Image-driven Audio-visual Universal Source Separation.

Chenxing Li Ye Bai Yang Wang Feng Deng Yuanyuan Zhao Zhuo Zhang Xiaorui Wang

Published in: INTERSPEECH (2023)

Keyphrases

audio visual
visual data
image data
source separation
multi modal
multiscale
audio features
image classification
image collections
image content
low level
visual information
multimedia
image retrieval
image features
image representation
data sets
visual features
feature vectors
high dimensional
image processing