Speech Emotion Recognition Using Quaternion Convolutional Neural Networks

Although speech recognition has become a widespread technology, inferring emotion from speech signals remains a challenge. Our paper addresses this problem by proposing a quaternion convolutional neural network (QCNN) based speech emotion recognition (SER) model in which Mel-spectrogram features of speech signals are encoded in an RGB quaternion domain. We demonstrate that our QCNN based SER model outperforms other real-valued methods in the Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS, 8-classes) dataset, achieving, to the best of our knowledge, state-of-the-art results. The QCNN model also achieves comparable results with state-of-the-art methods in the Interactive Emotional Dyadic Motion Capture (IEMOCAP 4-classes) and Berlin EMO-DB (7-classes) datasets. Specifically, the model achieves an accuracy of 77.87%, 70.46%, and 88.78% for the RAVDESS, IEMOCAP, and EMO-DB datasets, respectively. Additionally, model size results reveal that the quaternion unit structure is significantly better able to encode internal dependencies than real-valued structures.