This is an implementation of Speech Emotion Recognition with Dual-Sequence LSTM Architecture (DS-LSTM)
- Dual-Sequence LSTM (DS-LSTM)
- Dual-level model with DS-LSTM cell
- Python 3
- PyTorch 1.0
- IEMOCAP
| WA | UA | |
|---|---|---|
| MDS-LSTM | 69.4 | 69.5 |
| MLSTM + MDS-LSTM | 72.7 | 73.3 |
Jianyou Wang
Michael Xue
Ryan Culhane
Enmao Diao
Jie Ding
Vahid Tarokh