We present a framework to utilize general exponential families for acoustic modeling. Maximum Likelihood (ML) parameter estimation is carried out using sampling based estimates of the partition function and expected feature vector. Markov Chain Monte Carlo procedures are used to draw samples from general exponential densities. We apply our ML estimation framework to two new exponential families to demonstrate the modeling flexibility afforded by this framework.
Cite as: Goel, V., Olsen, P.A. (2009) Acoustic modeling using exponential families. Proc. Interspeech 2009, 1423-1426, doi: 10.21437/Interspeech.2009-437
@inproceedings{goel09_interspeech,
author={Vaibhava Goel and Peder A. Olsen},
title={{Acoustic modeling using exponential families}},
year=2009,
booktitle={Proc. Interspeech 2009},
pages={1423--1426},
doi={10.21437/Interspeech.2009-437}
}