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 word error rate on OGI-Digits database. Experiments on TIMIT database confirm that proposed modifications are indeed useful.
- 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 2016-08-08