Zhichao Peng, Zhi Zhu, Masashi Unoki, Jianwu Dang, Masato Akagi. Auditory-Inspired End-to-End Speech Emotion Recognition Using 3D Convolutional Recurrent Neural Networks Based on Spectral-Temporal Representation. In 2018 IEEE International Conference on Multimedia and Expo, ICME 2018, San Diego, CA, USA, July 23-27, 2018. pages 1-6, IEEE Computer Society, 2018. [doi]
@inproceedings{PengZUDA18,
title = {Auditory-Inspired End-to-End Speech Emotion Recognition Using 3D Convolutional Recurrent Neural Networks Based on Spectral-Temporal Representation},
author = {Zhichao Peng and Zhi Zhu and Masashi Unoki and Jianwu Dang and Masato Akagi},
year = {2018},
doi = {10.1109/ICME.2018.8486564},
url = {http://doi.ieeecomputersociety.org/10.1109/ICME.2018.8486564},
researchr = {https://researchr.org/publication/PengZUDA18},
cites = {0},
citedby = {0},
pages = {1-6},
booktitle = {2018 IEEE International Conference on Multimedia and Expo, ICME 2018, San Diego, CA, USA, July 23-27, 2018},
publisher = {IEEE Computer Society},
isbn = {978-1-5386-1737-3},
}