High-quality speech synthesis using context-dependent syllabic units.
Takashi SaitoYasuhide HashimotoMasaharu SakamotoPublished in: ICASSP (1996)
Keyphrases
- context dependent
- speech synthesis
- high quality
- speech recognition
- text to speech
- semantic level
- context free
- low level
- vocal tract
- natural language
- user centric
- prosodic features
- low quality
- high level
- high resolution
- image quality
- higher quality
- speech corpus
- pattern recognition
- context sensitive
- neural network
- language model
- co occurrence
- information extraction
- hidden markov models
- similarity measure
- image processing
- computer vision