logo Idiap Research Institute        
 [BibTeX] [Marc21]
MLP Based Hierarchical System for Task Adaptation in ASR
Type of publication: Conference paper
Citation: Pinto_ASRU_2009
Booktitle: Proceedings of the IEEE workshop on Automatic Speech Recognition and Understanding
Year: 2009
Month: 12
Location: Merano, Italy
Abstract: We investigate a multilayer perceptron (MLP) based hierarchical approach for task adaptation in automatic speech recognition. The system consists of two MLP classifiers in tandem. A well-trained MLP available off-the-shelf is used at the first stage of the hierarchy. A second MLP is trained on the posterior features estimated by the first, but with a long temporal context of around 130 ms. By using an MLP trained on 250 hours of conversational telephone speech, the hierarchical adaptation approach yields a word error rate of 1.8% on the 600-word Phonebook isolated word recognition task. This compares favorably to the error rate of 4% obtained by the conventional single MLP based system trained with the same amount of Phonebook data that is used for adaptation. The proposed adaptation scheme also benefits from the ability of the second MLP to model the temporal information in the posterior features.
Projects Idiap
Authors Pinto, Joel Praveen
Magimai.-Doss, Mathew
Bourlard, Hervé
Added by: [UNK]
Total mark: 0
  • Pinto_ASRU_2009.pdf