By establishing a human perceptual alignment metric and conducting systematic analysis, it is demonstrated that perceptual alignment is governed far more by how a model is trained (its learning objective) than by how well it performs (EER).
Szu-Chi Chen, Jia-Tang Dong, Yi-Cheng Lin et al.· 0 citations
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 and do not explicitly exploit harmonic periodicity, a strong cue for preserving voiced speech under noise. Perceptual optimization poses ano...
Shang-Fu Chen, Szu-Wei Fu, Sung-Feng Huang et al.· 0 citations
This work training a LALM with reinforcement learning to reason over its own speech output generates a draft speech as a form of audio-token reasoning, critiques its own generation by reflecting on the acoustic realization in text, and produces a refined version conditioned on both the first-pass speech and the critiqu...
Chee-En Yu, Yi-Cheng Lin, Sung-Feng Huang et al.· 1 citation
This work presents RT-SEMamba, a fully causal speech enhancement (SE) model built upon causal time-frequency Mamba blocks, and introduces a progressive knowledge distillation (KD) strategy that compresses an 8-layer teacher into a shallow 1-layer student by jointly distilling complex spectral outputs and intermediate r...
Rong Chao, Sung-Feng Huang, Moreno La Quatra et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.