High quality speech synthesis using a small speech dataset.
Pavel ChistikovAndrey TalanovPublished in: SLTU (2014)
Keyphrases
- speech synthesis
- speech recognition
- high quality
- text to speech
- vocal tract
- prosodic features
- speech signal
- small number
- training dataset
- genetic algorithm
- automatic speech recognition
- higher quality
- feature set
- benchmark datasets
- multi modal
- ground truth
- high resolution
- image processing
- machine learning
- speech corpus