Multimodal Speech Emotion Recognition and Ambiguity Resolution
This work addresses emotion recognition from speech for applications like human-computer interaction, but it is incremental as it builds on existing feature-based approaches.
The paper tackled speech emotion recognition by comparing traditional machine learning classifiers and deep learning models using hand-crafted audio and text features, showing that lighter models achieve performance comparable to current deep learning state-of-the-art methods.
Identifying emotion from speech is a non-trivial task pertaining to the ambiguous definition of emotion itself. In this work, we adopt a feature-engineering based approach to tackle the task of speech emotion recognition. Formalizing our problem as a multi-class classification problem, we compare the performance of two categories of models. For both, we extract eight hand-crafted features from the audio signal. In the first approach, the extracted features are used to train six traditional machine learning classifiers, whereas the second approach is based on deep learning wherein a baseline feed-forward neural network and an LSTM-based classifier are trained over the same features. In order to resolve ambiguity in communication, we also include features from the text domain. We report accuracy, f-score, precision, and recall for the different experiment settings we evaluated our models in. Overall, we show that lighter machine learning based models trained over a few hand-crafted features are able to achieve performance comparable to the current deep learning based state-of-the-art method for emotion recognition.