A comparison of composite features under degraded speech in speaker recognition.
John P. OpenshawZ. P. SunJohn S. MasonPublished in: ICASSP (2) (1993)
Keyphrases
- speaker recognition
- mel frequency cepstral coefficients
- vector quantization
- gaussian mixture model
- speaker verification
- speaker identification
- feature vectors
- probabilistic neural network
- speech signal
- speech recognition
- feature extraction
- extracting features
- spectral features
- broadcast news
- feature set
- audio visual
- multi modal
- low level