BAE-Net: a Low Complexity and High Fidelity Bandwidth-Adaptive Neural Network for Speech Super-Resolution.
Guochen YuXiguang ZhengNan LiRunqiang HanChengshi ZhengChen ZhangChao ZhouQi HuangBing YuPublished in: ICASSP (2024)
Keyphrases
- low complexity
- high fidelity
- super resolution
- high resolution
- motion estimation
- video streaming
- low resolution
- high quality
- image restoration
- image reconstruction
- low resolution images
- real time
- computational complexity
- multi frame
- video sequences
- video coding
- motion vectors
- audio visual
- low spatial resolution
- spatial resolution
- distributed video coding
- image sequences
- multiple description coding
- inter frame
- computer vision
- motion compensated
- video compression
- motion compensation
- motion model
- depth map
- compressed video
- optical flow
- spatial domain
- error resilient
- multimedia
- image processing