Abstract: In this work, we propose CleanMel, a single-channel Mel-spectrogram denoising and dereverberation network for improving both speech quality and automatic speech recognition (ASR) performance ...
Abstract: The rapid proliferation of deepfake techniques has introduced diverse forgery artifacts, posing substantial challenges to audio anti-spoofing. This paper proposes a model that adaptively ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results