Browsing by Author "Wang, Shih-Chieh"

Now showing 1 - 2 of 2

Irregular puncturing for convolutional codes and the application to unequal error protection
(2006)
Wang, Chung-Hsuan
;
Wang, Shih-Chieh
;
Chang, Yun-Liang
;
電信工程研究所
;
Institute of Communications Engineering
In this paper, convolutional codes are studied for puncturing with irregular puncturing periods. Irregular puncturing can generate punctured codes with more available rates and better bit-error-rate performance compared with the conventional scheme with a single puncturing period. For the application to unequal error protection, a new multiplexing scheme is also proposed for rate-compatible punctured convolutional (RCPC) codes which can guarantee smooth transition between rates without extra overheads. Finally, families of good RCPC codes with irregular puncturing tables are given by a computer search.
Speech signal-based emotion recognition and its application to entertainment robots
(2014)
Song, Kai-Tai
;
Han, Meng-Ju
;
Wang, Shih-Chieh
;
電機資訊學士班
;
Undergraduate Honors Program of Electrical Engineering and Computer Science
By recognizing sensory information, through touch, vision, or voice sensory modalities, a robot can interact with people in a more intelligent manner. In human-robot interaction (HRI), emotion recognition has been a popular research topic in recent years. This paper proposes a method for emotion recognition, using a speech signal to recognize several basic human emotional states, for application in an entertainment robot. The proposed method uses voice signal processing and classification. Firstly, end-point detection and frame setting are accomplished in the pre-processing stage. Then, the statistical features of the energy contour are computed. Fisher's linear discriminant analysis (FLDA) is used to enhance the recognition rate. In the final stage, a support vector machine (SVM) is used to complete the emotional state classification. In order to determine the effectiveness of emotional HRI, an embedded system was constructed and integrated with a self-built entertainment robot. The experimental results for the entertainment robot show that the robot interacts with a person in a responsive manner. The average recognition rate for five emotional states is 73.8% using the database constructed in the authors' lab.