Generative Extraction of Audio Classifiers for Speaker Identification.
Tejumade AfonjaLucas BourtouleVarun ChandrasekaranSageev OoreNicolas PapernotPublished in: CoRR (2022)
Keyphrases
- speaker identification
- feature transformation
- speech recognition
- gaussian mixture model
- speech processing
- speaker recognition
- audio signals
- broadcast news
- speech signal
- feature extraction
- noisy environments
- linear classifiers
- support vector
- audio features
- audio signal
- training data
- information extraction
- generative model
- em algorithm
- computer vision
- multi modal
- feature set