Meta-Learning for Low-Resource Speech Emotion Recognition

Suransh Chopra, Puneet Mathur, Ramit Sawhney, Rajiv Ratn ShahICASSP 2021 · OpenReview

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 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> , 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.
BibTeX
@inproceedings{chopra2021meta,
  author = {Suransh Chopra and Puneet Mathur and Ramit Sawhney and Rajiv Ratn Shah},
  title = {{Meta-Learning for Low-Resource Speech Emotion Recognition}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2021},
  url = {https://openreview.net/forum?id=7ehz3sR186},
}

Loading related content...

Figure