IEEE

A Multimodal Deep Learning Framework for Depression Detection Using Vision Transformers and Large Language Models

Abstract: This study proposes a novel multimodal deep learning framework for depression detection, integrating visual, audio, and textual data. Using OpenFace and Librosa for feature extraction, the ...
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).
IEEE

Model-Guided Deep Learning for Line Segment Detection in Time–Frequency Spectrograms of an Ocean Waveguide

Abstract: The application of machine learning in underwater acoustics is often limited by the lack of high-quality data. One method to avoid this data issue is to use modeled data to train a machine ...
GitHub

SoundPlot: Birdsong Acoustic Analysis & Neural Synthesis Framework

An open-source framework for analyzing birdsong recordings through acoustic feature extraction, dimensionality reduction, and neural audio synthesis. Transform audio signals into interactive 3D ...