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: This study proposes an innovative speech translation method based on Pix2PixGAN, which maps the Mel spectrograms of speech produced by deaf individuals to those of normal-hearing individuals ...
All the datasets must be located in the datasets folder. This folder should contain the following subfolders after downloading the datasets: GTZAN Speech_Music: Contains the GTZAN Speech Music dataset ...
This is a more advanced, but more flexible version of the original program. It changes the spectrometer from educational 'toy' to serious instrument, which can easily compete with commercial units ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results