Phase Autocorrelation Bark Wavelet Transform (PACWT) Features for Robust Speech Recognition

Abstract

In this paper, a new feature-extraction method is proposed to achieve robustness of speech recognition systems. This method combines the benefits of phase autocorrelation (PAC) with bark wavelet transform. PAC uses the angle to measure correlation instead of the traditional autocorrelation measure, whereas the bark wavelet transform is a special type of wavelet transform that is particularly designed for speech signals. The extracted features from this combined method are called phase autocorrelation bark wavelet transform (PACWT) features. The speech recognition performance of the PACWT features is evaluated and compared to the conventional feature extraction method mel frequency cepstrum coefficients (MFCC) using TI-Digits database under different types of noise and noise levels. This database has been divided into male and female data. The result shows that the word recognition rate using the PACWT features for noisy male data (white noise at 0 dB SNR) is 60%, whereas it is 41.35% for the MFCC features under identical conditions.

Bulletin of the Polish Academy of Sciences: Technical Sciences

“…Wavelets have been used in many domains such as statistics [8][9][10], time series analysis [11][12][13], biological data analysis [14,15], signal processing [16][17][18], image processing [19][20][21][22][23], speech recognition [24] and databases [25]. Recently, a new orientation that adopts the wavelets in the field of data mining [26,27] has emerged.…”

Archives of Acoustics

“…In (Wang et al, 2007), DWT-based approaches were developed for SQ evaluation (SQE) of non-stationary vehicle noises. As an extension to the DWT, wavelet packet transform (WPT) provides a specific filter bank with identical features to the center frequencies and critical bandwidths (Majeed et al, 2015;Parfieniuk et al, 2006).…”