{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T15:49:24Z","timestamp":1750261764760},"reference-count":17,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"10","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2022,10,1]]},"DOI":"10.1587\/transinf.2022edl8045","type":"journal-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T22:34:01Z","timestamp":1664577241000},"page":"1803-1806","source":"Crossref","is-referenced-by-count":4,"title":["Convolutional Auto-Encoder and Adversarial Domain Adaptation for Cross-Corpus Speech Emotion Recognition"],"prefix":"10.1587","volume":"E105.D","author":[{"given":"Yang","family":"WANG","sequence":"first","affiliation":[{"name":"Key Laboratory of Grain Information Processing and Control, Henan University of Technology, Ministry of Education"},{"name":"College of Information Science and Engineering, Henan University of Technology"}]},{"given":"Hongliang","family":"FU","sequence":"additional","affiliation":[{"name":"Key Laboratory of Grain Information Processing and Control, Henan University of Technology, Ministry of Education"},{"name":"College of Information Science and Engineering, Henan University of Technology"}]},{"given":"Huawei","family":"TAO","sequence":"additional","affiliation":[{"name":"Key Laboratory of Grain Information Processing and Control, Henan University of Technology, Ministry of Education"},{"name":"College of Information Science and Engineering, Henan University of Technology"}]},{"given":"Jing","family":"YANG","sequence":"additional","affiliation":[{"name":"Key Laboratory of Grain Information Processing and Control, Henan University of Technology, Ministry of Education"},{"name":"College of Information Science and Engineering, Henan University of Technology"}]},{"given":"Hongyi","family":"GE","sequence":"additional","affiliation":[{"name":"Key Laboratory of Grain Information Processing and Control, Henan University of Technology, Ministry of Education"},{"name":"College of Information Science and Engineering, Henan University of Technology"}]},{"given":"Yue","family":"XIE","sequence":"additional","affiliation":[{"name":"School of Communication Engineering, Nanjing Institute of Technology"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"publisher","unstructured":"[1] M.B. Ak\u00e7ay and K. O\u011fuz, \u201cSpeech emotion recognition: Emotional models, databases, features, preprocessing methods, supporting modalities, and classifiers,\u201d Speech Communication, vol.116, pp.56-76, 2020. 10.1016\/j.specom.2019.12.001","DOI":"10.1016\/j.specom.2019.12.001"},{"key":"2","doi-asserted-by":"crossref","unstructured":"[2] J. Zhang, L. Jiang, Y. Zong, W. Zheng, and L. Zhao, \u201cCross-Corpus Speech Emotion Recognition Using Joint Distribution Adaptive Regression,\u201d ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, pp.3790-3794, 2021. 10.1109\/icassp39728.2021.9414372","DOI":"10.1109\/ICASSP39728.2021.9414372"},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] S. Latif, J. Qadir, and M. Bilal, \u201cUnsupervised adversarial domain adaptation for cross-lingual speech emotion recognition,\u201d 2019 8th International Conference on Affective Computing and Intelligent Interaction (ACII), IEEE, pp.732-737, 2019. 10.1109\/acii.2019.8925513","DOI":"10.1109\/ACII.2019.8925513"},{"key":"4","doi-asserted-by":"publisher","unstructured":"[4] J. Gideon, M.G. McInnis, and E.M. Provost, \u201cImproving cross-corpus speech emotion recognition with adversarial discriminative domain generalization (addog),\u201d IEEE Transactions on Affective Computing, vol.12, no.4, pp.1055-1068, 2021. 10.1109\/taffc.2019.2916092","DOI":"10.1109\/TAFFC.2019.2916092"},{"key":"5","doi-asserted-by":"publisher","unstructured":"[5] J. Liu, W. Zheng, Y. Zong, C. Lu, and C. Tang, \u201cCross-corpus speech emotion recognition based on deep domain-adaptive convolutional neural network,\u201d IEICE Trans. Inf. & Syst., vol.E103-D, no.2, pp.459-463, 2020. 10.1587\/transinf.2019edl8136","DOI":"10.1587\/transinf.2019EDL8136"},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] Y. Gao, J. Liu, L. Wang, and J. Dang, \u201cDomain-Adversarial Autoencoder with Attention Based Feature Level Fusion for Speech Emotion Recognition,\u201d ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, pp.6314-6318, 2021. 