arXiv subjects

Xiaobin Rong

Publications and source records attributed to Xiaobin Rong.

13 recordsLinked to original sources

arXiv2026

CoFi-Lite: Pushing the Limits of Ultra-Lightweight Speech Enhancement

Ultra-lightweight models are essential for the deployment of deep learning-based speech enhancement algorithms on edge devices. Although recent approaches have achieved a certain balance between computational complexity and performance, pushing the complexity limits further demands more sophisticated designs. In this letter, we propose CoFi-Lite, a highly efficient model that decouples spectral modeling into coarse- and fine-grained streams. By leveraging two parallel and symmetric encoder-decoder paths, it simultaneously extracts full-band envelopes and low-frequency details for complementary enhancement. In addition, a novel Cross-Path Fusion (CPF) module is introduced to bridge the distinct paths, facilitating efficient feature interaction. Remarkably, CoFi-Lite requires extremely low computational resources, featuring only 12.87M MACs/s and 83.12k parameters. Experimental results demonstrate that our proposed model outperforms the ultra-lightweight baseline GTCRN while requiring only 40.26% of its computational complexity. Its scaled-up variant also delivers performance on par with that of the SOTA ultra-lightweight model AdaptCRN alongside a 19.34% reduction in computational cost. Audio examples are available at https://acceleration123.github.io/CoFiLite-demo/.

eess.AS↗

arXiv2026

PhASE-Flow: Phonetic-Conditioned Acoustic Flow Matching in SSL Representation Domain for Speech Enhancement

Flow matching (FM) enables high-fidelity generation, while self-supervised learning (SSL) speech models provide hierarchical representations spanning acoustic and phonetic levels. However, existing FM-based speech enhancement (SE) methods operate primarily in the spectral domain, treating SSL features only as external conditions rather than modeling directly in the SSL latent space. To fully exploit the structural richness of SSL representations, we propose PhASE-Flow, an FM-based SE framework that operates entirely in the SSL space. It models the conditional distribution of clean acoustic representations given phonetic ones, reconstructing the waveform via a neural vocoder. Experiments show that PhASE-Flow outperforms state-of-the-art baselines in perceptual quality and intelligibility. Notably, it achieves competitive performance with only four sampling steps, enabling highly efficient inference. Audio demos are available at https://anonymous.4open.science/w/phase-flow_demo-E6E1/.

eess.AS↗

arXiv2026

HALO: Half-Frame-Rate Adaptive Learnable Operator for Lightweight STFT-Based Speech Enhancement

STFT-based speech enhancement typically adopts overlapping analysis frames. While overlap is essential for stable STFT processing, it makes adjacent frames highly correlated, causing redundant computation in lightweight models. We propose Half-frame-rate Adaptive Learnable Operator (HALO), a causal plug-in module that halves the internal frame rate without altering the STFT procedure. Broadly applicable to many lightweight models, HALO applies adaptive rate reduction before the backbone and restoration afterward, reconstructing the full-rate spectrum on the original STFT grid. Both reduction and restoration are implemented with lightweight dynamic convolutions. By halving the processed frame rate, HALO reduces backbone compute cost with no added algorithmic latency, freeing budget for channel widening. Experiments on the DNS3 dataset show consistent gains across diverse lightweight models under matched complexity, demonstrating the effectiveness of reducing overlap-induced redundancy.

eess.AS↗

arXiv2026

FSC-Net: Integrating Fast Fourier Convolutions and Progressive Learning for Speech Bandwidth Extension

Speech bandwidth extension (BWE) aims to reconstruct high-fidelity wideband audio from narrowband inputs. While recent approaches have made significant progress, they often struggle to reconstruct realistic high-frequency phase and harmonic structures, leading to perceptual artifacts. In this paper, we propose FSC-Net (Full-Spectrum Context Network), a parameter-efficient architecture designed to explicitly model cross-band harmonic dependencies. By integrating Fast Fourier Convolutions (FFCs) into a complex spectral mapping framework, FSC-Net expands its receptive field to the entire spectrum, capturing long-range frequency interactions effectively. To address the ill-posed nature of high-frequency generation, our novel frequency-progressive learning curriculum guides the network to reconstruct spectral details from coarse to fine. Experimental results on the VCTK and unseen EARS datasets demonstrate that FSC-Net delivers consistently strong reconstruction quality and generalization, particularly in the challenging VCTK 4 kHz-to-48 kHz task. Compared to scaled-up baselines, our model attains leading LSD and PESQ scores while maintaining a highly compact parameter footprint (1.54 M).

