Browse > Article

A Study on the Phonemic Analysis for Korean Speech Segmentation  

Lee, Sou-Kil (Dept. of Computer Engineering, PaiChai University)
Song, Jeong-Young (Dept. of Computer Engineering, PaiChai University)
Abstract
It is generally known that accurate segmentation is very necessary for both an individual word and continuous utterances in speech recognition. It is also commonly known that techniques are now being developed to classify the voiced and the unvoiced, also classifying the plosives and the fricatives. The method for accurate recognition of the phonemes isn't yet scientifically established. Therefore, in this study we analyze the Korean language, using the classification of 'Hunminjeongeum' and contemporary phonetics, with the frequency band, Mel band and Mel Cepstrum, we extract notable features of the phonemes from Korean speech and segment speech by the unit of the phonemes to normalize them. Finally, through the analysis and verification, we intend to set up Phonemic Segmentation System that will make us able to adapt it to both an individual word and continuous utterances.
Keywords
Speech recognition; Phonemic segmentation; Phonemic analysis; Hunminjeongeum;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Juchae Bae, 'Synopsis of Hangul phonology,' Shingu CulturePublishers, 1997
2 Younghuan O, 'Management of volce data,' Heungryung SciencePublishers, 1998
3 Sou-Kil Lee, Jeong-voung Song, 'A Stuay on the Pnonemic Analysis for Korean Speech,' Proceeding of the Electronics, Information andSystems Conference Electronics, Information and Systems Society, I.E.E. of Japan, 2003
4 Peter B. Denes, Elliot N Pinson, 'The Speech Chain,' HanshinCulture Books, 1999
5 Lawrence Rabiner 'Fundamentals of SPeech Recoqnition.' PrenticeHall, 1993
6 Byunggon Yang, 'Theory & Practicals of Voice Analysis Using Praat.' Mansu Publishers, 2003
7 Changyun Yu, 'Notes on Hunminjungeum,' Hyoungsul Publishers,1998
8 John Clark, Collin Yallop, 'Phonetics & phonology' Hanshin CultureBooks, 1998
9 Jinsoo Han, 'Management of Voice Signal,' Osung Media, 2000