Meta-Learning For Low-Resource Speech Emotion Recognition

While emotion recognition is a well-studied task, it remains unexplored to a large extent in cross-lingual settings. Speech Emotion Recognition (SER) in low-resource languages poses difficulties as existing approaches for knowledge transfer do not generalize seamlessly. Probing the learning process of generalized representations across languages, we propose a meta-learning approach for low-resource speech emotion recognition. The proposed approach achieves fast adaptation on a number of unseen target languages simultaneously. We evaluate the Model Agnostic Meta-Learning (MAML) algorithm on three low-resource target languages - Persian, Italian, and Urdu. We empirically demonstrate that our proposed method - MetaSER, considerably outperforms multitask and transfer learning-based methods for speech emotion recognition task, and discuss the benefits, efficiency, and challenges of MetaSER on limited data settings.