Direct articulatory observation reveals phoneme recognition performance characteristics of a self-supervised speech model.

Autor: Shi, Xuan1 (AUTHOR), Feng, Tiantian1 (AUTHOR), Huang, Kevin1 (AUTHOR), Kadiri, Sudarsana Reddy1 (AUTHOR), Lee, Jihwan1 (AUTHOR), Lu, Yijing2 (AUTHOR) tiantiaf@usc.edu, Zhang, Yubin2 (AUTHOR), Goldstein, Louis2 (AUTHOR), Narayanan, Shrikanth1,2 (AUTHOR)
Zdroj: JASA Express Letters. Nov2024, Vol. 4 Issue 11, p1-7. 7p.
Databáze: Academic Search Ultimate
Nepřihlášeným uživatelům se plný text nezobrazuje