CONF pinto:TSD:2008/IDIAP Reverse Correlation for analyzing MLP Posterior Features in ASR Pinto, Joel Praveen Sivaram, G. S. V. S. Hermansky, Hynek EXTERNAL http://publications.idiap.ch/attachments/papers/2008/pinto-TSD-2008.pdf PUBLIC http://publications.idiap.ch/index.php/publications/showcite/pinto:rr08-13 Related documents 11th International Conference on Text, Speech, and Dialogue 2008 IDIAP-RR 08-13 In this work, we investigate the reverse correlation technique for analyzing posterior feature extraction using an multilayered perceptron trained on multi-resolution RASTA (MRASTA) features. The filter bank in MRASTA feature extraction is motivated by human auditory modeling. The MLP is trained based on an error criterion and is purely data driven. In this work, we analyze the functionality of the combined system using reverse correlation analysis. REPORT pinto:rr08-13/IDIAP Reverse Correlation for analyzing MLP Posterior Features in ASR Pinto, Joel Praveen Sivaram, G. S. V. S. Hermansky, Hynek EXTERNAL http://publications.idiap.ch/attachments/reports/2008/pinto-idiap-rr-08-13.pdf PUBLIC Idiap-RR-13-2008 2008 IDIAP Submitted for publication In this work, we investigate the reverse correlation technique for analyzing posterior feature extraction using an multilayered perceptron trained on multi-resolution RASTA (MRASTA) features. The filter bank in MRASTA feature extraction is motivated by human auditory modeling. The MLP is trained based on an error criteria and is purely data driven. In this work, we analyze the functionality of the combined system using reverse correlation analysis.