CMAC spectral subtraction for speech enhancement

• Main Authors: Abdul Rahman, Abdul Wahab, Eng, Chong Tan, Abut, Huseyin
• Format: Conference or Workshop Item
• Language: English
• Published: 2001
• Subjects: T Technology (General)
• Online Access: http://irep.iium.edu.my/38205/1/CMAC_spectral_subtraction_for_speech_enhancement.pdf; http://irep.iium.edu.my/38205/; http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=950246&tag=1
• Institution: Universiti Islam Antarabangsa Malaysia

One of the major problems in speech signal enhancement and cancellation of additive noise is the availability of a reference signal. A comprehensive and efficient technique for speech enhancement based an extension of the spectral subtraction method is developed. In our proposed model, enhancement is achieved by using a class of associative memory based on the cerebellar model arithmetic computer (CMAC) as a robust method to estimate the reference signal. CMAC can learn very fast and it can approximate a wide variety of non-linear functions. Thus the learning algorithm of CMAC can be integrated with the spectral subtraction method to produce a system that allows the noise estimate to be learned adaptively. The effectiveness of the architecture is demonstrated on a speech corrupted with very low signal to noise ratio (from -5db to -20db) on a vehicular environment.