[1]X. LI^*, X. Shi, D. Hu, Y. Li, Q. Zhang, Z. Wang, M. Unoki, and M. Akagi.”Music Theory-inspired Acoustic Representation for Speech Emotion Recognition,”IEEE/ACM Transactions on Audio, Speech, and Language Processing (2023),Vol.31．pp. 2534 – 2547.

[2]X.Shi^*,X.Li, T.Toda.”Emotion Awareness in Multi-utterance Turn for Improving Emotion Prediction in Multi-Speaker Conversation,”in INTERSPEECH 2023, Dublin, Ireland, Proceedings, pp.765-769.

[3]X. LI^*, M. AKAGI,” Improving Multilingual Speech Emotion Recognition by Combining Acoustic Features in A Three-Layer Model,” Speech Communication, Vol. 110, July 2019, pp.1--12.

[4] Z. Peng*,X. LI, Z. Zhu, M. Unoki, J. Dang, M. Akagi, “Auditory Model as Front-ends for Speech Emotion Recognition Using 3D Convolution and Attention-based Sliding Recurrent Network,” IEEE Access, Vol.8 , pp. 16560-16572, 2020.

[5]X. LI^*, T. GUO, X. HU, X. XU, J. DANG, M. AKAGI, “Hierarchical Prosody Analysis Improves Categorical and Dimensional Emotion Recognition”, in APSIPA ASC 2021, Tokyo, Japan, Proceedings,pp.700-704.

[6]X. LI^*, M. AKAGI, “The Contribution of Acoustic Features Analysis to Model Emotion Perceptual Process for Language Diversity”, in INTERSPEECH 2019, Graz, Austria, Proceedings, pp. 3262-3266.

[7]X. LI^*, M. AKAGI, “A Three-Layer Emotion Perception Model for Valence and Arousal-Based Detection from Multilingual Speech,” in INTERSPEECH 2018, Hyderabad, India, Proceedings, pp. 3643-3647.

[8]X. LI^*, M. AKAGI, “Maximal Information Coefficient and Predominant Correlation-Based Feature Selection Toward A Three-Layer Model for Speech Emotion Recognition,” in APSIPA ASC 2018, Honolulu, Hawaii, Proceedings, pp. 1428-1434.

[9]X. LI^*, M. AKAGI, “Multilingual Speech Emotion Recognition Using A Three-Layer Model,” in INTERSPEECH 2016, San Francisco, California, Proceedings, pp. 3608–3612.

[10]X. LI^*, M. AKAGI, “Automatic Speech Emotion Recognition in Chinese Using A Three-Layered Model in Dimensional Approach,” in NCSP2016, Honolulu, Hawaii, pp. 17-20.

[11]X. LI^*, M. AKAGI, “Toward Improving Estimation Accuracy of Emotion Dimensions in Bilingual Scenario Based on Three-Layered Model,” in O-COCOSDA/CASLRE 2015, Shanghai, China, Proceedings pp. 21–26.

[12]X. LI^*, M. AKAGI,” Acoustic Feature Selection Toward A Three-Layer Emotion Perception Model” in Acoustic Society of Japan Autumn 2018, 2-Q-10, pp. 1061-1064.

[13]X. LI^*, M. AKAGI, “Toward Automatic Multilingual Emotion Detection in 2D Space Using A Three-Layer Model,” in Acoustic Society of Japan Spring 2018, 2-Q-9, pp. 159-162.

[14]X. LI^*, M. AKAGI, “Multilingual Emotion Recognition from Speech Using A Three Layer Model,” in Acoustic Society of Japan Autumn 2017, 1-R-33, pp. 235-238.

[15]X. LI^*, Z. ZHU, M. AKAGI, “Acoustic Feature Selection for Improving Estimation of Emotions Using A Three Layer Model,” in Acoustic Society of Japan Spring 2017, 1-Q14, pp. 117-120.

[16]X. LI^*, M. AKAGI, “Improving Estimation Accuracy of Dimension Values for Speech Emotion in Bilingual Cases Using a Three-layered Model,” in Proceedings of the auditory research meeting 45(7), 577-581, 2015-10-23, Acoustic Society of Japan.

[17]X. LI^*, M. AKAGI, “Study on Estimation of Bilingual Speech Emotion Dimensions Using A Three-Layered Model,” in Acoustic Society of Japan Autumn 2015, 1-Q-39, pp. 305-308.

[18]X. LI^*, M. AKAGI, “Acoustic Features Analysis to Model Emotion Perceptual Process for Language Diversity,” in Acoustic Society of Japan Autumn 2019, 2-Q-5, pp. 891--894.