Adaptive Korean Continuous Speech Recognizer to Speech Rate


The Transactions of the Korea Information Processing Society (1994 ~ 2000), Vol. 4, No. 6, pp. 1531-1540, Jun. 1997
10.3745/KIPSTE.1997.4.6.1531,   PDF Download:

Abstract

In this paper, we presents automatic Korean continuous speech recognizer which is improved by the speech rate estimation and the compensation methods. Automatic continuous speech recognition is significantly more difficult than isolated word recognition because of coarticulatory effects and variations in speech rate. In order to recognize continuous speech, modeling methods of coarticulatory effects and variations in speech rate are needed.In this paper, the speech rate is measured by change of format, and the compensation is peformed by extracting relatively many feature vectors in fast speech. Coarticulatory effects are modeled by defining 514 Korean diphone set, and ETRI''s 445 word DB is used for training speech material. With combining above methods, we implement automatic Korean continuous speech recognizer, which shows improved recognition rate, based on DHMM(Discrete Hidden Markov Model).


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
K. J. Beom, P. C. Kyu, L. J. Hyun, "Adaptive Korean Continuous Speech Recognizer to Speech Rate," The Transactions of the Korea Information Processing Society (1994 ~ 2000), vol. 4, no. 6, pp. 1531-1540, 1997. DOI: 10.3745/KIPSTE.1997.4.6.1531.

[ACM Style]
Kim Jae Beom, Park Chan Kyu, and Lee Jung Hyun. 1997. Adaptive Korean Continuous Speech Recognizer to Speech Rate. The Transactions of the Korea Information Processing Society (1994 ~ 2000), 4, 6, (1997), 1531-1540. DOI: 10.3745/KIPSTE.1997.4.6.1531.