Evaluation of Noise Reduction Methods for Sentence Recognition by Sinhala Speaking Listeners (ICIIS 2023)
Malitha Gunawardhana, Chathuki Navanjana, Dinithi Fernando, Nipuna Upeksha, Anjula De Silva
Abstract: Noise reduction is a crucial aspect of hearing aids, which researchers have been striving to address over the years. However, most existing noise reduction algorithms have primarily been evaluated using English. Considering the linguistic differences between English and Sinhala languages, including variation in syllable structures and vowel duration, it is very important to assess the performance of noise reduction tailored to Sinhala language. This paper presents a comprehensive analysis between wavelet transformation and adaptive filters for noise reduction in Sinhala languages. We investigate the performance of ten wavelet families with soft and hard thresholding methods against adaptive filters with Normalized Least Mean Square, Least Mean Square Average Normalized Least Mean Square, Recursive Least Square, and Adaptive Filtering Averaging optimization algorithms along with cepstral and energy-based voice activity detection algorithms. The performance evaluation is done using objective metrics; Signal to Noise Ratio and Perceptual Evaluation of Speech Quality and a subjective metric; Mean Opinion Score. A newly recorded Sinhala language audio dataset and the NOIZEUS database by the University of Texas, Dallas were used for the evaluation.
- You can download the NOIZEUS dataset from this link. Sinhala database is included in the repo.
- To evaluate the performance, go to each folder and run the 'main.m' file
In case of any query, create a issue