（五十五）：Learning Alignment for Multimodal Emotion Recognition from Speech
- Abstract
- 1. Introduction
- 2. Related Work
- 3. Algorithm Details
-
- 3.1. Speech Encoder
- 3.2. Text Encoder
- 3.3. Attention Based Alignment
- 4. Evaluations
-
- 4.1. Data
- 4.2. Implementation
- 4.3. Experiments
- 5. Conclusions
- 出处： INTERSPEECH 2019: 3569-3573;CCF-C
- 代码：https://github.com/Zh