logo Idiap Research Institute        
 [BibTeX] [Marc21]
Introducing Temporal Asymmetries in Feature Extraction for Automatic Speech Recognition
Type of publication: Idiap-RR
Citation: sgarimel:rr08-25
Number: Idiap-RR-25-2008
Year: 2008
Institution: IDIAP
Abstract: We propose a new auditory inspired feature extraction technique for automatic speech recognition (ASR). Features are extracted by filtering the temporal trajectory of spectral energies in each critical band of speech by a bank of finite impulse response (FIR) filters. Impulse responses of these filters are derived from a modified Gabor envelope in order to emulate asymmetries of the temporal receptive field (TRF) profiles observed in higher level auditory neurons. We obtain $11.4\% $ relative improvement in word error rate on OGI-Digits database and, $3.2\%$ relative improvement in phoneme error rate on TIMIT database over the MRASTA technique.
Userfields: ipdmembership={speech},
Keywords:
Projects Idiap
Authors Sivaram, G. S. V. S.
Hermansky, Hynek
Crossref by sgarimel:is:2008
Added by: [UNK]
Total mark: 0
Attachments
  • sgarimel-idiap-rr-08-25.pdf
  • sgarimel-idiap-rr-08-25.ps.gz
Notes