# PASE: Leveraging the Phonological Prior of WavLM for Low-Hallucination Generative Speech Enhancement

arXiv: https://arxiv.org/abs/2511.13300 · HTML: https://mlsanity.com/paper/2511.13300/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 43 references that are in the map.
- First posted on arXiv 17 Nov 2025.

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [High-Fidelity Audio Compression with Improved RVQGAN](https://mlsanity.com/paper/2306.06546/) (2023)
- [UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022](https://mlsanity.com/paper/2204.02152/) (2022)
- [FSD50K: An Open Dataset of Human-Labeled Sound Events](https://mlsanity.com/paper/2010.00475/) (2020)
- [Layer-wise Analysis of a Self-supervised Speech Representation Model](https://mlsanity.com/paper/2107.04734/) (2021)
- [DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressors](https://mlsanity.com/paper/2010.15258/) (2020)
- [FMA: A Dataset For Music Analysis](https://mlsanity.com/paper/1612.01840/) (2016)
- [An Unsupervised Autoregressive Model for Speech Representation Learning](https://mlsanity.com/paper/1904.03240/) (2019)
- [DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressors](https://mlsanity.com/paper/2110.01763/) (2021)
- [Comparative layer-wise analysis of self-supervised speech models](https://mlsanity.com/paper/2211.03929/) (2022)
- [WHAM!: Extending Speech Separation to Noisy Environments](https://mlsanity.com/paper/1907.01160/) (2019)
- [The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Results](https://mlsanity.com/paper/2005.13981/) (2020)
- [Conditional Diffusion Probabilistic Model for Speech Enhancement](https://mlsanity.com/paper/2202.05256/) (2022)
- [WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling](https://mlsanity.com/paper/2408.16532/) (2024)
- [StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation](https://mlsanity.com/paper/2212.11851/) (2022)
- [OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformer](https://mlsanity.com/paper/2401.16658/) (2024)
- [Self-Supervised Speech Representations are More Phonetic than Semantic](https://mlsanity.com/paper/2406.08619/) (2024)
- [ICASSP 2023 Deep Noise Suppression Challenge](https://mlsanity.com/paper/2303.11510/) (2023)
- [TF-GridNet: Integrating Full- and Sub-Band Modeling for Speech Separation](https://mlsanity.com/paper/2211.12433/) (2022)
- [Pushing the limits of raw waveform speaker recognition](https://mlsanity.com/paper/2203.08488/) (2022)
- [SpeechBERTScore: Reference-Aware Automatic Evaluation of Speech Generation Leveraging NLP Evaluation Metrics](https://mlsanity.com/paper/2401.16812/) (2024)
- [Probing self-supervised speech models for phonetic and phonemic information: a case study in aspiration](https://mlsanity.com/paper/2306.06232/) (2023)
- [Investigating self-supervised learning for speech enhancement and separation](https://mlsanity.com/paper/2203.07960/) (2022)
- [GenSE: Generative Speech Enhancement via Language Models using Hierarchical Modeling](https://mlsanity.com/paper/2502.02942/) (2025)
- [FlowSE: Efficient and High-Quality Speech Enhancement via Flow Matching](https://mlsanity.com/paper/2505.19476/) (2025)
- [Self-Supervised Learning for Speech Enhancement through Synthesis](https://mlsanity.com/paper/2211.02542/) (2022)

## Built on by (most cited first, 5 of 5)

- [GAP-URGENet: A Generative-Predictive Fusion Framework for Universal Speech Enhancement](https://mlsanity.com/paper/2604.01832/) (2026)
- [Noise Adaptive Streaming Audio-Visual Speech Token Enhancement for Robust Full-Duplex Spoken Dialogue Models](https://mlsanity.com/paper/2609.08390/) (2026)
- [StuPASE: Towards Low-Hallucination Studio-Quality Generative Speech Enhancement](https://mlsanity.com/paper/2603.09234/) (2026)
- [UniPASE: A Generative Model for Universal Speech Enhancement with High Fidelity and Low Hallucinations](https://mlsanity.com/paper/2604.14606/) (2026)
- [PhASE-Flow: Phonetic-Conditioned Acoustic Flow Matching in SSL Representation Domain for Speech Enhancement](https://mlsanity.com/paper/2606.17806/) (2026)

## Abstract (arXiv)

Generative models have shown remarkable performance in speech enhancement (SE), achieving superior perceptual quality over traditional discriminative approaches. However, existing generative SE approaches often overlook the risk of hallucination under severe noise, leading to incorrect spoken content or inconsistent speaker characteristics, which we term linguistic and acoustic hallucinations, respectively. We argue that linguistic hallucination stems from models' failure to constrain valid phonological structures and it is a more fundamental challenge. While language models (LMs) are well-suited for capturing the underlying speech structure through modeling the distribution of discrete tokens, existing approaches are limited in learning from noise-corrupted representations, which can lead to contaminated priors and hallucinations. To overcome these limitations, we propose the Phonologically Anchored Speech Enhancer (PASE), a generative SE framework that leverages the robust phonological prior embedded in the pre-trained WavLM model to mitigate hallucinations. First, we adapt WavLM into a denoising expert via representation distillation to clean its final-layer features. Guided by the model's intrinsic phonological prior, this process enables robust denoising while minimizing linguistic hallucinations. To further reduce acoustic hallucinations, we train the vocoder with a dual-stream representation: the high-level phonetic representation provides clean linguistic content, while a low-level acoustic representation retains speaker identity and prosody. Experimental results demonstrate that PASE not only surpasses state-of-the-art discriminative models in perceptual quality, but also significantly outperforms prior generative models with substantially lower linguistic and acoustic hallucinations.