An Overview on Voice and Speech Recognition Motion Techniques

Evaluation of an Algorithm for Voice and Speech Recognition

Abstract

From the outcomes obtained its proficiency is satisfying it was concluded that the algorithm actualized in Lab View is working effectively. Be that as it may, since the algorithm does not extract the vowels from the speech, the value obtained for Formant 1 weren't totally right as they were obtained by processing all the samples of the speech. It was also seen from trials that by increasing the unvoiced part in the speech, similar to the sound of ‗s', the value of pitch increases consequently hampering the sex detection in case of Male samples. Likewise by increasing the voiced, similar to the sound of ‗a', decreases the value of pitch yet the framework takes care of such plunge in value and results were not affected by the same. Also, extraordinary speech by the same speaker talked in the near to identical conditions generated the same pitch value establishing that the framework can be used for identification of speaker after further work.