2025/05/27 by Haixin Zhao, Zhao, Haixin, Nilesh Madhu +1 · 1 citation
Computer Science · Engineering · #Advanced Adaptive Filtering Techniques #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Sound (cs.SD) #Speech and Audio Processing #electronic engineering #information engineering
paper · doi:10.48550/arxiv.2505.21057
openalex publication_date 2025/05/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/31
In speech enhancement, achieving state-of-the-art (SotA) performance while adhering to the computational constraints on edge devices remains a formidable challenge. Networks integrating stacked temporal and spectral modelling effectively leverage improved architectures such as transformers; however, they inevitably incur substantial computational complexity and model expansion. Through systematic ablation analysis on transformer-based temporal and spectral modelling, we demonstrate that the architecture employing streamlined Frequency-Time-Frequency (FTF) stacked transformers efficiently learns global dependencies within causal context, while avoiding considerable computational demands. Utilising discriminators in training further improves learning efficacy and enhancement without introducing additional complexity during inference. The proposed lightweight, causal, transformer-based architecture with adversarial training (LCT-GAN) yields SoTA performance on instrumental metrics among contemporary lightweight models, but with far less overhead. Compared to DeepFilterNet2, the LCT-GAN only requires 6% of the parameters, at similar complexity and performance. Against CCFNet+(Lite), LCT-GAN saves 9% in parameters and 10% in multiply-accumulate operations yet yielding improved performance. Further, the LCT-GAN even outperforms more complex, common baseline models on widely used test datasets.