Auditory processing of speech signals for robust speech recognition in real-world noisy environments

Abstract

This paper presents a new approach to an auditory model for robust speech recognition in noisy environments. The proposed model consists of cochlear bandpass filters and nonlinear operations in which frequency information of the signal is obtained by zero-crossing intervals. Intensity information is also incorporated by a peak detector and a compressive nonlinearity. The robustness of the zero-crossings in spectral estimation is verified by analyzing the variance of the level-crossing intervals as a function of the crossing level values. Compared with other auditory models, the proposed auditory model is computationally efficient, free from many unknown parameters, and able to serve as a robust front-end for speech recognition in noisy environments. Experimental results of speech recognition demonstrate the robustness of the proposed method in various types of noisy environments.

The Research of Noise-Robust Speech Recognition Based on Frequency Warping Wavelet

“…ZCPA feature extraction scheme Fig. 2 shows the feature extraction block scheme of ZCPA (Doh-suk et al, 1999). This system consists of a bank of band-pass filters, zero-crossing detector, peak detector, nonlinear compression and frequency receiver.…”

“…Frequencies are distributed according to logarithm relationship along the basilar membrane over 800Hz. The frequency-position relationship can be expressed as Equation (1) (Doh-suk et al, 1999):…”

“…The centre frequency of every filter can be obtained from the Equation (1). And bandwidths are set to be proportional to the equivalent rectangular bandwidth (ERB) (Oded, 1992;Doh-suk et al, 1999). ERB = 6.23F 2 + 93.39F + 28.52…”

“…Bark wavelet is a warping wavelet that divides frequency band according to critical band (Qiang et al, 2000). At the same time, MFCC (Mel Frequency Cepstrum Coefficients) (Lawrence, 1999) and ZCPA (Zero-Crossing with Peak Amplitude) (Doh-suk et al, 1999) features themselves have noise-robust performance. HMM is classical recognition network, and wavelet neural network is also popular recognition network (Tianbing et al, 2001).…”

Pitch-Synchronous ZCPA (PS-ZCPA)-Based Feature Extraction with Auditory Masking

“…

A pitch-synchronous (PS) auditory feature extraction method based on ZCPA (Zero-Crossings PeakAmplitudes) was proposed in [1] and showed more robust over the conventional ZCPA [2]. In this paper, we examine the effect of auditory masking, both simultaneous and temporal, into the proposed PS-ZCPA method.

…”