# A Comparison of Speech Data Augmentation Methods Using S3PRL Toolkit

arXiv: https://arxiv.org/abs/2303.00510 · HTML: https://mlsanity.com/paper/2303.00510/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 37 references that are in the map.
- First posted on arXiv 27 Feb 2023.

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

- [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)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [SUPERB: Speech processing Universal PERformance Benchmark](https://mlsanity.com/paper/2105.01051/) (2021)
- [Attention-Based Models for Speech Recognition](https://mlsanity.com/paper/1506.07503/) (2015)
- [Deep Speech: Scaling up end-to-end speech recognition](https://mlsanity.com/paper/1412.5567/) (2014)
- [vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations](https://mlsanity.com/paper/1910.05453/) (2019)
- [Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders](https://mlsanity.com/paper/1910.12638/) (2019)
- [TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech](https://mlsanity.com/paper/2007.06028/) (2020)
- [Recent Advances in End-to-End Automatic Speech Recognition](https://mlsanity.com/paper/2111.01690/) (2021)
- [Unsupervised pretraining transfers well across languages](https://mlsanity.com/paper/2002.02848/) (2020)
- [The fifth 'CHiME' Speech Separation and Recognition Challenge: Dataset, task and baselines](https://mlsanity.com/paper/1803.10609/) (2018)
- [TorchAudio: Building Blocks for Audio and Speech Processing](https://mlsanity.com/paper/2110.15018/) (2021)
- [Rethinking Evaluation in ASR: Are Our Models Robust Enough?](https://mlsanity.com/paper/2010.11745/) (2020)
- [WHAMR!: Noisy and Reverberant Single-Channel Speech Separation](https://mlsanity.com/paper/1910.10279/) (2019)
- [Audio ALBERT: A Lite BERT for Self-supervised Learning of Audio Representation](https://mlsanity.com/paper/2005.08575/) (2020)
- [Learning from Between-class Examples for Deep Sound Recognition](https://mlsanity.com/paper/1711.10282/) (2017)
- [Generalized Data Augmentation for Low-Resource Translation](https://mlsanity.com/paper/1906.03785/) (2019)
- [Improving Multimodal Speech Recognition by Data Augmentation and Speech Representations](https://mlsanity.com/paper/2204.13206/) (2022)
- [WeMix: How to Better Utilize Data Augmentation](https://mlsanity.com/paper/2010.01267/) (2020)

## Built on by (most cited first, 1 of 1)

- [ArabEmoNet: A Lightweight Hybrid 2D CNN-BiLSTM Model with Attention for Robust Arabic Speech Emotion Recognition](https://mlsanity.com/paper/2509.01401/) (2025)

## Abstract (arXiv)

Data augmentations are known to improve robustness in speech-processing tasks. In this study, we summarize and compare different data augmentation strategies using S3PRL toolkit. We explore how HuBERT and wav2vec perform using different augmentation techniques (SpecAugment, Gaussian Noise, Speed Perturbation) for Phoneme Recognition (PR) and Automatic Speech Recognition (ASR) tasks. We evaluate model performance in terms of phoneme error rate (PER) and word error rate (WER). From the experiments, we observed that SpecAugment slightly improves the performance of HuBERT and wav2vec on the original dataset. Also, we show that models trained using the Gaussian Noise and Speed Perturbation dataset are more robust when tested with augmented test sets.