{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,18]],"date-time":"2025-01-18T05:07:37Z","timestamp":1737176857689,"version":"3.33.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832334","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"533-539","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Domain Generalization in Speech Emotion Recognition by Combining Domain-Variant Representations and Domain-Invariant Classifiers"],"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","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1140.001.0001"},{"key":"ref2","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":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref6","article-title":"Spurious correlations in machine learning: A survey","author":"Ye","year":"2024","journal-title":"arXiv:2402.12715v2"},{"article-title":"Learning debiased representation via disentangled feature augmentation","volume-title":"Proc. of NeurIPS","author":"Lee","key":"ref7"},{"article-title":"Distributionally robust neural networks","volume-title":"Proc. of ICLR","author":"Sagawa","key":"ref8"},{"key":"ref9","first-page":"1459","article-title":"openSMILE-the munich versatile and fast open-source audio feature extractor","volume-title":"Proc. of ACM Multimedia","author":"Eyben"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263585"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096370"},{"key":"ref14","article-title":"Invariant risk minimization","author":"Arjovsky","year":"2019","journal-title":"arXiv:1907.02893"},{"key":"ref15","article-title":"The risks of invariant risk minimization","author":"Rosenfeld","year":"2020","journal-title":"arXiv:2010.05761"},{"key":"ref16","article-title":"The missing invariance principle found-the reciprocal twin of invariant risk minimization","author":"Huh","year":"2022","journal-title":"arXiv:2205.14546"},{"article-title":"Spuriosity didn\u2019t kill the classifier: Using invariant predictions to harness spurious features","volume-title":"Proc. of NeurIPS","author":"Eastwood","key":"ref17"},{"article-title":"Overparameterisation and worst-case generalisation: friend or foe?","volume-title":"Proc. of ICLR","author":"Menon","key":"ref18"},{"article-title":"Last layer re-training is sufficient for robustness to spurious correlations","volume-title":"Proc. of ICLR","author":"Kirichenko","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1502.03167"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2016.7918977"},{"key":"ref22","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":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2515617"},{"key":"ref25","article-title":"HuBERT Large"},{"key":"ref26","first-page":"2579","article-title":"Visualizing high dimensional data using t-sne","author":"Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2024,12,2]]},"location":"Macao","end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832334.pdf?arnumber=10832334","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T07:50:31Z","timestamp":1737100231000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832334\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832334","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}