Title :
Teager energy based feature parameters for speech recognition in car noise
Author :
Jabloun, Firas ; Çetin, A. Enis ; Erzin, Engin
Author_Institution :
Dept. of Electr. & Electron. Eng., Bilkent Univ., Ankara, Turkey
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 :
acoustic noise; cepstral analysis; discrete cosine transforms; feature extraction; parameter estimation; speech recognition; Teager energy operator; car engine noise; cepstral feature parameters; feature vector; inverse discrete cosine transform; log-compression; mel-scale; multirate filterbank; multirate signal processing; nonuniform subbands; robust performance; speech feature parameters; speech recognition; speech signal; Additive noise; Autocorrelation; Discrete cosine transforms; Engines; Filter bank; Noise robustness; Signal processing; Speech enhancement; Speech processing; Speech recognition;
Journal_Title :
Signal Processing Letters, IEEE
