IEEE

CleanMel: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR

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 ...
IEEE

FFT-Trans: Enhancing Robustness in Mechanical Fault Diagnosis With Fourier Transform-Based Transformer Under Noisy Conditions

Abstract: A fast and effective fault diagnosis system is crucial for ensuring complex mechanical equipment’s safe and reliable operation. Deep learning has shown promising prospects in fault diagnosis ...
GitHub

SkyShield - RF-Based Drone Detection & Threat Classification System

Drones are everywhere. Some are harmless (photography, delivery, agriculture). Some are not (surveillance, smuggling, weaponized attacks). Current counter-drone systems cost $100K - $5M+ and are only ...
GitHub

Beyond Spectrograms: Rethinking Audio Classification from EnCodec’s Latent Space

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 ...