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
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9488–9499
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.findings-acl.565/
DOI:
10.18653/v1/2024.findings-acl.565
Bibkey:
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. Association for Computational Linguistics.
Cite (Informal):
Revisiting Interpolation Augmentation for Speech-to-Text Generation (Xu et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.findings-acl.565.pdf