Mack W, Habets E (2023)
Publication Type: Conference contribution
Publication year: 2023
Publisher: Institute of Electrical and Electronics Engineers Inc.
Pages Range: 502-508
Conference Proceedings Title: 2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings
Event location: Doha, QAT
ISBN: 9798350396904
DOI: 10.1109/SLT54892.2023.10023206
State-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.
APA:
Mack, W., & Habets, E. (2023). A Hybrid Acoustic Echo Reduction Approach Using Kalman Filtering and Informed Source Extraction with Improved Training. In 2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings (pp. 502-508). Doha, QAT: Institute of Electrical and Electronics Engineers Inc..
MLA:
Mack, Wolfgang, and Emanuël Habets. "A Hybrid Acoustic Echo Reduction Approach Using Kalman Filtering and Informed Source Extraction with Improved Training." Proceedings of the 2022 IEEE Spoken Language Technology Workshop, SLT 2022, Doha, QAT Institute of Electrical and Electronics Engineers Inc., 2023. 502-508.
BibTeX: Download