Real time face detection for multimodal speech recognition.
Kazumasa MuraiSatoshi NakamuraPublished in: ICME (2) (2002)
Keyphrases
- speech recognition
- real time face detection
- face detection
- hidden markov models
- language model
- pattern recognition
- speech synthesis
- automatic speech recognition
- haar like features
- noisy environments
- multi modal
- speech recognition technology
- speech recognizer
- speech signal
- speech recognition systems
- neural network
- speaker identification
- multi stream
- maximum likelihood
- audio visual
- noise reduction
- face recognition
- image processing