Deep Denoising Auto-encoder for Statistical Speech Synthesis.
Zhenzhou WuShinji TakakiJunichi YamagishiPublished in: CoRR (2015)
Keyphrases
- speech synthesis
- denoising
- speech recognition
- text to speech
- image denoising
- total variation
- vocal tract
- prosodic features
- wavelet domain
- natural images
- noisy images
- image processing
- wavelet packet
- rate distortion
- bit rate
- neural network
- noise removal
- speech corpus
- gaussian noise
- low complexity
- statistical analysis
- denoising methods
- information theoretic
- subband
- motion estimation