ACL Findings2024
Revisiting Interpolation Augmentation for Speech-to-Text Generation
Chen Xu, Jie Wang, Xiaoqian Liu, Qianqian 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. 1
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- CMOT: Cross-modal Mixup via Optimal Transport for Speech Translation cites wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
- Robust Speech Recognition via Large-Scale Weak Supervision cites wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
Builds on5
- wav2vec 2.0: A Framework for Self-Supervised Learning of Speech RepresentationsAlexei Baevski, Yuhao Zhou, Abdelrahman Mohamed, Michael AuliNeurIPS 2020 · 9,451 citations
- Robust Speech Recognition via Large-Scale Weak SupervisionAlec Radford, Jong Wook Kim, Tao Xu, Greg Brockman et al.ICML 2023 · 6,966 citations
- CMOT: Cross-modal Mixup via Optimal Transport for Speech TranslationYan Zhou, Qingkai Fang, Yang FengACL 2023 · 24 citations
- Global Mixup: Eliminating Ambiguity with ClusteringXiangjin Xie, Yangning Li, Wang Chen, Kai Ouyang et al.AAAI 2023 · 5 citations
- On the Pitfall of Mixup for Uncertainty CalibrationDeng-Bao Wang, Lanqing Li, Peilin Zhao, Pheng-Ann Heng et al.CVPR 2023
Related papers
- CASSI: Contextual and Semantic Structure-based Interpolation Augmentation for Low-Resource NERTanmay Surana, Thi-Nga Ho, Kyaw Zin Tun, Eng Siong ChngEMNLP Findings 2023 · 3 citations
- DAGA: Data Augmentation with a Generation Approach forLow-resource Tagging TasksBosheng Ding, Linlin Liu, Lidong Bing, Canasai Kruengkrai et al.EMNLP 2020 · 132 citations
- MetaMixSpeech: Meta Task Augmentation for Low-Resource Speech RecognitionYaqi Chen, Hao Zhang, Wenlin Zhang, XuKui Yang et al.EMNLP Findings 2025
- MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text ClassificationJiaao Chen, Zichao Yang, Diyi YangACL 2020 · 340 citations
- LLM2LLM: Boosting LLMs with Novel Iterative Data EnhancementNicholas Lee, Thanakul Wattanawong, Sehoon Kim, Karttikeya Mangalam et al.ACL Findings 2024 · 21 citations
