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.

While modern deep learning-based models have significantly outperformed traditional methods in the area of speech enhancement, they often necessitate a lot of parameters and extensive computational power, making them impractical to be deployed on edge devices in real-world applications. In this paper, we introduce Grouped Temporal Convolutional Recurrent Network (GTCRN), which incorporates grouped strategies to efficiently simplify a competitive model, DPCRN. Additionally, it leverages subband feature extraction modules and temporal recurrent attention modules to enhance its performance. Remarkably, the resulting model demands ultralow computational resources, featuring only 23.7 K parameters and 39.6 MMACs per second. Experimental results show that our proposed model not only surpasses RNNoise, a typical lightweight model with similar computational burden, but also achieves competitive performance when compared to recent baseline models with significantly higher computational resources requirements.

This paper summarizes a hybrid multi-channel speech enhancement system for the ICASSP Signal Processing Grand Challenge: Clarity Challenge (Speech Enhancement for Hearing Aids) 2023. The system consists of a rule-based dereverberation module, a multi-channel enhancement module, and a post-processing module. Without using the head rotation information and the enrollment speech, the system can reach an average hearing aid speech perception index (HASPI) score of 0.696 and hearing aid speech quality index (HASQI) score of 0.320 on the official development set. The corresponding scores are 0.729 and 0.316 respectively on the Eval1 set for the challenge ranking.