TensorFlow/Keras reference implementation for detecting AI-generated speech using Mel-spectrogram features and a compact 2D CNN. The project ships with utilities for training a demonstration model on ...
Abstract: A non-invasive pathological voice detection system has been presented in this paper. This work considers two spectral images of voice signals namely spectrogram and Mel-spectrogram to detect ...
This project aims at building a speech enhancement system to attenuate environmental noise. Audios have many different ways to be represented, going from raw time series to time-frequency ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results