# A Noise-Robust Self-supervised Pre-training Model Based Speech Representation Learning for Automatic Speech Recognition

arXiv: https://arxiv.org/abs/2201.08930 · HTML: https://mlsanity.com/paper/2201.08930/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jan 2022.

## Built on by (most cited first, 22 of 22)

- [Self-Supervised Speech Representation Learning: A Review](https://mlsanity.com/paper/2205.10643/) (2022)
- [How Does Pre-trained Wav2Vec 2.0 Perform on Domain Shifted ASR? An Extensive Benchmark on Air Traffic Control Communications](https://mlsanity.com/paper/2203.16822/) (2022)
- [Improving Distortion Robustness of Self-supervised Speech Processing Tasks with Domain Adaptation](https://mlsanity.com/paper/2203.16104/) (2022)
- [Unifying Speech Enhancement and Separation with Gradient Modulation for End-to-End Noise-Robust Speech Separation](https://mlsanity.com/paper/2302.11131/) (2023)
- [Gradient Remedy for Multi-Task Learning in End-to-End Noise-Robust Speech Recognition](https://mlsanity.com/paper/2302.11362/) (2023)
- [Wav2code: Restore Clean Speech Representations via Codebook Lookup for Noise-Robust ASR](https://mlsanity.com/paper/2304.04974/) (2023)
- [Cross-Modal Global Interaction and Local Alignment for Audio-Visual Speech Recognition](https://mlsanity.com/paper/2305.09212/) (2023)
- [Improving generalizability of distilled self-supervised speech processing models under distorted settings](https://mlsanity.com/paper/2210.07978/) (2022)
- [CPT-Boosted Wav2vec2.0: Towards Noise Robust Speech Recognition for Classroom Environments](https://mlsanity.com/paper/2409.14494/) (2024)
- [Dual-Branch Knowledge Distillation for Noise-Robust Synthetic Speech Detection](https://mlsanity.com/paper/2310.08869/) (2023)
- [Noise-Robust Keyword Spotting through Self-supervised Pretraining](https://mlsanity.com/paper/2403.18560/) (2024)
- [Some voices are too common: Building fair speech recognition systems using the Common Voice dataset](https://mlsanity.com/paper/2306.03773/) (2023)
- [Ditch the Denoiser: Emergence of Noise Robustness in Self-Supervised Learning from Data Curriculum](https://mlsanity.com/paper/2505.12191/) (2025)
- [WavRx: a Disease-Agnostic, Generalizable, and Privacy-Preserving Speech Health Diagnostic Model](https://mlsanity.com/paper/2406.18731/) (2024)
- [Deepfake Detection of Singing Voices With Whisper Encodings](https://mlsanity.com/paper/2501.18919/) (2025)
- [HuBERT-VIC: Improving Noise-Robust Automatic Speech Recognition of Speech Foundation Model via Variance-Invariance-Covariance Regularization](https://mlsanity.com/paper/2508.12292/) (2025)
- [Learning Robust Spatial Representations from Binaural Audio through Feature Distillation](https://mlsanity.com/paper/2508.20914/) (2025)
- [Dimensionality-Aware Anomaly Detection in Learned Representations of Self-Supervised Speech Models](https://mlsanity.com/paper/2605.02715/) (2026)
- [Layer-Wise Analysis of Self-Supervised Representations for Age and Gender Classification in Children's Speech](https://mlsanity.com/paper/2508.10332/) (2025)
- [Reduce, Reuse, Recycle: Is Perturbed Data better than Other Language augmentation for Low Resource Self-Supervised Speech Models](https://mlsanity.com/paper/2309.12763/) (2023)
- [Noise robust distillation of self-supervised speech models via correlation metrics](https://mlsanity.com/paper/2312.12153/) (2023)
- [How Well Do Self-Supervised Speech Models Encode Age and Gender in Children's Speech? A Layer-Wise Analysis Across Multiple Architectures](https://mlsanity.com/paper/2606.22177/) (2026)

## Abstract (arXiv)

Wav2vec2.0 is a popular self-supervised pre-training framework for learning speech representations in the context of automatic speech recognition (ASR). It was shown that wav2vec2.0 has a good robustness against the domain shift, while the noise robustness is still unclear. In this work, we therefore first analyze the noise robustness of wav2vec2.0 via experiments. We observe that wav2vec2.0 pre-trained on noisy data can obtain good representations and thus improve the ASR performance on the noisy test set, which however brings a performance degradation on the clean test set. To avoid this issue, in this work we propose an enhanced wav2vec2.0 model. Specifically, the noisy speech and the corresponding clean version are fed into the same feature encoder, where the clean speech provides training targets for the model. Experimental results reveal that the proposed method can not only improve the ASR performance on the noisy test set which surpasses the original wav2vec2.0, but also ensure a tiny performance decrease on the clean test set. In addition, the effectiveness of the proposed method is demonstrated under different types of noise conditions.