A Pruned-CELP Speech Codec Using Denoising Autoencoder with Spectral Compensation for Quality and Intelligibility Enhancement.
Yu-Ting LoSyu-Siang WangYu TsaoSheng-Yu PengPublished in: AICAS (2019)
Keyphrases
- denoising
- speech recognition
- linear prediction
- image processing
- high quality
- quality assessment
- image denoising
- noisy images
- spectral features
- total variation
- image coding
- neural network
- natural images
- speech signal
- speech quality
- gaussian mixture model
- video coding
- gaussian noise
- wavelet packet
- automatic speech recognition
- noisy environments
- markov random field
- pruning algorithm
- speaker identification
- motion estimation