Emulating Temporal Receptive Fields of Higher Level Auditory Neurons for ASR

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 higher level auditory neurons, we obtain more than 11.4% relative improvement in word error rate on OGI-Digits database. Experiments on TIMIT database confirm that proposed modifications are indeed useful.


Published in:
Text, Speech And Dialogue, Proceedings, 5246, 509-516
Presented at:
11th International Conference on Text, Speech and Dialogue, Brno, CZECH REPUBLIC, Sep 08-12, 2008
Year:
2008
Publisher:
Springer-Verlag New York, Ms Ingrid Cunningham, 175 Fifth Ave, New York, Ny 10010 Usa
Keywords:
Laboratories:




 Record created 2010-11-30, last modified 2018-03-17


Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)