"thereby":[21],"improving":[22],"robustness":[23],"and":[24,29,84,98,115,122,132],"generalization":[25],"both":[27],"in-":[28],"out-of-domain":[30,88],"settings.":[31],"The":[32],"proposed":[33],"method,":[34],"Decoder-Centric":[35],"Regularization":[36],"EncoderDecoder":[38],"(DeCRED),":[39],"adds":[40],"auxiliary":[41],"classifiers":[42],"to":[43,65,96,101],"decoder,":[45],"enabling":[46],"next":[47],"token":[48],"prediction":[49],"via":[50],"intermediate":[51],"logits.":[52],"Empirically,":[53],"DeCRED":[54,107,128],"reduces":[55],"mean":[57],"LM":[59],"BPE":[60],"perplexity":[61],"36.6%":[63],"relative":[64],"11":[66],"test":[67,89],"sets.":[68],"Furthermore,":[69],"this":[70],"translates":[71],"into":[72],"actual":[73],"WER":[74,93],"improvements":[75],"over":[76],"baseline":[78,114],"5":[80],"of":[81,86],"7":[82],"in-domain":[83],"3":[85],"4":[87],"sets,":[90],"reducing":[91],"macro":[92],"from":[94],"6.4%":[95],"6.3%":[97],"18.2":[99],"%":[100,110,121],"16.2":[102],"%,":[103],"respectively.":[104,124],"On":[105],"TEDLIUM3,":[106],"achieves":[108],"7.0":[109],"WER,":[111],"surpassing":[112],"encoder-centric":[116],"InterCTC":[117],"0.6":[120],"0.5%,":[123],"Finally,":[125],"we":[126],"compare":[127],"with":[129,143],"OWSM":[130],"v3.1":[131],"Whisper-medium,":[133],"showing":[134],"competitive":[135],"WERs":[136],"despite":[137],"training":[138],"on":[139],"much":[140],"less":[141],"data":[142],"fewer":[144],"parameters.":[145]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-04-03T00:00:00"}