Discriminatively Trained Recurrent Neural Networks for Continuous Dimensional Emotion Recognition from Audio
IJCAI, pp. 2196-2202, 2016.
Continuous dimensional emotion recognition from audio is a sequential regression problem, where the goal is to maximize correlation between sequences of regression outputs and continuous-valued emotion contours, while minimizing the average deviation. As in other domains, deep neural networks trained on simple acoustic features achieve go...More
PPT (Upload PPT)