Multi-space channel representation learning for mono-to-binaural conversion based audio deepfake detection
Lists
Only you see this
Abstract
Highlights•We pioneer the definition of a feature representation of binaural audio as three spaces.•We present MSCR-ADD, a novel ADD scheme with a novel multi-space channel representation learning strategy.•Experimental results on four datasets verify the power of our method.
BibTeX
@article{liu2024multi,
author = {Rui Liu and Jinhua Zhang and Guanglai Gao},
title = {{Multi-space channel representation learning for mono-to-binaural conversion based audio deepfake detection}},
journal = {Information Fusion},
year = {2024},
doi = {10.1016/j.inffus.2024.102257},
}Loading related content...