Improving Speaker Identification Performance Under the Shouted Talking Condition Using the Second-Order Hidden Markov Models.
Ismail ShahinPublished in: EURASIP J. Adv. Signal Process. (2005)
Keyphrases
- hidden markov models
- speaker identification
- speech recognition
- speech signal
- speech processing
- speaker independent
- audio signals
- speaker dependent
- noisy environments
- gaussian mixture model
- baum welch
- automatic speech recognition
- speech recognizer
- higher order
- sequential data
- broadcast news
- neural network
- document images
- visual speech
- spatio temporal
- pattern recognition
- information retrieval