Neural Network-augmented Kalman Filtering for Robust Online Speech Dereverberation in Noisy Reverberant Environments
This addresses speech enhancement for applications in noisy reverberant settings, but it is incremental as it builds on existing Kalman filtering and WPE methods with neural network augmentation.
The paper tackled robust online speech dereverberation in noisy environments by proposing a neural network-augmented Kalman filtering variant of the weighted prediction error method, which corrected filter variations estimation to avoid distortions and achieved strong dereverberation and denoising performance, especially for highly noisy inputs.
In this paper, a neural network-augmented algorithm for noise-robust online dereverberation with a Kalman filtering variant of the weighted prediction error (WPE) method is proposed. The filter stochastic variations are predicted by a deep neural network (DNN) trained end-to-end using the filter residual error and signal characteristics. The presented framework allows for robust dereverberation on a single-channel noisy reverberant dataset similar to WHAMR!. The Kalman filtering WPE introduces distortions in the enhanced signal when predicting the filter variations from the residual error only, if the target speech power spectral density is not perfectly known and the observation is noisy. The proposed approach avoids these distortions by correcting the filter variations estimation in a data-driven way, increasing the robustness of the method to noisy scenarios. Furthermore, it yields a strong dereverberation and denoising performance compared to a DNN-supported recursive least squares variant of WPE, especially for highly noisy inputs.