Speech Recognition on MPEG/Audio Encoded Files.
Lawrence YappGregory L. ZickPublished in: ICMCS (1997)
Keyphrases
- speech recognition
- multimedia
- speaker identification
- speech processing
- speech recognition technology
- audio visual speech recognition
- hidden markov models
- automatic speech recognition
- speech signal
- video signals
- speech synthesis
- language model
- cepstral coefficients
- audio signals
- broadcast news
- speech recognizer
- pattern recognition
- speaker recognition
- noisy environments
- metadata
- voice activity detection
- compressed domain
- audio visual
- speech recognition systems
- speech recognizers
- signal processing
- speaker dependent
- audio features
- mel frequency cepstral coefficients
- visual information
- visual data
- multimedia information
- multi modal
- multimedia data
- acoustic features
- isolated word
- neural network