hao25@interspeech_2025@ISCA

Total: 1

#1 L3C-DeepMFC: Low-Latency Low-Complexity Deep Marginal Feedback Cancellation with Closed-Loop Fine Tuning for Hearing Aids [PDF] [Copy] [Kimi] [REL]

Authors: Fengyuan Hao, Brian C. J. Moore, Huiyong Zhang, Xiaodong Li, Chengshi Zheng

Feedback control in hearing aids mitigates acoustic feedback caused by the coupling between the receiver and microphone. While DNN-based methods have achieved progress, they remain computationally intensive with relatively high latency. This paper introduces L3C-DeepMFC, a low-latency and low-complexity time-frequency (T-F) domain method that employs complex spectrum mapping to estimate the magnitude and phase components of the desired speech. This method integrates full- and sub-band recurrent modeling to capture spectro-temporal patterns and modifies the overlap-add method for low-latency processing. Moreover, we utilize closed-loop fine tuning with dynamically generated feedback mixtures to minimize the mismatch between training and estimation. Evaluations using the AISHELL-3 dataset confirm its competitive performance across various gains, significantly improving the maximum stable gain (MSG). Integration with traditional methods shows better performance of feedback suppression.

Subject: INTERSPEECH.2025 - Others