A Cross-Lingual Meta-Learning Method Based on Domain Adaptation for Speech Emotion Recognition

TL;DR

This paper introduces a practical cross-lingual meta-learning approach with domain adaptation for speech emotion recognition, achieving high accuracy on unseen language datasets with limited training data.

Contribution

It proposes an improved meta-learning framework using a large pre-trained backbone and prototypical networks, with a novel fine-tuning method for better out-of-distribution performance.

Findings

Achieved 83.78% accuracy on Greek speech emotion recognition.

Achieved 56.30% accuracy on Romanian speech emotion recognition.

Demonstrated effectiveness of the method on low-resource, cross-lingual datasets.

Abstract

Best-performing speech models are trained on large amounts of data in the language they are meant to work for. However, most languages have sparse data, making training models challenging. This shortage of data is even more prevalent in speech emotion recognition. Our work explores the model's performance in limited data, specifically for speech emotion recognition. Meta-learning specializes in improving the few-shot learning. As a result, we employ meta-learning techniques on speech emotion recognition tasks, accent recognition, and person identification. To this end, we propose a series of improvements over the multistage meta-learning method. Unlike other works focusing on smaller models due to the high computational cost of meta-learning algorithms, we take a more practical approach. We incorporate a large pre-trained backbone and a prototypical network, making our methods more feasible and applicable. Our most notable contribution is an improved fine-tuning technique during meta-testing that significantly boosts the performance on out-of-distribution datasets. This result, together with incremental improvements from several other works, helped us achieve accuracy scores of 83.78% and 56.30% for Greek and Romanian speech emotion recognition datasets not included in the training or validation splits in the context of 4-way 5-shot learning.