Emulating Temporal Receptive Fields of Auditory Mid-Brain Neurons for Automatic Speech Recognition

• Presented at: Proc. 16th European Signal Processing Conference (EUSIPCO)
• Publication date: 2008

This paper proposes modifications to the Multi-resolution RASTA (MRASTA) feature extraction technique for the automatic speech recognition (ASR). By emulating asymmetries of the temporal receptive field (TRF) profiles of auditory mid-brain neurons, we obtain more than $13% $ relative improvement in word error rate on OGI-Digits database. Experiments on TIMIT database confirm that proposed modifications are indeed useful.

Note:

IDIAP-RR 08-24

Reference

• LIDIAP-CONF-2008-058
• URL: http://publications.idiap.ch/downloads/papers/2008/sgarimel-eusipco-2008.pdf
• Related documents: http://publications.idiap.ch/index.php/publications/showcite/sgarimel:rr08-24

Record created on 2010-02-11, modified on 2017-05-10