%Aigaion2 BibTeX export from Idiap Publications
%Thursday 04 December 2025 10:45:37 PM

@INPROCEEDINGS{Pinto_ICASSP_2009,
                      author = {Pinto, Joel Praveen and Sivaram, G. S. V. S. and Hermansky, Hynek and Magimai-Doss, Mathew},
                    projects = {Idiap, SNSF-KEYSPOT, SNSF-MULTI, IM2},
                       title = {Volterra Series for Analyzing MLP based Phoneme Posterior Probability Estimator},
                   booktitle = {Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
                        year = {2009},
                    crossref = {Pinto_Idiap-RR-69-2008},
                    abstract = {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.},
                         pdf = {https://publications.idiap.ch/attachments/papers/2009/Pinto_ICASSP_2009.pdf}
}



crossreferenced publications: 
@TECHREPORT{Pinto_Idiap-RR-69-2008,
                      author = {Pinto, Joel Praveen and Sivaram, G. S. V. S. and Hermansky, Hynek and Magimai-Doss, Mathew},
                    projects = {SNSF-KEYSPOT, IM2, SNSF-MULTI},
                       month = {10},
                       title = {Volterra Series for Analyzing MLP based Phoneme Posterior Probability Estimator},
                        type = {Idiap-RR},
                      number = {Idiap-RR-69-2008},
                        year = {2008},
                 institution = {Idiap},
                    abstract = {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.},
                         pdf = {https://publications.idiap.ch/attachments/reports/2008/Pinto_Idiap-RR-69-2008.pdf}
}