Effective lip localization and tracking for achieving multimodal speech recognition.
Wei Chuang OoiChangwon JeonKihyeon KimDavid K. HanHanseok KoPublished in: MFI (2008)
Keyphrases
- speech recognition
- audio visual speech recognition
- multi stream
- hidden markov models
- audio visual
- language model
- speech processing
- speech synthesis
- automatic speech recognition
- noisy environments
- speaker identification
- pattern recognition
- speech signal
- multi modal
- speech recognition technology
- lip reading
- speech recognizer
- keyword spotting
- speech recognizers
- speech recognition systems
- speech understanding
- visual speech recognition
- localization method