Cheapnet: Improving Light-weight Speech Enhancement Network By Projected Loss Function
2023 · Kaijun Tan, Benzhe Dai, Jiakui Li, et al.
Abstract
Noise suppression and echo cancellation are critical in speech enhancement and essential for smart devices and real-time communication. Deployed in voice processing front-ends and edge devices, these algorithms must ensure efficient real-time inference with low computational demands. Traditional edge-based noise suppression often uses MSE-based amplitude spectrum mask training, but this approach has limitations. We introduce a novel projection loss function, diverging from MSE, to enhance noise suppression. This method uses projection techniques to isolate key audio components from noise, significantly improving model performance. For echo cancellation, the function enables direct predictions on LAEC pre-processed outputs, substantially enhancing performance. Our noise suppression model achieves near state-of-the-art results with only 3.1M parameters and 0.4GFlops/s computational load. Moreover, our echo cancellation model outperforms replicated industry-leading models, introducing a n
Authors
(none)
Tags
Stats
Related papers
- Lisennet: Lightweight Sub-band And Dual-path Modeling For Real-time Speech Enhancement (2024)9.03
- Effect Of Noise Suppression Losses On Speech Distortion And ASR Performance (2021)10.74
- A Consolidated View Of Loss Functions For Supervised Deep Learning-based Speech Enhancement (2020)13.93
- Dense-tsnet: Dense Connected Two-stage Structure For Ultra-lightweight Speech Enhancement (2024)0.00
- Thlnet: Two-stage Heterogeneous Lightweight Network For Monaural Speech Enhancement (2023)0.00
- Lmfca-net: A Lightweight Model For Multi-channel Speech Enhancement With Efficient Narrow-band And Cross-band Attention (2025)3.58
- F-T-LSTM Based Complex Network For Joint Acoustic Echo Cancellation And Speech Enhancement (2021)11.19
- Weighted Speech Distortion Losses For Neural-network-based Real-time Speech Enhancement (2020)14.51