Phonological feature based variable frame rate scheme for improved speech recognition.
Abhijeet SangwanJohn H. L. HansenPublished in: ASRU (2007)
Keyphrases
- speech recognition
- frame rate
- video sequences
- high speed
- hidden markov models
- language model
- video camera
- speech processing
- automatic speech recognition
- speech signal
- speech synthesis
- pattern recognition
- noisy environments
- speech recognition technology
- video quality
- motion blur
- speech recognition systems
- speech retrieval
- speaker identification
- d scene
- speaker adaptation
- speech recognizers
- speech recognizer
- speaker independent
- neural network
- audio visual speech recognition
- speaker dependent
- bitstream
- information retrieval