Volterra series for analyzing MLP based phoneme posterior 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.

• Type: Journal
• Year: 2009
• Where: ICASSP
• Authors: Joel Pinto, Garimella S. V. S. Sivaram, Hynek Hermansky, Mathew Magimai-Doss
• Keywords: ICASSP 2009, Order Volterra Kernels, Signal Processing, Volterra, Volterra Series