![Comparison of spectral subtraction noise reduction algorithms](/rails/active_storage/representations/proxy/eyJfcmFpbHMiOnsibWVzc2FnZSI6IkJBaHBBaUFQIiwiZXhwIjpudWxsLCJwdXIiOiJibG9iX2lkIn19--14ba87f46bb0b12a374eebbc2f0efbcc90ef7a81/eyJfcmFpbHMiOnsibWVzc2FnZSI6IkJBaDdCem9MWm05eWJXRjBTU0lJYW5CbkJqb0dSVlE2QzNKbGMybDZaVWtpRFRZd01IZzJNREErQmpzR1ZBPT0iLCJleHAiOm51bGwsInB1ciI6InZhcmlhdGlvbiJ9fQ==--a3b53ba1a0f83efef18f6e75a8d4ce784384bee2/Homepage%20and%20feature%20image.jpg)
Here, the authors investigated methods to reduce noise in audio composed of real-word sounds. They specifically used two spectral subtraction noise reduction algorithms: stationary and non-stationary finding notable differences in noise improvements depending on the noise sources.
Read More...