Multi-Modal Emotion Recognition Using Speech Features and Text-Embedding

Recently, intelligent personal assistants, chat-bots and AI speakers are being utilized more broadly as communication interfaces and the demands for more natural interaction measures have increased as well. Humans can express emotions in various ways, such as using voice tones or facial expressions; therefore, multimodal approaches to recognize human emotions have been studied. In this paper, we propose an emotion recognition method to deliver more accuracy by using speech and text data. The strengths of the data are also utilized in this method. We conducted 43 feature vectors such as spectral features, harmonic features and MFCC from speech datasets. In addition, 256 embedding vectors from transcripts using pre-trained Tacotron encoder were extracted. The acoustic feature vectors and embedding vectors were fed into each deep learning model which produced a probability for the predicted output classes. The results show that the proposed model exhibited more accurate performance than in previous research.