Multimodal HMM-based NAM-to-speech conversion.
Viet-Anh TranGérard BaillyHélène LoevenbruckTomoki TodaPublished in: INTERSPEECH (2009)
Keyphrases
- audio visual
- hidden markov models
- multimodal interfaces
- speech recognition
- multi stream
- speech signal
- multimodal interaction
- multi modal
- speech synthesis
- text to speech
- automatic speech recognition
- human computer interaction
- visual speech
- dialogue system
- spoken language
- speaker verification
- speech processing
- recognition engine
- multimodal data
- endpoint detection
- speaker recognition
- speech recognizer
- spontaneous speech
- spoken dialogue systems
- information retrieval
- emotion recognition
- binary images
- non stationary
- video sequences