REPORT Pinto_Idiap-RR-39-2010/IDIAP Hierarchical Tandem Features for ASR in Mandarin Pinto, Joel Praveen Magimai-Doss, Mathew Bourlard, Hervé EXTERNAL http://publications.idiap.ch/attachments/reports/2010/Pinto_Idiap-RR-39-2010.pdf PUBLIC Idiap-RR-39-2010 2010 Idiap November 2010 We apply multilayer perceptron (MLP) based hierarchical Tandem features to large vocabulary continuous speech recognition in Mandarin. Hierarchical Tandem features are estimated using a cascade of two MLP classifiers which are trained independently. The first classifier is trained on perceptual linear predictive coefficients with a 90 ms temporal context. The second classifier is trained using the phonetic class conditional probabilities estimated by the first MLP, but with a relatively longer temporal context of about 150 ms. Experiments on the Mandarin DARPA GALE eval06 dataset show significant reduction (about 7.6% relative) in character error rates by using hierarchical Tandem features over conventional Tandem features.