HMM-based text-to-audio-visual speech synthesis.
Shinji SakoKeiichi TokudaTakashi MasukoTakao KobayashiTadashi KitamuraPublished in: INTERSPEECH (2000)
Keyphrases
- audio visual
- speech synthesis
- text to speech
- speech recognition
- multi modal
- hidden markov models
- visual information
- multi stream
- multimedia
- visual data
- vocal tract
- audio visual speech recognition
- emotion recognition
- speaker verification
- person authentication
- automatic speech recognition
- word processing
- information retrieval
- text documents
- human body
- document collections
- text mining
- nearest neighbor
- video sequences
- image processing
- neural network