Adaptive Multi-Frame-Rate Scheme for Distributed Speech Recognition Based on a Half Frame-Rate Front-End.
Zheng-Hua TanPaul DalsgaardBørge LindbergPublished in: MMSP (2005)
Keyphrases
- frame rate
- speech recognition
- video sequences
- high speed
- hidden markov models
- speech synthesis
- video camera
- video quality
- language model
- speech signal
- automatic speech recognition
- speech recognition technology
- pattern recognition
- speech recognizers
- speech recognition systems
- speech recognizer
- noisy environments
- speech processing
- d scene
- motion blur
- dynamic scenes
- speaker identification
- probabilistic model
- image processing
- feature selection