activity
20242026
collaborators

13 papers

eess.AS2026

Listen, Critique, and Refine: RL-Based Self-Refinement for Instruction-Following Speech Synthesis

Chee-En Yu, Yi-Cheng Lin, Sung-Feng Huang +4

Large Audio Language Models (LALMs) can follow diverse instructions to synthesize speech in specified styles. However, complex instructions that require simultaneous control over p…

eess.AS2026

HAMMER: Harmonic-Aware Parallel Context Modeling and Discriminator-Free Perceptual Optimization for Speech Enhancement

Shang-Fu Chen, Szu-Wei Fu, Sung-Feng Huang +3

Recent speech enhancement systems combine self-attention and Mamba to capture global interactions and long-range dependencies. Yet these hybrids usually operate as sequence mixers…

cs.SD2026

RT-SEMamba: Real-Time Speech Enhancement Mamba via Progressive Knowledge Distillation

Rong Chao, Sung-Feng Huang, Moreno La Quatra +4

We present RT-SEMamba, a fully causal speech enhancement (SE) model built upon causal time-frequency Mamba blocks. Unlike Transformer-based architectures that rely on a growing key…

cs.SD2026

One Model, Many Latencies: Universal Speech Enhancement for Diverse Real-Time Applications

Szu-Wei Fu, Rong Chao, Xuesong Yang +4

Different real-time speech applications impose distinct latency budgets, often requiring separately trained enhancement models for each scenario. In this paper, we propose a one-fo…

cs.SD2026

Rethinking Training Targets, Architectures and Data Quality for Universal Speech Enhancement

Szu-Wei Fu, Rong Chao, Xuesong Yang +6

Universal Speech Enhancement (USE) aims to restore speech quality under diverse degradation conditions while preserving signal fidelity. Despite recent progress, key challenges in…

eess.AS2026

How Auditory Knowledge in LLM Backbones Shapes Audio Language Models: A Holistic Evaluation

Ke-Han Lu, Szu-Wei Fu, Chao-Han Huck Yang +13

Large language models (LLMs) have been widely used as knowledge backbones of Large Audio Language Models (LALMs), yet how much auditory knowledge they encode through text-only pre-…