Speech Enhancement with Multi-granularity Vector Quantization.
Xiao-Ying ZhaoQiushi ZhuJie ZhangYeping ZhouPeiqi LiuPublished in: APSIPA ASC (2023)
Keyphrases
- vector quantization
- multi granularity
- speech enhancement
- noise reduction
- noisy environments
- signal to noise ratio
- single channel
- speech signal
- image compression
- multi user
- vector quantizer
- privacy protection
- dynamic integration
- location aware
- linear prediction
- speaker recognition
- multi channel
- computer vision
- speech recognition
- image coding
- signal processing
- feature space
- face recognition