• Proceedings of the KIEE Conference
• /
• 1999.11c
• /
• pp.727-729
• /
• 1999

We have developed a realtime phonetic typewriter implemented on IBM PC with sound card based on Windows 95. In this system, analyzing of speech signal, learning of neural network, labeling of output neurons and visualizing of recognition results are performed on realtime. The developing environment for speech processing is established by adding various functions, such as editing, saving, loading of speech data and 3-D or gray level displaying of spectrogram. Recognition experimental using Korean phone had a 71.42% for 13 basic consonant and 90.01% for 7 basic vowel accuracy.

• MALSORI
• /
• no.39
• /
• pp.43-51
• /
• 2000

The aim of this paper is to present a phonetically oriented keyboard array for the International Korean Phonetic Alphabet (IKPA). IKPA is a phonetic alphabet devised on the basis of Hangout (Korean alphabet) (Lee, 1999). Every computer has a keyboard as its input device and the English keyboard array is hewn as 'QWERTY' system, which represents the first six letters of the second line of the keyboard. This array is a traditional one devised to protect the congestion of the keys of the mechanical typewriter. To improve the anay of the keyboard, another system named 'Dvorak' has been devised. Likewise, a serious attempt has been made by the authors to work out an efficient keyboard for IKPA representing the manner of vowel and consonant classification. In the phonetic keyboard, the consonant symbols are arranged in the left hand side according to the Place and mauler of the articulation and the vowel symbols in the right hand side according to the vowel quadrilateral.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.6 no.1
• /
• pp.34-42
• /
• 2011

In an effort to the practical realization of phonetic typewriter, we concentrate on the classification of consonants in this paper. Since many of consonants do not show periodic behavior in time domain and thus the validity for Fourier analysis of them are not convincing, vector quantization (VQ) via LBG clustering is first performed to check if the feature vectors of MFCC and LPCC are ever meaningful for consonants. Experimental results of VQ showed that it's not easy to draw a clear-cut conclusion as to the validity of Fourier analysis for consonants. For classification purpose, two kinds of neural networks are employed in our study: self organizing map (SOM) and learning vector quantization (LVQ). Results from SOM revealed that some pairs of phonemes are not resolved. Though LVQ is free from this difficulty inherently, the classification accuracy was found to be low. This suggests that, as long as consonant classification by LVQ is concerned, other types of feature vectors than MFCC should be deployed in parallel. However, the combination of MFCC/LVQ was not found to be inferior to the classification of phonemes by language-moded based approach. In all of our work, LPCC worked worse than MFCC.