Speaker Identification in Shouted Talking Environments Based on Novel Third-Order Hidden Markov Models.
Ismail ShahinPublished in: CoRR (2017)
Keyphrases
- hidden markov models
- speaker identification
- speech recognition
- speech signal
- speech processing
- speaker independent
- noisy environments
- automatic speech recognition
- gaussian mixture model
- audio signals
- speaker dependent
- broadcast news
- feature extraction
- visual speech
- speech recognizer
- sequential data
- machine learning
- multi modal
- image segmentation
- feature selection