Role of noise elimination algorithms in speech processing applications: A comprehensive research and some experimental results

Abstract

The performance of speech-based systems is severely degraded due to the presence of background noise in real-world environments. Effective noise elimination algorithms are essential for enhancing speech quality and improving the performance of speech processing applications, such as voice activity detection (VAD) and speech encoding. Various speech enhancement techniques have been proposed to tackle this, and in this context, choosing an appropriate enhancement technique for improving speech quality and intelligibility is an important consideration. This paper presents a concise experimental review of different noise elimination techniques using objective and subjective metrics. The experiments are conducted on the noisy speech corpus (NOIZEUS) across different noise types and signal-to-noise ratio (SNR) levels. Comparative results indicate that the soft mask estimator with a priori SNR uncertainty (SMPR) is considerably more useful in enhancing speech quality. Furthermore, we analyze the SMPR performance in enhancing speech quality under various noise conditions, specifically focusing on their impact on speech encoding and VAD applications. Our results reveal that integrating the SMPR enhancement module into linear predictive coding (LPC)-based speech encoding system significantly improves speech quality. Additionally, the application of SMPR in VAD systems demonstrates notable improvements, enhancing the accuracy of speech detection.