Experimental Speech Recognition From Pathological Voices

Speech recognition has been the subject of quite a few research subjects as it is the adequate means for dynamic, efficient and interaction Human communication simultaneously using the two phenomena of phonation and hearing between speakers, the applications of its searches are enormous for example one can quote: the dictation, the speech synthesis within the Windows software, the speech recognition of the Google search engine at the Smartphone level …… ..etc. all its applications depend on the conditions of use in which they are implemented, to be done and to overcome the puzzles of imperfection it is necessary to be sure to properly characterize the speech signal by extracting the most relevant characters such as: the fundamental frequency (pitch in English), timbre, tonality, to extract them many techniques are possible, the most used of which are acoustic such as: MFCC, PLP, LPC, RASTA and other in the form of combination (hybridization) namely: PLP RASTA, MFCC PLP etc. They are used in data transmission, speaker recognition and even in speech synthesis.