Evaluation of Noise Reduction Methods for Sentence Recognition by Sinhala Speaking Listeners

Noise reduction is a critical aspect of hearing aids that researchers trying to solve over the years. Most of the noise reduction algorithms are evaluated using English Speech Material. There are many differences between the linguistic features of English and Sinhala languages, such as different syllable structures and different vowel duration. Both wavelet transformation and adaptive filtering have been widely used for noise reduction in hearing aids. This paper compares the performance of wavelet transformation of ten wavelet families with soft and hard thresholding methods against adaptive filters with Normalized Least Mean Square (NLMS), Least Mean Square (LMS), Average Normalized Least Mean Square (ANLMS), Recursive Least Square (RLS), and Adaptive Filtering Averaging (AFA) optimization algorithms along with cepstral and energy-based voice activity detection (VAD) algorithms. The performance evaluation is done using objective metrics; Signal to Noise Ratio (SNR) and Perceptual Evaluation of Speech Quality (PESQ) and a subjective metric; Mean Opinion Score (MOS). The NOIZEUS database by the University of Texas, Dallas and a newly formed Sinhala language audio database were used for the evaluation.