logo Idiap Research Institute        
 [BibTeX] [Marc21]
Reverse Correlation for analyzing MLP Posterior Features in ASR
Type of publication: Conference paper
Citation: pinto:TSD:2008
Booktitle: 11th International Conference on Text, Speech, and Dialogue
Year: 2008
Note: IDIAP-RR 08-13
Crossref: pinto:rr08-13:
Abstract: 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.
Userfields: ipdmembership={speech},
Projects Idiap
Authors Pinto, Joel Praveen
Sivaram, G. S. V. S.
Hermansky, Hynek
Added by: [UNK]
Total mark: 0
  • pinto-TSD-2008.pdf
  • pinto-TSD-2008.ps.gz