Browse > Article

Performance Evaluation of Speech Recognition Using the Reconstructed Feature Parameter with Voiced-Unvoiced Measure  

이광석 (진주산업대학교 전자공학부)
한학용 (동아대학교 전기ㆍ전자ㆍ컴퓨터공학부)
고시영 (경일대학교 전자정보공학부)
허강인 (동아대학교 전기ㆍ전자ㆍ컴퓨터공학부)
Publication Information
Journal of the Korea Institute of Information and Communication Engineering / v.7, no.2, 2003 , pp. 177-182 More about this Journal
Abstract
In this study, we research the robust speech recognition for the syllables and phoneme units with the feature parameter including the voiced-unvoiced measures for the confusable words. In order to make it possible, we propose the measure representing the voiced-unvoiced degree by using the HPS(Harmonic Product Spectrum) information, used on pitch detection. We proposed this measures with the sharpnes, peak count and height measure of HPS. We reconstructed the feature parameter including this measures, then we performs the speech recognition experiments and compared with the typical feature parameters under the CVC type confusable syllables DB.
Keywords
Speech Recognition; HPS; Feature Parameter; Voiced; Unvoiced;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Lawrence Rabiner, Bing-Hwang Juang, 'Funda mental of speech recognition,' Prentice Hall, 1993
2 Nolt M., 'Pitch determination of human speech by the harmonic product spectrum, the harmonic sum spectrum, and a maximum likelihood estimate,' In Proceedings of the Symposium on Computer Processing Communications, pp. 779-797, Polytechnic Institute of Brooklyn
3 L. R. Rabiner, R. W .Schafer : 'Digital-processing of speech signals,' Prentice Hall
4 Andras Zolnay, Ralf Schluter, Hermann Ney, 'Robust speech recognition a voiced-unvoiced feature' Vol.2, pp. 1065, ICSLP, 2002
5 http://www-ccrma.stanford.edu/-pdelac/PitchDetection/icmc01-pitch. pdf