Research on Speech Recognition Robot Based on Embedded System and DSP

Abstract:

This paper has a discussion and research on the design and realization of the speech recognition robot based on embedded system and DSP. The solution of embedded system and DSP has made the performance, cost, reconfigurable ability and extensible ability of the system to a high level. And the system has adapted the modified MFCC method to extract the feature of the speech and used the HMM model based on K segmented equalizing value to do the speech study and recognition. It has improved the transplanting and real-time ability of the arithmetic.

• Periodical: Applied Mechanics and Materials (Volumes 701-702)
• Pages: 341-347
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.701-702.341
• Online since: December 2014
• Authors: Xuan Gong*
• Keywords: DSP, Embedded, HMM, MFCC, Robot, Speech Recognition

References

[1] LvChengguo, Zhao Bing: Speech Recognition Technology with Low SNR [C] Annual Meeting Proceedings of Academic Exchange of Heilongjiang Computer Society in 2007, 2007: 243-245.

[2] Wang Sheguo, Zhao Jianguang: Research on Embedded Speech Recognition System based on ARM [J]. Micro Computer Information, 2007, 2-2: 148-150.

[3] LuoJunguang, Yang Rongjiang: Research on Speaker-independent Speech Recognition System based on DSP [J] Micro Computer Information, 2007. 4-2: 195-196.

[4] Li Jin, He Peiyu: An improved HMM Speaker-independent Speech Recognition Algorithm based on wavelet denoising [J]. Sichuan University (Natural Science), 2007. 2: 69-72.

[5] Zhang Yuehui: Studies on Speech Recognition [D], Master's degree thesis in Nanjing University, 2006. 5.

[6] Guo Jun: Research on Speaker Adaptation in Speech Recognition [D], Doctoral Dissertations from Beijing University of Posts and Telecommunications, 2007. 5.