Robust feature extraction from spectrum estimated using bispectrum for Isolated Word Recognition

Abstract

Extraction of robust features from noisy speech signals is one of the challenging problems in Automatic Speech Recognition (ASR). For Gaussian process, its bispectrum and all higher order spectra are identically zero, which means that bispectrum removes the additive white Gaussian noise while preserving the magnitude and phase information of original signal. Using this bispectrum property, spectrum of original signal can be recovered from its noisy version. Robust Mel Frequency Cepstral Coefficients (MFCC) are extracted from the estimated spectral magnitude (denoted as Bispectral-MFCC (BMFCC)). The effectiveness of BMFCC has been tested on TI-46 isolated word database in noisy (additive white Gaussian) environment. The experimental results show the superiority of the proposed technique over conventional methods for Isolated Word Recognition (IWR).