Bridging the Language Gap: Synthetic Voice Diversity via Latent Mixup for Equitable Speech Recognition
This addresses the problem of unfair speech recognition performance for underrepresented linguistic communities, offering a practical solution, though it is incremental as it builds on existing augmentation strategies.
The paper tackled the performance gap in speech recognition for low-resource languages by introducing a novel data augmentation technique, demonstrating significant improvements and outperforming existing methods.
Modern machine learning models for audio tasks often exhibit superior performance on English and other well-resourced languages, primarily due to the abundance of available training data. This disparity leads to an unfair performance gap for low-resource languages, where data collection is both challenging and costly. In this work, we introduce a novel data augmentation technique for speech corpora designed to mitigate this gap. Through comprehensive experiments, we demonstrate that our method significantly improves the performance of automatic speech recognition systems on low-resource languages. Furthermore, we show that our approach outperforms existing augmentation strategies, offering a practical solution for enhancing speech technology in underrepresented linguistic communities.