Text-to-audio-visual speech synthesis based on parameter generation from HMM.
Masatsune TamuraShigekazu KondoTakashi MasukoTakao KobayashiPublished in: EUROSPEECH (1999)
Keyphrases
- audio visual
- speech synthesis
- multi stream
- speech recognition
- text to speech
- hidden markov models
- multi modal
- audio visual speech recognition
- vocal tract
- visual data
- visual information
- multimedia
- speech signal
- information retrieval
- text mining
- text documents
- automatic speech recognition
- emotion recognition
- language model
- speaker verification
- pattern recognition
- keywords
- machine learning
- contextual information
- image classification
- word processing
- image features
- video sequences