Multimodal Synthesizer for Russian and Czech Sign Languages and Audio-Visual Speech.
Alexey KarpovZdenek KrnoulMilos ZeleznýAndrey RonzhinPublished in: HCI (6) (2013)
Keyphrases
- visual speech
- language independent
- text to speech
- hidden markov models
- visual speech recognition
- speaker identification
- audio visual speech recognition
- language identification
- noisy environments
- audio signals
- speech signal
- video signals
- acoustic features
- cross lingual
- broadcast news
- multi modal
- audio visual
- machine translation
- cross language
- multi stream
- speech recognition
- pattern recognition
- gaussian mixture model
- audio signal