A Perceptual Neural Audio Coder with a Mean-Scale Hyperprior.
Joon ByunSeungmin ShinYoungcheol ParkJongmo SungSeungkwon BeackPublished in: ICASSP (2023)
Keyphrases
- network architecture
- cross modal
- multimedia
- image compression
- image coding
- neural network
- visual processing
- subband
- audio visual
- broadcast news
- visual perception
- bitstream
- digital video
- visual information
- multi modal
- scale space
- low level
- audio video
- human perception
- perceptual grouping
- multimedia information
- quantization scheme
- audio stream