[Project launch] Everyday sound recognition with limited annotations
The goal is to explore general-proposed audio understanding in the limited annotations.
Jinhua Liang
Hello, welcome to my homepage. I am Jinhua Liang, a final-year PhD researcher at Queen Mary University of London. I am fortunate to be co-advised by Emmanouil Benetos, Huy Phan, and Mark Sandler.
My research expertise lies in the fields of Multimodal Learning for Audio Perception, Generative AI for Audio Content Creation and Editing, (Low-Shot) Acoustic Pattern Recognition, Auditory Scene Analysis, Model Compression and Acceleration, and Audio Emotion Analysis. Specifically, I have hands-on research experience on developing large language models (LLMs) as a universal system for audio understanding or generation.
Recent Posts
Channel Compression: Rethinking Information Redundancy Among Channels in CNN Architecture
This paper is accepted by IEEE Access.
Research on efficient acoustic scene recognition based on deep learning
The goal is to explore high-performance acoustic scene classification (ASC) technologies at a low computational cost.
Acoustic scene classification using deep cnn with fine-resolution feature
Accepted by Expert Systems with Applications.