Improving Speech Emotion Recognition in Under-Resourced Languages via Speech-to-Speech Translation with Bootstrapping Data Selection
This addresses the challenge of building robust multilingual speech emotion recognition systems for natural human-computer interaction, though it appears incremental as it adapts existing translation methods to a specific data bottleneck.
The paper tackles the problem of scarce labeled data for speech emotion recognition in under-resourced languages by using expressive speech-to-speech translation with a bootstrapping data selection pipeline to generate labeled data from high-resource languages, achieving enhanced performance across different models and languages.
Speech Emotion Recognition (SER) is a crucial component in developing general-purpose AI agents capable of natural human-computer interaction. However, building robust multilingual SER systems remains challenging due to the scarcity of labeled data in languages other than English and Chinese. In this paper, we propose an approach to enhance SER performance in low SER resource languages by leveraging data from high-resource languages. Specifically, we employ expressive Speech-to-Speech translation (S2ST) combined with a novel bootstrapping data selection pipeline to generate labeled data in the target language. Extensive experiments demonstrate that our method is both effective and generalizable across different upstream models and languages. Our results suggest that this approach can facilitate the development of more scalable and robust multilingual SER systems.