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

作者：Jiadong Zhao, Dahan Wang, Yu Sun, Leyan Yang, Xiaobin Rong, Shiruo Sun, Yuxiang Hu, Jing Lu · 发表于：arXiv (Cornell University) · 年份：2026 · DOI：10.48550/arxiv.2606.12328 · 研究领域：Speech and Audio Processing、Speech Recognition and Synthesis、Advanced Adaptive Filtering Techniques

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.