Abstract
In this paper we propose a new algorithm of phoneme based speaker-independent English command recognition and develop a speaker-independent English command recognition system. It accelerates the whole system development by using HTK (hide Markov toolkits) and Visual C++ based on the character’istics of speaker-independent speech recognition. In recognition phase we combine the confidence measures with incomplete matching, which considerably improve the quality of recognition. The recognition accuracy is increased by 4.8% over complete matching without back-end processing when the sige of vocabulary is more than 10.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Cox R V. Speech and language processing for next-millennium communications services [A]. Proc. IEEE. [C]. 2000, 88(8): 1314–1338.
Becchetti C, Ricotti L P. Speech Recognition Theory and C++ Implementation [M]. Snos Ltd, John Wiley, 1999: 28–66.
Rabiner L, Juang B-H. Fundamentals of Speech Recognition [M]. Prentice-Hall International, Inc. New Jersey, 1999.
Young S. The HTK Book [M]. Entropic Ltd, Cambridge, 1999.
Liu J, et al. The theory and application of confidence measures in speech recognition [J]. Journal of Computer Research and Development, 2000, 37(7): 882–890 (in Chinese).
Author information
Authors and Affiliations
Additional information
Project supported by National Natural Science Foundation of China (Grant No. 60072031) and The Hong Kong Polytechnic University (Grant No.-T499)
About this article
Cite this article
Ben, J., Wan, WG. & Yu, XQ. Phoneme based speaker-independent english command recognition. J. of Shanghai Univ. 7, 163–167 (2003). https://doi.org/10.1007/s11741-003-0085-9
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/s11741-003-0085-9