Further optimisation of a robust IMELDA speech recogniser for applications with severely degraded speech.
Claude LefèbvreDariusz A. ZwierzynskiDavid R. StarksGary BirchPublished in: ICSLP (1992)
Keyphrases
- speech recognition
- audio visual
- speech signal
- recognition engine
- speech synthesis
- text to speech
- speaker recognition
- spoken language
- noisy environments
- automatic speech recognition
- endpoint detection
- emotion recognition
- human computer interaction
- computationally efficient
- dialogue system
- image sequences
- motion blur
- multi objective
- pattern recognition