CONF Pinto_ICASSP_2009/IDIAP Volterra Series for Analyzing MLP based Phoneme Posterior Probability Estimator Pinto, Joel Praveen Sivaram, G. S. V. S. Hermansky, Hynek Magimai.-Doss, Mathew EXTERNAL https://publications.idiap.ch/attachments/papers/2009/Pinto_ICASSP_2009.pdf PUBLIC https://publications.idiap.ch/index.php/publications/showcite/Pinto_Idiap-RR-69-2008 Related documents Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2009 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. REPORT Pinto_Idiap-RR-69-2008/IDIAP Volterra Series for Analyzing MLP based Phoneme Posterior Probability Estimator Pinto, Joel Praveen Sivaram, G. S. V. S. Hermansky, Hynek Magimai.-Doss, Mathew EXTERNAL https://publications.idiap.ch/attachments/reports/2008/Pinto_Idiap-RR-69-2008.pdf PUBLIC Idiap-RR-69-2008 2008 Idiap October 2008 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.