logo Idiap Research Institute        
 [BibTeX] [Marc21]
Posterior-based Sparse Representation for Automatic Speech Recognition
Type of publication: Conference paper
Citation: Bahaadini_INTERSPEECH_2014
Booktitle: Proceeding of Interspeech
Year: 2014
Crossref: Bahaadini_Idiap-RR-11-2014:
Abstract: Posterior features have been shown to yield very good performance in multiple contexts including speech recognition, spoken term detection, and template matching. These days, posterior features are usually estimated at the output of a neural network. More recently, sparse representation has also been shown to potentially provide additional advantages to improve discrimination and robustness. One possible instance of this, is referred to as exemplar-based sparse representation. The present work investigates how to exploit sparse modelling together with posterior space properties to further improve speech recognition features. In that context, we leverage exemplar-based sparse representation, and propose a novel approach to project phone posterior features into a new, high-dimensional, sparse feature space. In fact, exploiting the properties of posterior spaces, we generate, new, high-dimensional, linguistically inspired (sub-phone and words), posterior distributions. Validation experiments are performed on the Phonebook (isolated words) and HIWIRE (continuous speech) databases, which support the effectiveness of the proposed approach for speech recognition tasks.
Keywords: exemplar-based modeling, hidden variable, posterior feature, sparse representation, speech recognition
Projects Idiap
FP 7
PHASER 200021-153507
Authors Bahaadini, Sara
Asaei, Afsaneh
Imseng, David
Bourlard, Hervé
Added by: [UNK]
Total mark: 0
Attachments
  • Bahaadini_INTERSPEECH_2014.pdf
Notes