Rao NK, Chetupalli SR, Shetu S, Habets E, Thiergart O (2025)
Publication Type: Conference contribution
Publication year: 2025
Publisher: Institute of Electrical and Electronics Engineers Inc.
Conference Proceedings Title: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
DOI: 10.1109/ICASSP49660.2025.10890597
Existing neural network-based speech dereverberation approaches use a fixed-length early reflection part of the reverberant signal as the target for estimation, irrespective of the severity of reverberation. Such an approach often leads to distortions in the enhanced signals in highly reverberant scenarios. In practice, while some listeners prefer minimal speech distortions, others have a higher tolerance for distortions and prefer a clean signal. To address these points, we propose a novel target definition and a low-complexity neural network for user-controlled single-channel dereverberation. Our target definition is parameterized by the relative amount of reduction in the late reverberation energy. Further, the same parameter is passed as a control input to the dereverberation network for adaptability during inference. Objective and subjective evaluation shows the feasibility of the proposed dereverberation approach.
APA:
Rao, N.K., Chetupalli, S.R., Shetu, S., Habets, E., & Thiergart, O. (2025). Low-Complexity Neural Speech Dereverberation With Adaptive Target Control. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Hyderabad, IN: Institute of Electrical and Electronics Engineers Inc..
MLA:
Rao, Nagashree K.S., et al. "Low-Complexity Neural Speech Dereverberation With Adaptive Target Control." Proceedings of the 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025, Hyderabad Institute of Electrical and Electronics Engineers Inc., 2025.
BibTeX: Download