Canonical Correlation Analysis


We discuss algorithms for performing canonical correlation analysis. In canonical correlation analysis we try to find correlations between two data sets. The canonical correlation coefficients can be calculated directly from the two data sets or from (reduced) representations such as the covariance matrices. The algorithms for both representations are based on singular value decomposition. The methods described here have been implemented in the speech analysis program PRAAT (Boersma & Weenink, 1996), and some examples will be demonstated for formant frequency and formant level data from 50 male Dutch speakers as were reported by Pols et al. (1973).

13 Figures and Tables

Cite this paper

@inproceedings{Weenink2004CanonicalCA, title={Canonical Correlation Analysis}, author={David Weenink}, year={2004} }