Continuous Episodic Memory Based Speech Recognition Using Articulatory Dynamics.
Sébastien DemangeSlim OuniPublished in: INTERSPEECH (2011)
Keyphrases
- speech recognition
- vocal tract
- speech signal
- speech synthesis
- multi stream
- automatic speech recognition
- acoustic features
- spoken language
- dynamical systems
- audio visual
- speech processing
- text to speech
- linear prediction
- dynamic model
- recognition engine
- neural dynamics
- artificial intelligence
- formant frequencies
- memory based learning
- highly nonlinear
- speaker recognition
- emotion recognition
- visual information
- non stationary
- language model