End-to-End time-continuous emotion recognition for spontaneous interactions

Abstract

Speech emotion recognition has emerged in the area of speech signal research since it can have a signficant role in Artificial intelligent. In the area of speech emotion recognition, hand-engineered features are traditionally used as an input. However, it requires an additional step to extract features before the prediction and prior knowledge to select a feature set. For this reason, recent research is focusing on end-to-end speech emotion recognition to reduce the required efforts for the feature extraction and increase performance. Whereas this approach has been applied for prediction of categorical emotions, the study for prediction of continuous dimensional emotions is still rare. This paper presents a method for time-continuous prediction of emotions from speech in end-to-end manner. Proposed model comprises convolutional neural network (CNN) and Recurrent Neural Network with Long Short-Term Memory (RNN-LSTM). Hyperparameters of CNN are investigated to improve the performance of our model. After finding the optimal hyperparameters, the performance of the system with waveform and spectrogram as input is compared in terms of concordance correlation coefficient (CCC).