Enhancing automatic speaker identification using phoneme clustering and frame based parameter and frame size selection.
Jason W. PelecanosStefan SlomkaSridha SridharanPublished in: ISSPA (1999)
Keyphrases
- speaker identification
- speech recognition
- speaker dependent
- gaussian mixture model
- speaker recognition
- noisy environments
- speech signal
- clustering algorithm
- k means
- feature transformation
- feature extraction
- language model
- broadcast news
- hidden markov models
- unsupervised learning
- neural network
- audio signal
- pattern recognition
- speaker independent
- video frames
- data points
- multimedia