A.S. Cavaretta, Charles A. Micchelli, et al.
Analysis
We consider a parametric family of multivariate density functions formed by mixture models from univariate functions of the type exp(–|x|α) for modeling acoustic feature vectors used in automatic recognition of speech. The parameter α is used to measure the non-Gaussian nature of the data. Previous work has focused on estimating the mean and the variance of the data for a fixed α. Here we attempt to estimate the α from the data using a maximum likelihood criterion. Among other things, we show that there is a balance between α and the number of data pointsNthat must be satisfied for efficient estimation. Numerical experiments are performed on multidimensional vectors obtained from speech data. © 2001 American Statistical Association, Institute of Mathematical Statistics, and Interface Foundation of North America.
A.S. Cavaretta, Charles A. Micchelli, et al.
Analysis
Dahmen Wolfgang, Charles A. Micchelli
Acta Mathematicae Applicatae Sinica
Charles A. Micchelli, Allan Pinkus
Trans. Am. Math. Soc.
Martin D. Buhmann, Charles A. Micchelli
Proceedings of the London Mathematical Society