{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T06:59:37Z","timestamp":1775199577952,"version":"3.50.1"},"reference-count":20,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434603","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":["Robust Speech Emotion Recognition via Classifier Retraining on Mixup-Augmented Representations"],"prefix":"10.1109","author":[{"given":"Shi-Wook","family":"Lee","sequence":"first","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology,Japan"}]}],"member":"263","reference":[{"key":"ref1","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. of NIPS","author":"Baevski"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref3","first-page":"1298","article-title":"data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"Proc. of ICML","author":"Baevski"},{"key":"ref4","first-page":"28492","article-title":"Robust speech recognition via largescale weak supervision","volume-title":"International conference on machine learning. PMLR","author":"Radford"},{"issue":"2","key":"ref5","first-page":"3","article-title":"LoRA: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref7","article-title":"Bitfit: Simple parameter-efficient fine-tuning for transformer-based masked languagemodels","author":"Zaken","year":"2021","journal-title":"ACL Findings"},{"key":"ref8","article-title":"Vicinal risk minimization","volume-title":"Proc. of NeurIPS","author":"Chapelle"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013714"},{"key":"ref11","article-title":"Domainadjusted regression or: ERM may already learn features sufficient for out-of-distribution generalization","volume-title":"Proc. of NeurIPS 2022 Workshop on Distribution Shifts (DistShift)","author":"Rosenfeld"},{"key":"ref12","article-title":"Last layer re-training is sufficient for robustness to spurious correlations","author":"Kirichenko","year":"2022","journal-title":"arXiv preprint arXiv:2204.02937"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref14","article-title":"HuBERT Large"},{"key":"ref15","first-page":"13898","article-title":"Release of pretrained models for the Japanese language","volume-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)","volume":"5","author":"Sawada"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2016.7918977"},{"key":"ref17","article-title":"JVNV: A corpus of Japanese emotional speech with verbal content and nonverbal expressions","author":"Xin","year":"2023","journal-title":"arXiv:2310.06072"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2515617"},{"key":"ref20","first-page":"2579","article-title":"Visualizing high dimensional data using t-SNE","author":"der Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"}],"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\/11434603.pdf?arnumber=11434603","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:56:15Z","timestamp":1775192175000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434603\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434603","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}