A Noise-Robust Continuous Speech Recognition System Using Block-Based Dynamic Range Adjustment

Abstract

SUMMARYA new approach to speech feature estimation under noise circumstances is proposed in this paper. It is used in noise-robust continuous speech recognition (CSR). As the noise robust techniques in isolated word speech recognition, the running spectrum analysis (RSA), the running spectrum filtering (RSF) and the dynamic range adjustment (DRA) methods have been developed. Among them, only RSA has been applied to a CSR system. This paper proposes an extended DRA for a noise-robust CSR system. In the stage of speech recognition, a continuous speech waveform is automatically assigned to a block defined by a short time length. The extended DRA is applied to these estimated blocks. The average recognition rate of the proposed method has been improved under several different noise conditions. As a result, the recognition rates are improved up to 15% in various noises with 10 dB SNR.

Enhanced Running Spectrum Analysis for Robust Speech Recognition Under Adverse Conditions: A Case Study on Japanese Speech

“…Although running spectrum analysis (RSA) is a well known method focusing on modulation spectrum, it has mostly been applied for automatic continuous speech recognition [19]. Furthermore, in speech, its application has been mainly focused on the frequency components in the range of 2-8 Hz because this range contains the dominant elements of the amplitude envelope of speech [20][21]. The modulation frequency band at higher than 8 Hz can be regarded as miscellaneous noise or unnecessary speech components related to the speakers characteristics, such as tone and pronunciation, among other factors [22].…”