# Revisiting Interpolation Augmentation for Speech-to-Text Generation

arXiv: https://arxiv.org/abs/2406.15846 · HTML: https://mlsanity.com/paper/2406.15846/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 43 references that are in the map.
- First posted on arXiv 22 Jun 2024.

## Builds on (most cited first, 20 of 20)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline](https://mlsanity.com/paper/1709.05522/) (2017)
- [Augmenting Data with Mixup for Sentence Classification: An Empirical Study](https://mlsanity.com/paper/1905.08941/) (2019)
- [Intermediate Loss Regularization for CTC-based Speech Recognition](https://mlsanity.com/paper/2102.03216/) (2021)
- [Speech Recognition with Augmented Synthesized Speech](https://mlsanity.com/paper/1909.11699/) (2019)
- [MixSpeech: Data Augmentation for Low-resource Automatic Speech Recognition](https://mlsanity.com/paper/2102.12664/) (2021)
- [Exploring Transformers for Large-Scale Speech Recognition](https://mlsanity.com/paper/2005.09684/) (2020)
- [M3ST: Mix at Three Levels for Speech Translation](https://mlsanity.com/paper/2212.03657/) (2022)
- [Recent Advances in Direct Speech-to-text Translation](https://mlsanity.com/paper/2306.11646/) (2023)
- [CTC-based Non-autoregressive Speech Translation](https://mlsanity.com/paper/2305.17358/) (2023)
- [Mixup-breakdown: a consistency training method for improving generalization of speech separation models](https://mlsanity.com/paper/1910.13253/) (2019)
- [Learning Robust Self-attention Features for Speech Emotion Recognition with Label-adaptive Mixup](https://mlsanity.com/paper/2305.06273/) (2023)
- [Global Mixup: Eliminating Ambiguity with Clustering](https://mlsanity.com/paper/2206.02734/) (2022)

## Abstract (arXiv)

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.