A novel speech processing algorithm based on Kepstrum analysis procedure is proposed in this paper, which provides very good speech enhancement for Dysarthric speech. Kepstrum approach has so far been used in communication applications like two microphone noise cancellation. The other applications are derivation of Kalman filter and wiener filter equations. So an attempt to use kepstrum approach to enhance the dysarthric speech is made in this paper. The algorithm is tested on various monosyllabic and bisyllabic (Consonant-Vowel pattern and Consonant-Vowel-Consonant-Vowel pattern) dysarthric speech samples of cerebral palsy patients between the age group of 40–60 years and it was found that there was considerable formant shift and modification in the energy of the output signal. Also the results obtained by kepstrum approach is compared with the results obtained by Linear Prediction Coefficients (LPC) method and it is found that kepstrum approach gives better results.