logo Idiap Research Institute        
 [BibTeX] [Marc21]
Hierarchical Tandem Features for ASR in Mandarin
Type of publication: Idiap-RR
Citation: Pinto_Idiap-RR-39-2010
Number: Idiap-RR-39-2010
Year: 2010
Month: 11
Institution: Idiap
Abstract: 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.
Projects Idiap
Authors Pinto, Joel Praveen
Magimai.-Doss, Mathew
Bourlard, Hervé
Crossref by Pinto_INTERSPEECH_2011
Added by: [ADM]
Total mark: 0
  • Pinto_Idiap-RR-39-2010.pdf (MD5: 99af6a271a0aea2bf577827518fc2ac5)