eess.AS↗

arXiv2026

Reducing Linguistic Hallucination in LM-Based Speech Enhancement via Noise-Invariant Acoustic-Semantic Distillation

Language model (LM)-based speech enhancement (SE) can generate natural-sounding speech, but under severe noise it often suffers from unreliable conditioning, leading to perceptually plausible yet linguistically incorrect outputs. To address this issue, we propose L3-SE, a noise-invariant acoustic-semantic distillation framework for reducing linguistic hallucination in LM-based SE. The proposed method learns a noise-invariant conditioning encoder from noisy speech by jointly distilling two complementary clean-speech targets: an acoustic target for reconstruction fidelity and a semantic target for linguistic consistency. The resulting noise-invariant acoustic-semantic representations are used to condition a decoder-only autoregressive language model, which predicts clean acoustic tokens that are decoded into enhanced speech. To support high-quality generation, we further employ a high-fidelity codec built on learnable weighted WavLM layer representations as the discrete acoustic interface. By improving the reliability of conditioning under adverse conditions, the proposed framework substantially reduces hallucination and improves content faithfulness. Experiments show that the proposed method consistently outperforms prior LM-based speech enhancement baselines on linguistic consistency metrics, with especially clear gains under low-SNR and reverberant conditions, while maintaining competitive perceptual quality. Audio samples are available at https://max1wz.github.io/L3-SE-Demo-Page/. The complete source code will be released after the manuscript is accepted.

eess.AS↗

arXiv2026

UniPASE: A Generative Model for Universal Speech Enhancement with High Fidelity and Low Hallucinations

Universal speech enhancement (USE) aims to restore speech signals from diverse distortions across multiple sampling rates. We propose UniPASE, an extension of the low-hallucination PASE framework tailored for USE. At its core is DeWavLM-Omni, a unified representation-level enhancement module fine-tuned from WavLM via knowledge distillation on a large-scale supervised multi-distortion dataset. This module directly converts degraded waveforms into clean and linguistically faithful phonetic representations, ensuring robust enhancement with minimal linguistic hallucination. Based on these enhanced phonetic representations, an Adapter generates enhanced acoustic representations containing rich acoustic details, which a neural Vocoder uses to reconstruct corresponding high-fidelity 16-kHz waveforms. A PostNet then converts the waveforms to 48~kHz before resampling them to their original rates, enabling seamless handling of inputs and outputs at multiple sampling rates. Experimental results on several evaluation datasets, covering sub-tasks and full tasks, demonstrate that UniPASE achieves superior or competitive performance compared with existing state-of-the-art models. The proposed model also serves as the backbone of our submission to the URGENT 2026 Challenge, which achieved 1st place in the objective evaluation. The source code and audio demos are available at https://github.com/xiaobin-rong/unipase/.

eess.AS↗

arXiv2026

GAP-URGENet: A Generative-Predictive Fusion Framework for Universal Speech Enhancement

We introduce GAP-URGENet, a generative-predictive fusion framework developed for Track 1 of the ICASSP 2026 URGENT Challenge. The system integrates a generative branch, which performs full-stack speech restoration in a self-supervised representation domain and reconstructs the waveform via a neural vocoder, along with a predictive branch that performs spectrogram-domain enhancement, providing complementary cues. Outputs from both branches are fused by a post-processing module, which also performs bandwidth extension to generate the enhanced waveform at 48 kHz, later downsampled to the original sampling rate. This generative-predictive fusion improves robustness and perceptual quality, achieving top performance in the blind-test phase and ranking 1st in the objective evaluation. Audio examples are available at https://xiaobin-rong.github.io/gap-urgenet_demo.

eess.AS↗

arXiv2026

StuPASE: Towards Low-Hallucination Studio-Quality Generative Speech Enhancement

Achieving high perceptual quality without hallucination remains a challenge in generative speech enhancement (SE). A representative approach, PASE, is robust to hallucination but has limited perceptual quality under adverse conditions. We propose StuPASE, built upon PASE to achieve studio-level quality while retaining its low-hallucination property. First, we show that finetuning PASE with dry targets rather than targets containing simulated early reflections substantially improves dereverberation. Second, to address performance limitations under strong additive noise, we replace the GAN-based generative module in PASE with a flow-matching module, enabling studio-quality generation even under highly challenging conditions. Experiments demonstrate that StuPASE consistently produces perceptually high-quality speech while maintaining low hallucination, outperforming state-of-the-art SE methods. Audio demos are available at: https://xiaobin-rong.github.io/stupase_demo/.

