Intoxicated speech detection: A fusion framework with speaker-normalized hierarchical functionals and GMM supervectors.
Daniel BoneMing LiMatthew P. BlackShrikanth S. NarayananPublished in: Comput. Speech Lang. (2014)
Keyphrases
- speaker recognition
- fusion framework
- speaker identification
- gaussian mixture model
- voice activity detection
- speech recognition
- speaker verification
- audio visual
- noisy environments
- speech signal
- automatic speech recognition
- mel frequency cepstral coefficients
- object detection
- feature vectors
- combining multiple
- broadcast news
- mixture model
- image processing
- coarse to fine
- fusion process
- expectation maximization
- acoustic features
- speaker diarization
- similarity measure