Language Model based on VCCV and Test of Smoothing Techniques for Sentence Speech Recognition


The KIPS Transactions:PartB , Vol. 11, No. 2, pp. 241-246, Apr. 2004
10.3745/KIPSTB.2004.11.2.241,   PDF Download:

Abstract

In this paper, we propose VCCV units as a processing unit of language model and compare them with clauses and morphemes of existing processing units. Clauses and morphemes have many vocabulary and high perplexity. But VCCV units have low perplexity because of the small lexicon and the limited vocabulary. The construction of language models needs an issue of the smoothing. The smoothing technique used to better estimate probabilities when there is an insufficient data to estimate probabilities accurately. This paper made a language model of morphemes, clauses and VCCV units and calculated their perplexity. The perplexity of VCCV units is lower than morphemes and clauses units. We constructed the N-grams of VCCV units with low perplexity and tested the language model using Katz, absolute, modified Kneser-Ney smoothing and so on. In the experiment results, the modified Kneser-Ney smoothing is tested proper smoothing technique for VCCV units.,


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]
P. S. Hui, N. Y. Wan, H. G. Seog, "Language Model based on VCCV and Test of Smoothing Techniques for Sentence Speech Recognition," The KIPS Transactions:PartB , vol. 11, no. 2, pp. 241-246, 2004. DOI: 10.3745/KIPSTB.2004.11.2.241.

[ACM Style]
Park Seon Hui, No Yong Wan, and Hong Gwang Seog. 2004. Language Model based on VCCV and Test of Smoothing Techniques for Sentence Speech Recognition. The KIPS Transactions:PartB , 11, 2, (2004), 241-246. DOI: 10.3745/KIPSTB.2004.11.2.241.