๐”– Bobbio Scriptorium
โœฆ   LIBER   โœฆ

Continuous HMM applied to quantization of on-line Korean character spaces

โœ Scribed by K.C Jung; S.M Yoon; H.J Kim


Book ID
104305006
Publisher
Elsevier Science
Year
2000
Tongue
English
Weight
179 KB
Volume
21
Category
Article
ISSN
0167-8655

No coin nor oath required. For personal study only.

โœฆ Synopsis


This paper demonstrates the eectiveness of a continuous HMM (CHMM) for quantizing on-line Korean character spaces. Vector quantization (VQ) error is a major factor that aects the performance of pattern recognition. Accordingly, a CHMM is used to classify on-line Korean character space into clusters where each cluster is represented by a CHMM state Gaussian function. The experimental results show that the proposed CHMM vector quantization decreases the quantization distortion in the VQ stage compared to other methods and thereby improves the performance of a discrete HMM-based recognition system.


๐Ÿ“œ SIMILAR VOLUMES


Nonlinear regression by visualization of
โœ Mark Van Den Brink; Wilfred Smulders; Alex M. Van Herk; Anton L. German ๐Ÿ“‚ Article ๐Ÿ“… 1999 ๐Ÿ› John Wiley and Sons ๐ŸŒ English โš– 225 KB ๐Ÿ‘ 2 views

The copolymerization of โฃ-methylene-โฅ-butyrolactone and methyl methacrylate in DMSO was studied by on-line Raman spectroscopy. Reactivity ratios for this system were estimated from the in situ conversion measurements. The estimates are in good agreement with estimates obtained from low-conversion ex