DiffVQE is presented as the first reproducible diffusion-based AEC model that outperforms Microsoft's DeepVQE in echo/noise control, model size, and computational complexity using URGENT Challenge data.
EchoFree: Towards Ultra Lightweight and Efficient Neural Acoustic Echo Cancellation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
other 1
citation-polarity summary
fields
eess.AS 2years
2026 2verdicts
UNVERDICTED 2roles
other 1polarities
unclear 1representative citing papers
LMPAN is a 480K-parameter network using multi-path alignment, attention integration, and dynamic post-filtering that matches larger models on joint AEC and NS while supporting real-time inference.
citing papers explorer
-
DiffVQE: Hybrid Diffusion Voice Quality Enhancement Under Acoustic Echo and Noise
DiffVQE is presented as the first reproducible diffusion-based AEC model that outperforms Microsoft's DeepVQE in echo/noise control, model size, and computational complexity using URGENT Challenge data.
-
LMPAN: A Lightweight Multi-Path Alignment Network for Joint Full-Duplex Acoustic Echo Cancellation and Noise Suppression
LMPAN is a 480K-parameter network using multi-path alignment, attention integration, and dynamic post-filtering that matches larger models on joint AEC and NS while supporting real-time inference.