A Recognition Judgment Method of Isolated-Word Speech-Recognition

Abstract:

Isolated-word speech-recognition system adopted the shortest distance of Dynamic Time Warping (DTW) to make recognition judgment, which has the disadvantage of high False Accept Rate (FAR), poor anti-noise and robustness. This paper proposes a new method based on DTW distance Threshold Estimation for recognition judgment. This method processes the maximum distance between template speech and training input speech multiplying adjusting coefficient, then plus noise DTW distance, which regard the final result as distance Threshold Estimation. At the time of doing speech recognition, if the distance between testing speech and template speech exceeds the Threshold Estimation, then the system will not recognize this speech. The experiment shows that this method can greatly improve the anti-noise and robustness performance of the Isolated-word speech-recognition system and solve the problem of high FAR.

• Periodical: Applied Mechanics and Materials (Volumes 543-547)
• Pages: 2337-2340
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.543-547.2337
• Online since: March 2014
• Authors: Yi Zhang*, Xiao Song Li, Yang Song
• Keywords: DTW, Isolated-Word Speech-Recognition, Matching Distance Threshold, Recognition Judgment

References

[1] Zhiqiang Wang, The research of key issues for isolated-word speech-recognition system, Beijing University of Posts and Telecommunications, MA, (2006).

[2] Xiaodong Shi, The design of isolated-word speech-recognition system, Zhejiang University , MA, (2006).

[3] Yunhong Li, Ziling Li, The improved DTW voice recognition algorithm (Published Journal style), Information Technology Applications in Industry, pp.2328-2331, (2013).

[4] Shichun Zhou, The research of algorithm for auditory characteristics and noise estimation in speech enhancement, East China University of Science and Technology, MA, (2013).

[5] Junqin Wu , Junjun Yu, An improved arithmetic of MFCC in speech recognition system(Published Proceedings style), IEEE , International Conference on Electronics, Communications and Control 2011, pp.719-722.

DOI: 10.1109/icecc.2011.6066676

[6] I. Cohen, Noise spectrum estimation in adverse environments: improved minima controlled recursive averaging (Published Journal style), IEEE Transactions on Speech and Audio Processing, vol. 11, no. 5, pp.466-475, (2003).

DOI: 10.1109/tsa.2003.811544

[7] Xueji Jin, The research and implementation of algorithm for speech enhancement, Zhejiang University , MA, (2005).

[8] T. Painter, A. Spanias, Perceptual coding of digital audio (Published Journal style), Proceedings of the IEEE, vol. 88, no. 4, pp.451-503, (2000).

DOI: 10.1109/5.842996