Teager energy based feature parameters for speech recognition in car noise
- 1 October 1999
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 6 (10) , 259-261
- https://doi.org/10.1109/97.789604
Abstract
In this letter, a new set of speech feature parameters based on multirate signal processing and the Teager energy operator is introduced. The speech signal is first divided into nonuniform subbands in mel-scale using a multirate filterbank, then the Teager energies of the subsignals are estimated. Finally, the feature vector is constructed by log-compression and inverse discrete cosine transform (DCT) computation. The new feature parameters have robust speech recognition performance in the presence of car engine noise.Keywords
This publication has 9 references indexed in Scilit:
- Subband based classification of speech under stressPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Subband analysis for robust speech recognition in the presence of car noisePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Conditions for positivity of an energy operatorIEEE Transactions on Signal Processing, 1994
- AM-FM energy detection and separation in noise using multiband energy operatorsIEEE Transactions on Signal Processing, 1993
- Energy separation in signal modulations with application to speech analysisIEEE Transactions on Signal Processing, 1993
- On amplitude and frequency demodulation using energy operatorsIEEE Transactions on Signal Processing, 1993
- A class of linear-phase regular biorthogonal waveletsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1992
- Some observations on oral air flow during phonationIEEE Transactions on Acoustics, Speech, and Signal Processing, 1980
- Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentencesIEEE Transactions on Acoustics, Speech, and Signal Processing, 1980