Speaker identification with whispered speech based on modified LFCC parameters and feature mapping.
Xing FanJohn H. L. HansenPublished in: ICASSP (2009)
Keyphrases
- speaker identification
- feature mapping
- speech signal
- speech recognition
- gaussian mixture model
- broadcast news
- noisy environments
- feature extraction
- endpoint detection
- maximum likelihood
- multiple instance learning
- hidden markov models
- audio features
- mixture model
- feature space
- pattern recognition
- data analysis
- automatic speech recognition
- support vector
- training data
- clustering algorithm
- computer vision