Speech Synthesis Based on Articulatory-Movement HMMs with Voice-Source Codebooks.
Tsuneo NittaTakayuki OnodaMasashi KimuraYurie IribeKouichi KatsuradaPublished in: INTERSPEECH (2011)
Keyphrases
- speech synthesis
- speech recognition
- hidden markov models
- vocal tract
- text to speech
- prosodic features
- automatic speech recognition
- vector quantization
- speech signal
- pattern recognition
- language model
- speech corpus
- noisy environments
- speaker identification
- gesture recognition
- image representation
- multi stream
- vector quantizer
- image patches
- word processing
- feature space
- reinforcement learning
- multiscale
- neural network