Revisiting Interpolation Augmentation for Speech-to-Text Generation
This addresses the problem of limited labeled data for speech-to-text systems, offering a promising solution for resource-constrained settings, though it appears incremental as it applies an existing technique to a new domain.
The paper tackled the challenge of low-resource speech-to-text generation by exploring interpolation augmentation, finding that an appropriate strategy significantly enhances performance across tasks, architectures, and data scales.
Speech-to-text (S2T) generation systems frequently face challenges in low-resource scenarios, primarily due to the lack of extensive labeled datasets. One emerging solution is constructing virtual training samples by interpolating inputs and labels, which has notably enhanced system generalization in other domains. Despite its potential, this technique's application in S2T tasks has remained under-explored. In this paper, we delve into the utility of interpolation augmentation, guided by several pivotal questions. Our findings reveal that employing an appropriate strategy in interpolation augmentation significantly enhances performance across diverse tasks, architectures, and data scales, offering a promising avenue for more robust S2T systems in resource-constrained settings.