LECTURE 17: SPECTRAL TRANSFORMATIONS

• Objectives:
  
  
  • Introduce perceptual linear prediction
    
    
  • Discuss speaker-dependent frequency scaling
    
    
  • Introduce vocal tract length normalization
    
    
  • Review

The original reference for perceptual linear prediction is:

H. Hermansky, "Perceptual linear predictive (PLP) analysis of speech," J. Acoust. Soc. Amer., vol. 87, no. 4, pp. 1738--1752, 1990.

Similarly, the original reference for vocal tract length normalization is reprinted here:

A. Andreou, T. Kamm, and J. Cohen, "Experiments in vocal tract normalization," Proceedings CAIP Workshop: Frontiers in Speech Recognition II, 1994.

The course textbook and resource links also contain good explanations of this material.