In landmark-based speech recognition system. We need to locate the landmark of speech such a consonant landmark or a vowel landmark. For using that kind of landmark as an input data to speech recognition system. This thesis focuses on finding broad manner class of Thai speech. For developing the landmark-based speech recognition system This thesis is aimed at the improvement of the acoustic parameters for the Thai automatic speech recognition system. We proposed acoustic parameters that capture the characteristics of broad manner class of Thai speech. These acoustic parameters are: 1) spectral center of gravity 2) short time zero crossing rate to 3) the energy ratio E[0-400] to E[400-6000]. The results showed 28.09%, 11.0% and 2.41% error reductions for the continuant, the syllabic and the silence features, respectively, when compared to acoustic parameters used in English. The accuracy of 80.46% was obtained from the speech segmentation task and also introduced a 23.46% error reduction when compared to the baseline HMM-MFCC based broad class segmentation. We also found similar performance for word classification in the CVC context when compared to the baseline HMM-MFCC in word recognition tasks.