10.1109\/icassp39728.2021.9413710","DOI":"10.1109\/ICASSP39728.2021.9413710"},{"key":"7","doi-asserted-by":"publisher","unstructured":"[7] M. Abdelwahab and C. Busso, \u201cDomain adversarial for acoustic emotion recognition,\u201d IEEE\/ACM Trans. Audio, Speech, Lang. Process, vol.26, no.12, pp.2423-2435, 2018. 10.1109\/taslp.2018.2867099","DOI":"10.1109\/TASLP.2018.2867099"},{"key":"8","unstructured":"[8] S. Arora, R. Ge, Y. Liang, T. Ma, and Y. Zhang, \u201cGeneralization and equilibrium in generative adversarial nets (gans),\u201d In International Conference on Machine Learning, PMLR, pp.224-232, 2017. 10.1145\/3188745.3232194"},{"key":"9","doi-asserted-by":"publisher","unstructured":"[9] W. Wang, H. Li, Z. Ding, F. Nie, J. Chen, X. Dong, and Z. Wang, \u201cRethinking maximum mean discrepancy for visual domain adaptation,\u201d IEEE Trans. Neural Netw. Learn. Syst, pp.1-14, 2021. 10.1109\/tnnls.2021.3093468","DOI":"10.1109\/TNNLS.2021.3093468"},{"key":"10","doi-asserted-by":"publisher","unstructured":"[10] Mustaqeem and S. Kwon, \u201cMLT-DNet: Speech emotion recognition using 1D dilated CNN based on multi-learning trick approach,\u201d Expert Systems with Applications, vol.167, 2021. 10.1016\/j.eswa.2020.114177","DOI":"10.1016\/j.eswa.2020.114177"},{"key":"11","doi-asserted-by":"publisher","unstructured":"[11] S. Zhang, X. Tao, Y. Chuang, and X. Zhao, \u201cLearning deep multimodal affective features for spontaneous speech emotion recognition,\u201d Speech Communication, vol.127, pp.73-81, 2021. 10.1016\/j.specom.2020.12.009","DOI":"10.1016\/j.specom.2020.12.009"},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] F. Burkhardt, A. Paeschke, M. Rolfes, W.F. Sendlmeier, and B. Weiss, \u201cA database of german emotional speech,\u201d Ninth European Conference on Speech Communication and Technology, pp.1517-1520, 2005. 10.21437\/interspeech.2005-446","DOI":"10.21437\/Interspeech.2005-446"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] O. Martin, I. Kotsia, B. Macq, and I. Pitas, \u201cThe eNTERFACE'05 audio-visual emotion database,\u201d 22nd International Conference on Data Engineering Workshops (ICDEW'06), p.8, IEEE, 2006. 10.1109\/icdew.2006.145","DOI":"10.1109\/ICDEW.2006.145"},{"key":"14","unstructured":"[14] J. Tao, F. Liu, M. Zhang, and H. Jia, \u201cDesign of speech corpus for mandarin text to speech,\u201d The Blizzard Challenge 2008 Workshop, 2008."},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] B. Schuller, S. Steidl, A. Batliner, F. Burkhardt, L. Devillers, C. M\u00fcller, and S.S. Narayanan, \u201cThe INTERSPEECH 2010 paralinguistic challenge,\u201d INTERSPEECH, pp.2794-2797, 2010. 10.21437\/interspeech.2010-739","DOI":"10.21437\/Interspeech.2010-739"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] F. Eyben, M. W\u00f6llmer, and B. Schuller, \u201cOpensmile: the munich versatile and fast open-source audio feature extractor,\u201d Proceedings of the 18th ACM international conference on Multimedia, pp.1459-1462, ACM, 2010. 10.1145\/1873951.1874246","DOI":"10.1145\/1873951.1874246"},{"key":"17","doi-asserted-by":"publisher","unstructured":"[17] J. Li, E. Chen, Z. Ding, L. Zhu, K. Lu, and H.T. Shen, \u201cMaximum density divergence for domain adaptation,\u201d IEEE Trans. Pattern Anal. Mach. Intell., vol.43, no.11, pp.3918-3930, 2020. 10.1109\/tpami.2020.2991050","DOI":"10.1109\/TPAMI.2020.2991050"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E105.D\/10\/E105.D_2022EDL8045\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,9]],"date-time":"2024-05-09T04:56:00Z","timestamp":1715230560000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E105.D\/10\/E105.D_2022EDL8045\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,1]]},"references-count":17,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2022]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2022edl8045","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,1]]},"article-number":"2022EDL8045"}}