Mack, WolfgangWolfgangMackHabets, EmanuelEmanuelHabets2023-08-222023-08-222023https://publica.fraunhofer.de/handle/publica/44851310.1109/SLT54892.2023.100232062-s2.0-85147799459State-of-the-art acoustic echo and noise reduction combines adaptive filters with a deep neural network-based postfilter. While the signal-to-distortion ratio is often used for training, it is not well-defined for all echo-reduction scenarios. We propose well-defined loss functions for training and modifications of a recently proposed echo reduction system that is based on informed source extraction. The modifications include using a Kalman filter as a prefilter and a cyclical learning rate scheduler. The proposed modifications improve the performance on the blind test set of the Interspeech 2021 AEC challenge. A comparison to the challenge-winner shows that the proposed system underperforms the winner by 0.1 mean opinion score (MOS) points in double-talk echo reduction. However, it outperforms the winner by 0.3 MOS points in echo-only echo reduction. In all other scenarios, both algorithms perform comparably.enAcoustic Echo ReductionDNNKalman FilterMaskingSpeech Enhancementconference paper