Continuous Articulatory-to-Acoustic Mapping using Phone-based Trajectory HMM for a Silent Speech Interface.
Thomas HueberGérard BaillyBruce DenbyPublished in: INTERSPEECH (2012)
Keyphrases
- speech recognition
- acoustic models
- hidden markov models
- speaker independent
- speech signal
- automatic speech recognition
- speech recognizer
- speech recognition systems
- multi stream
- acoustic features
- speech synthesis
- language model
- speech sounds
- pattern recognition
- emotional speech
- speech processing
- vocal tract
- noisy speech
- speaker identification
- speech recognizers
- noisy environments
- handwriting recognition
- emotion recognition
- keyword spotting
- audio visual
- broadcast news
- automatic speech recognition systems
- user interface
- speaker adaptation
- spatio temporal
- recognition engine
- discriminative training
- user friendly
- formant frequencies