Study on Optimization of Pathological Voice Features
Xiaojun Zhang, Yating Shao, Baoyin Sun, Zhi Tao · 2015
This paper proposes a method to optimize Pathological Voice Features based on classification and experimental design.Firstly, all voice parameters of features are classified, then pick the right amount of each class of representative and typical parameters based on the principle of mathematical statistics.Finally, recognition experiments are performed with this combination.C4.5 decision tree algorithm is used to recognize vocal cord or non-vocal cord damage voice, results show that recognition rate of optimized features is 5% higher than non-optimized, which is up to 89%.