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.