BROWSE
Detail
Conference Paper
An Approach on a Combination of Higher-order Statistics and Higher-order Differential Energy Operator for Detecting Pathological Voice with Machine Learning
Cited 10 time in 
Download 6 time
Share 
Download 6 time
Share
- Authors
- Jihye Moon, Sanghun Kim
- Issue Date
- 2018-10
- Citation
- International Conference on Information and Communication Technology Convergence (ICTC) 2018, pp.46-51
- Language
- English
- Type
- Conference Paper
- Project Code
- 18ZS1100, Core Technology Research for Self-Improving Artificial Intelligence System, Lee Yunkeun
- Abstract
- Voice signal is an indicator finding a progression of diseases such as nerve disorder and muscle dysfunction. To improve the performance of medical diagnosis system using the voice signal, this paper suggests a new feature extraction method which combines higher-order statistics (HOS) and higher-order differential energy operator (DEO). For the experiment, Saarbruecken Voice Database (SVD) was used, and 687 healthy voice samples and 263 pathological voice samples which consist of Cysts, Paralysis, and Polyp were selected. In addition, the OpenSmile script which provides 6,373 features was used for comparison with our new features. To decide the most effective features, Gradient Boosting was conducted as a feature selector. Finally, 20 features including 15 combinations of HOS and DEO were chosen, and deep neural network(DNN) was trained using the new features. The best accuracy of 87.4% was obtained, which exceeds the best accuracy of 84.5% with the existing features. The finding suggests a possibility that the pathological voice can be efficiently detected with only statistical information without heavy computations such as convolutional neural networks. Due to the simple structure, we expect this approach will be easily applied to a variety of mobile systems.
- KSP Keywords
- Convolution neural network(CNN), Deep neural network(DNN), Diagnosis system, Energy operator, Medical diagnosis, Mobile system, Pathological voice, Statistical information, Voice signal, feature extraction method, gradient boosting