Towards Realizing Sign Language-to-Speech Conversion by Combining Deep Learning and Statistical Parametric Speech Synthesis.
Xiaochun AnHongwu YangZhenye GanPublished in: ICYCSEE (1) (2016)
Keyphrases
- speech synthesis
- deep learning
- sign language
- speech recognition
- text to speech
- sign language recognition
- vocal tract
- gesture recognition
- prosodic features
- unsupervised learning
- machine learning
- sign recognition
- unsupervised feature learning
- speech corpus
- mental models
- hand gestures
- weakly supervised
- language model
- high dimensional
- image processing
- speech signal
- human computer interaction
- training data
- learning algorithm