Feature Extraction Using Power-Law Adjusted Linear Prediction With Application to Speaker Recognition Under Severe Vocal Effort Mismatch.
Rahim SaeidiPaavo AlkuTom BäckströmPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2016)
Keyphrases
- speaker recognition
- speech signal
- power law
- linear prediction
- feature extraction
- speaker identification
- image coding
- speech recognition
- spectral analysis
- image processing
- non stationary
- feature space
- self organizing maps
- computer vision
- autoregressive
- frequency domain
- principal component analysis
- speaker verification