Meta-Learning for Low-Resource Speech Emotion Recognition

Abstract

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 1 , 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.

Speech Emotion Recognition Using Attention Model

“…They recorded an accuracy rate of 62.6% for IEMOCAP and 55.7% for the MSP-IMPROV datasets. In another study, Chopra et al [ 46 ] performed experiments to check the various combinations of datasets and models and they proposed a meta-learning approach for identifying the emotion.…”