A CRN-based deep ANC system with complex spectrum mapping and a voice retention loss outperforms FxLMS in noise reduction while preserving speech naturalness and intelligibility in ISM-simulated reverberant environments.
A new hybrid adaptive self-loading FxLMS and CNN-GRU net for active time-varying noise control,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SP 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Speech-preserving active noise control: a deep learning approach in reverberant environments
A CRN-based deep ANC system with complex spectrum mapping and a voice retention loss outperforms FxLMS in noise reduction while preserving speech naturalness and intelligibility in ISM-simulated reverberant environments.