Modified Cerebellar Model Articulation Controller (MCMAC) as an amplitude spectral estimator for speech enhancement

• Main Authors: Abdul Rahman, Abdul Wahab, Tan, Eng Chong, Abut, Huseyin
• Format: Book Chapter
• Language: English
• Published: Springer US 2005
• Subjects: T Technology (General)
• Online Access: http://irep.iium.edu.my/38189/1/Modified_Cerebellar_Model_Articulation_Controller_%28MCMAC%29_as_an_Amplitude_Spectral_Estimator_for_Speech_Enhancement.pdf; http://irep.iium.edu.my/38189/; http://link.springer.com/chapter/10.1007%2F0-387-22979-5_8
• Institution: Universiti Islam Antarabangsa Malaysia

In this chapter, we present a modified cerebellar model articulation controller (MCMAC) to be used together with the amplitude spectral estimator (ASE) for enhancing noisy speech. The MCMAC training overcomes the limitations of the CMAC technique we have employed noise/echo cancellation in a vehicular environment. While the CMAC in the training mode has trained only the trajectory it has visited by controlling the reference input, the modified MCMAC-ASE system architecture proposed in this work includes multiple MCMAC memory trainable for different noise sources.