GitHub

Making Acoustic Side-Channel Attacks on Noisy Keyboards Viable with LLM-Assisted Spectrograms "Typo" Correction

This repo is the implementation of a research project aimed at enhancing Acoustic Side-Channel Attacks (ASCAs) using a novel combination of Vision Transformers (VTs) and Large Language Models (LLMs).
GitHub

songsee — FFT so pretty, your ears will be jealous.

--output Output path (default: input name + extension) --format jpg or png (default: jpg) --width Output width (default: 1920) --height Output height (default: 1080 ...
IEEE

Spectrum Sensing in Radar-Communications Systems for Signal Identification: Deep Learning with Error-Guided Refinement

Abstract: This paper introduces Optimal Spectrogram Network (OS-Net), an encoder-decoder architecture tailored for segmenting wireless signals in the time-frequency domain. OS-Net integrates a ...
IEEE

Research on Silent Speech Reconstruction Based on the BigVGAN Network

Abstract: To make the audio of silent electromyographic facial motion speech reconstruction sound smoother, more natural, and realistic, this paper combines the Transformer network with the BigVGAN ...