Audiovisual-to-Articulatory Speech Inversion Using HMMs.
Athanassios KatsamanisGeorge PapandreouPetros MaragosPublished in: MMSP (2007)
Keyphrases
- multi stream
- audio visual
- speech recognition
- hidden markov models
- multi modal
- emotion recognition
- speech signal
- speech synthesis
- vocal tract
- visual information
- visual data
- automatic speech recognition
- speaker identification
- pattern recognition
- speech recognizer
- multimedia
- image reconstruction
- audio features
- speaker verification
- recognition engine
- acoustic models
- handwriting recognition
- noisy environments
- speech recognition systems