Discriminatively trained joint speaker and environment representations for adaptation of deep neural network acoustic models.
| Autor: | Yin, Maofan, Sivadas, Sunil, Yu, Kai, Ma, Bin |
|---|---|
| Zdroj: | 2016 IEEE International Conference on Acoustics, Speech & Signal Processing (ICASSP); 2016, p5065-5069, 5p |
| Databáze: | Complementary Index |
| Externí odkaz: |
|