Transformer encoder-based multilevel representations with fusion feature input for speech emotion recognition.

Autor: He Zhengran, Shen Qifan, Wu Jiaxin, Xu Mengyao, Zhao Li
Předmět:
Zdroj: Journal of Southeast University (English Edition); Mar2023, Vol. 39 Issue 1, p68-73, 6p
Databáze: Complementary Index