A Comparison of Speech Data Augmentation Methods Using S3PRL Toolkit
Not on the map. Why?
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 20 of its 37 references that are in the map. First posted on arXiv 27 Feb 2023.
Builds on
20 of 37 references.
References · 20
- 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
- 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,301
- 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
- 2021SUPERB: Speech processing Universal PERformance Benchmarkcited by 652
- 2015Attention-Based Models for Speech Recognitioncited by 400
- 2014Deep Speech: Scaling up end-to-end speech recognitioncited by 354
- 2019vq-wav2vec: Self-Supervised Learning of Discrete Speech Representationscited by 335
- 2019Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoderscited by 196
- 2020TERA: Self-Supervised Learning of Transformer Encoder Representation for Speechcited by 186
- 2021Recent Advances in End-to-End Automatic Speech Recognitioncited by 138
- 2020Unsupervised pretraining transfers well across languagescited by 100
- 2018The fifth 'CHiME' Speech Separation and Recognition Challenge: Dataset, task and baselinescited by 90
8 more
- 2021TorchAudio: Building Blocks for Audio and Speech Processingcited by 83
- 2020Rethinking Evaluation in ASR: Are Our Models Robust Enough?cited by 72
- 2019WHAMR!: Noisy and Reverberant Single-Channel Speech Separationcited by 61
- 2020Audio ALBERT: A Lite BERT for Self-supervised Learning of Audio Representationcited by 58
- 2017Learning from Between-class Examples for Deep Sound Recognitioncited by 53
- 2019Generalized Data Augmentation for Low-Resource Translationcited by 53
- 2022Improving Multimodal Speech Recognition by Data Augmentation and Speech Representationscited by 13
- 2020WeMix: How to Better Utilize Data Augmentationcited by 8
Built on by
Citing papers per year: 2025: 1.
1 paper.