Emulating temporal receptive fields of auditory mid-brain neurons for automatic speech recognition

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 wor...

Full description

Saved in:
Bibliographic Details
Published in2008 16th European Signal Processing Conference pp. 1 - 4
Main Authors Sivaram, G. S. V. S., Hermansky, Hynek
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.08.2008
Subjects
Feature extraction
Finite impulse response filters
Neurons
Speech
Time-frequency analysis
Trajectory
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:2219-5491
2219-5491