Volterra Series for Analyzing MLP based Phoneme Posterior Probability Estimator
We present a framework to apply Volterra series to analyze multilayered perceptrons trained to estimate the posterior probabilities of phonemes in automatic speech recognition. The identified Volterra kernels reveal the spectro-temporal patterns that are learned by the trained system for each phoneme. To demonstrate the applicability of Volterra series, we analyze a multilayered perceptron trained using Mel filter bank energy features and analyze its first order Volterra kernels.
- URL: http://publications.idiap.ch/downloads/papers/2009/Pinto_ICASSP_2009.pdf
- Related documents: http://publications.idiap.ch/index.php/publications/showcite/Pinto_Idiap-RR-69-2008
Record created on 2010-02-11, modified on 2016-08-08