Improvement of animated articulatory gesture extracted from speech for pronunciation training.
Yurie IribeSilasak ManosavanhKouichi KatsuradaRyoko HayashiChunyue ZhuTsuneo NittaPublished in: ICASSP (2012)
Keyphrases
- speech recognition
- acoustic models
- hidden markov models
- speech signal
- multi stream
- automatic speech recognition
- speech recognizer
- speech synthesis
- vocal tract
- language model
- hearing impaired
- gesture recognition
- speaker independent
- training set
- speech recognition systems
- speaker identification
- noisy environments
- discriminative training
- significant improvement
- training phase
- audio visual
- test set
- spontaneous speech
- training process
- automatically generated
- probabilistic model
- automatic speech recognition systems
- hand movements
- recognition engine
- training examples
- neural network