{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:04:11Z","timestamp":1775199851541,"version":"3.50.1"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100009950","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100009950","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434661","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["DeCRED: Decoder-Centric Regularization for Encoder-Decoder Based Speech Recognition"],"prefix":"10.1109","author":[{"given":"Alexander","family":"Polok","sequence":"first","affiliation":[{"name":"Brno University of Technology,Brno,Czech Republic"}]},{"given":"Santosh","family":"Kesiraju","sequence":"additional","affiliation":[{"name":"Brno University of Technology,Brno,Czech Republic"}]},{"given":"Karel","family":"Bene\u0161","sequence":"additional","affiliation":[{"name":"Brno University of Technology,Brno,Czech Republic"}]},{"given":"Bolaji","family":"Yusuf","sequence":"additional","affiliation":[{"name":"Brno University of Technology,Brno,Czech Republic"}]},{"given":"Luk\u00e1\u0161","family":"Burget","sequence":"additional","affiliation":[{"name":"Brno University of Technology,Brno,Czech Republic"}]},{"given":"Jan","family":"\u010cernock\u00fd","sequence":"additional","affiliation":[{"name":"Brno University of Technology,Brno,Czech Republic"}]}],"member":"263","reference":[{"key":"ref1","article-title":"SpecAugment: A simple data augmentation method for automatic speech recognition","author":"Park","year":"2019","journal-title":"ISCA"},{"key":"ref2","article-title":"Regularizing neural networks by penalizing confident output distributions","volume-title":"5th International Conference on Learning Representations, ICLR. OpenReview.net","author":"Pereyra"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2517"},{"key":"ref4","article-title":"Joint CTC\/attention decoding for end-to-end speech recognition","volume-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics","volume":"1","author":"Hori"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414594"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref7","article-title":"SpeechBrain: A generalpurpose speech toolkit","author":"Ravanelli","journal-title":"arXiv:2106.04624."},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.1109\/SLT.2018.8639610","article-title":"Toward domain-invariant speech recognition via large scale training","volume-title":"IEEE Spoken Language Technology Workshop (SLT).","author":"Narayanan"},{"key":"ref9","article-title":"SpeechStew: Simply mix all available speech recognition data to train one large neural network","author":"Chan","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2294"},{"key":"ref11","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proceedings of the 40th International Conference on Machine Learning.","author":"Radford"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389676"},{"key":"ref13","article-title":"OWLS: Scaling laws for multilingual speech recognition and translation models","author":"Chen"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1255"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889577"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-911"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747022"},{"key":"ref18","article-title":"Intermediate-layer output regularization for attention-based speech recognition with shared decoder","author":"Zhang","journal-title":"arXiv:2207.04177."},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.1109\/SLT54892.2023.10022656","article-title":"E-Branchformer: Branchformer with enhanced merging for speech recognition","volume-title":"IEEE Spoken Language Technology Workshop (SLT)","author":"Kim"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-007-9040-x"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1109\/SLT54892.2023.10023141","article-title":"FLEURS: Few-Shot Learning Evaluation of Universal Representations of Speech","volume-title":"2022 IEEE Spoken Language Technology Workshop (SLT)","author":"Conneau"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref23","article-title":"Earnings-22: A practical benchmark for accents in the wild","author":"Rio","journal-title":"arXiv:2203.15591."},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P19-1285","article-title":"Transformer-XL: Attentive language models beyond a fixed-length context","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics.","author":"Dai"},{"key":"ref26","doi-asserted-by":"crossref","article-title":"Conformer: Convolutionaugmented Transformer for speech recognition","author":"Gulati","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D18-2012","article-title":"SentencePiece: A simple and language independent subword tokenizer and detokenizer for neural text processing","volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing: System Demonstrations.","author":"Kudo"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225858"},{"key":"ref29","article-title":"The design for the Wall Street Journalbased CSR corpus","volume-title":"Speech and Natural Language: Proceedings of a Workshop","author":"Paul"},{"key":"ref30","article-title":"Common Voice: A massively-multilingual speech corpus","volume-title":"Proceedings of the Twelfth Language Resources and Evaluation Conference.","author":"Ardila"},{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP.2015.7178964","article-title":"Librispeech: An ASR corpus based on public domain audio books","volume-title":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Panayotov"},{"key":"ref32","article-title":"VoxPopuli: A large-scale multilingual speech corpus for representation learning, semi-supervised learning and interpretation","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing","volume":"1","author":"Wang"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99579-3_21"},{"key":"ref34","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations. OpenReview.net","author":"Loshchilov"},{"key":"ref35","article-title":"Confidence intervals for evaluation in machine learning","author":"Ferrer"},{"key":"ref36","article-title":"On calibration of modern neural networks","volume-title":"Proceedings of the 34th ICML","volume":"70","author":"Guo"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-176"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1194"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053600"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383515"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-020-09734-4"},{"key":"ref42","article-title":"Open automatic speech recognition leaderboard","author":"Srivastav","year":"2023"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434661.pdf?arnumber=11434661","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:58:01Z","timestamp":1775192281000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434661\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434661","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}