An Improved Distinguishing Different Vowel Sounds of Language Approach

Vowel is a speech sound created by the relatively free passage of breath through the larynx and oral cavity. The importance of vowels in distinguishing one word from another varies from language to language. It is very important to recognize different vowel classes. The least squares support vector machine (LSSVM) is adopted to recognize different vowels. The purpose of using recognition model is minimizing the expectation risks. Structural risk minimization provides a minimum of risk, which is different from the experience risk minimization. This is a more reasonable machine study design principles. When the LSSVM is used in vowel classifying, the Fibonacci symmetry searching algorithm is simplified and improved. The simulation results show the validity of the model.