Punjabi language is popular Indo-Aryan language. Its phoneme sounds are tonal in nature which dissent in almost all-Indian side of Punjab. This books focus on analysis of some pf the dominant feature extraction techniques used in Automatic Speech Recognition and analytically analyse which feature extraction techniques is best suitable for extracting features of the tone present in the Punjabi speech. Three feature extractions techniques are compared: ¿power normalized cepstral coefficients (PNCC)¿, ¿Mel frequency cepstral coefficients (MFCC)¿ and ¿Perceptual Linear Prediction (PLP)¿ following a statistical comparison based on the accuracy and correctness of results attained. To attain a higher rate of accuracy level 34 phones for Punjabi language are used to break each word into small sound frames. environments using evident number of speakers giving overall system results with MFCC as finest of all three in noise-free environment and PLP to be efficient feature extraction technique in noisy environment for Punjabi speech corpus.