Revisiting Interpolation Augmentation for Speech-to-Text Generation
Chen Xu, Jie Wang, Xiaoqian Liu, Qian Dong, Chunliang Zhang, Tong Xiao, JingBo Zhu, Dapeng Man, Wu Yang
Abstract
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.- Anthology ID:
- 2024.findings-acl.565
- Volume:
- Findings of the Association for Computational Linguistics ACL 2024
- Month:
- August
- Year:
- 2024
- Address:
- Bangkok, Thailand and virtual meeting
- Editors:
- Lun-Wei Ku, Andre Martins, Vivek Srikumar
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 9488–9499
- Language:
- URL:
- https://aclanthology.org/2024.findings-acl.565
- DOI:
- Cite (ACL):
- Chen Xu, Jie Wang, Xiaoqian Liu, Qian Dong, Chunliang Zhang, Tong Xiao, JingBo Zhu, Dapeng Man, and Wu Yang. 2024. Revisiting Interpolation Augmentation for Speech-to-Text Generation. In Findings of the Association for Computational Linguistics ACL 2024, pages 9488–9499, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.
- Cite (Informal):
- Revisiting Interpolation Augmentation for Speech-to-Text Generation (Xu et al., Findings 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2024.findings-acl.565.pdf