Study on Noise Reduction of Ventilator Noise in Recorded Speech Signals

Abstract This study aimed to reduce ventilator noise in the speech signals of patients who use a ventilator. Two applications, spectral subtraction and adaptive filtering, were examined. For the first experiment, we employed a new technique based on spectral subtraction for ventilator noise reduction and then evaluated the result using mean opinion score. The results showed that the new technique was superior to the common approach of spectral subtraction in reducing ventilator noise. For the second experiment, an adaptive filter was used in a simulated environment to reduce ventilator noise and three other signals (white noise, male speech, and female speech) from each speech signal. Adaptive filtering was able to reduce ventilator noise and, based on these results, we propose a new approach of recording speech signals in a real environment using an adaptive filter