Phoneme Embedding and its Application to Speech Driven Talking Avatar Synthesis.
Xu LiZhiyong WuHelen M. MengJia JiaXiaoyan LouLianhong CaiPublished in: INTERSPEECH (2016)
Keyphrases
- speech recognition
- facial animation
- speech synthesis
- automatic speech recognition
- automatic speech recognition systems
- phoneme recognition
- hidden markov models
- speaker dependent
- speech signal
- speech sounds
- facial expressions
- virtual world
- speech recognizer
- data driven
- text to speech
- virtual reality
- vocal tract
- language model
- prosodic features
- recognition engine
- program synthesis
- context dependent
- broadcast news
- nonlinear dimensionality reduction
- noisy environments
- graph embedding
- visual speech
- linear prediction
- speech recognition systems
- multidimensional scaling
- human computer interaction
- watermarking technique
- endpoint detection
- sign language