eess.AS↗

arXiv2025

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

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.

eess.AS↗

arXiv2025

A Lightweight Hybrid Dual Channel Speech Enhancement System under Low-SNR Conditions

Although deep learning based multi-channel speech enhancement has achieved significant advancements, its practical deployment is often limited by constrained computational resources, particularly in low signal-to-noise ratio (SNR) conditions. In this paper, we propose a lightweight hybrid dual-channel speech enhancement system that combines independent vector analysis (IVA) with a modified version of the dual-channel grouped temporal convolutional recurrent network (GTCRN). IVA functions as a coarse estimator, providing auxiliary information for both speech and noise, while the modified GTCRN further refines the speech quality. We investigate several modifications to ensure the comprehensive utilization of both original and auxiliary information. Experimental results demonstrate the effectiveness of the proposed system, achieving enhanced speech with minimal parameters and low computational complexity.

eess.AS↗

arXiv2025

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network

Universal speech enhancement aims to handle input speech with different distortions and input formats. To tackle this challenge, we present TS-URGENet, a Three-Stage Universal, Robust, and Generalizable speech Enhancement Network. To address various distortions, the proposed system employs a novel three-stage architecture consisting of a filling stage, a separation stage, and a restoration stage. The filling stage mitigates packet loss by preliminarily filling lost regions under noise interference, ensuring signal continuity. The separation stage suppresses noise, reverberation, and clipping distortion to improve speech clarity. Finally, the restoration stage compensates for bandwidth limitation, codec artifacts, and residual packet loss distortion, refining the overall speech quality. Our proposed TS-URGENet achieved outstanding performance in the Interspeech 2025 URGENT Challenge, ranking 2nd in Track 1.

eess.AS↗

arXiv2025

UL-UNAS: Ultra-Lightweight U-Nets for Real-Time Speech Enhancement via Network Architecture Search

Lightweight models are essential for real-time speech enhancement applications. In recent years, there has been a growing trend toward developing increasingly compact models for speech enhancement. In this paper, we propose an Ultra-Lightweight U-net optimized by Network Architecture Search (UL-UNAS), which is suitable for implementation in low-footprint devices. Firstly, we explore the application of various efficient convolutional blocks within the U-Net framework to identify the most promising candidates. Secondly, we introduce two boosting components to enhance the capacity of these convolutional blocks: a novel activation function named affine PReLU and a causal time-frequency attention module. Furthermore, we leverage neural architecture search to discover an optimal architecture within our carefully designed search space. By integrating the above strategies, UL-UNAS not only significantly outperforms the latest ultra-lightweight models with the same or lower computational complexity, but also delivers competitive performance compared to recent baseline models that require substantially higher computational resources. Source code and audio demos are available at https://github.com/Xiaobin-Rong/ul-unas.

eess.AS↗

arXiv2025

Adaptive Convolution for CNN-based Speech Enhancement Models

Deep learning-based speech enhancement methods have significantly improved speech quality and intelligibility. Convolutional neural networks (CNNs) have been proven to be essential components of many high-performance models. In this paper, we introduce adaptive convolution, an efficient and versatile convolutional module that enhances the model's capability to adaptively represent speech signals. Adaptive convolution performs frame-wise causal dynamic convolution, generating time-varying kernels for each frame by assembling multiple parallel candidate kernels. A lightweight attention mechanism is proposed for adaptive convolution, leveraging both current and historical information to assign adaptive weights to each candidate kernel. This enables the convolution operation to adapt to frame-level speech spectral features, leading to more efficient extraction and reconstruction. We integrate adaptive convolution into various CNN-based models, highlighting its generalizability. Experimental results demonstrate that adaptive convolution significantly improves the performance with negligible increases in computational complexity, especially for lightweight models. Moreover, we present an intuitive analysis revealing a strong correlation between kernel selection and signal characteristics. Furthermore, we propose the adaptive convolutional recurrent network (AdaptCRN), an ultra-lightweight model that incorporates adaptive convolution and an efficient encoder-decoder design, achieving superior performance compared to models with similar or even higher computational costs.

eess.AS↗