# Exploring WavLM on Speech Enhancement

arXiv: https://arxiv.org/abs/2211.09988 · HTML: https://mlsanity.com/paper/2211.09988/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Nov 2022.

## Built on by (most cited first, 9 of 9)

- [Adapting Multi-Lingual ASR Models for Handling Multiple Talkers](https://mlsanity.com/paper/2305.18747/) (2023)
- [TS-SUPERB: A Target Speech Processing Benchmark for Speech Self-Supervised Learning Models](https://mlsanity.com/paper/2505.06660/) (2025)
- [One-Step Knowledge Distillation and Fine-Tuning in Using Large Pre-Trained Self-Supervised Learning Models for Speaker Verification](https://mlsanity.com/paper/2305.17394/) (2023)
- [SAGE: Spliced-Audio Generated Data for Enhancing Foundational Models in Low-Resource Arabic-English Code-Switched Speech Recognition](https://mlsanity.com/paper/2506.22143/) (2025)
- [Universal Sound Separation with Self-Supervised Audio Masked Autoencoder](https://mlsanity.com/paper/2407.11745/) (2024)
- [Heterogeneous Space Fusion and Dual-Dimension Attention: A New Paradigm for Speech Enhancement](https://mlsanity.com/paper/2408.06911/) (2024)
- [Pac-HuBERT: Self-Supervised Music Source Separation via Primitive Auditory Clustering and Hidden-Unit BERT](https://mlsanity.com/paper/2304.02160/) (2023)
- [Joint Learning using Mixture-of-Expert-Based Representation for Speech Enhancement and Robust Emotion Recognition](https://mlsanity.com/paper/2509.08470/) (2025)
- [Masked Autoencoders as Universal Speech Enhancer](https://mlsanity.com/paper/2602.02413/) (2026)

## Abstract (arXiv)

There is a surge in interest in self-supervised learning approaches for end-to-end speech encoding in recent years as they have achieved great success. Especially, WavLM showed state-of-the-art performance on various speech processing tasks. To better understand the efficacy of self-supervised learning models for speech enhancement, in this work, we design and conduct a series of experiments with three resource conditions by combining WavLM and two high-quality speech enhancement systems. Also, we propose a regression-based WavLM training objective and a noise-mixing data configuration to further boost the downstream enhancement performance. The experiments on the DNS challenge dataset and a simulation dataset show that the WavLM benefits the speech enhancement task in terms of both speech quality and speech recognition accuracy, especially for low fine-tuning resources. For the high fine-tuning resource condition, only the word error rate is substantially improved.