Using multiple time scales in the framework of multi-stream speech recognition.
Astrid HagenHervé BourlardPublished in: INTERSPEECH (2000)
Keyphrases
- speech recognition
- audio visual speech recognition
- multi stream
- hidden markov models
- language model
- pattern recognition
- speech signal
- automatic speech recognition
- probabilistic model
- audio visual
- noisy environments
- speaker identification
- feature selection
- image data
- speech processing
- speech recognizer
- speech recognition technology