Segmentation of speech into syllable units using fuzzy smoothed short term energy contour

Sheikhi G., Almasganj F.

2011 18th Iranian Conference of Biomedical Engineering, ICBME 2011, Tehran, Iran, 14 - 16 December 2011, pp.195-198, (Full Text) identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/icbme.2011.6168554
  • City: Tehran
  • Country: Iran
  • Page Numbers: pp.195-198
  • Keywords: fuzzy smoothing, short term energy function, speech segmentation, syllable
  • Middle East Technical University Northern Cyprus Campus Affiliated: No

Abstract

This paper investigates the problem of segmenting speech into sub-word units. In this work, a novel technique based on fuzzy smoothing is applied on short term energy function of speech wave. The smoothed energy contour is searched then in order to find local minima that imply to syllable units. Experimental results-conducted on 200 different sentences, 20 speakers (12 males, 8 females) in Farsdat 1 dataset-showed that about 93.8% of syllables are detected with less than 20% of average syllable duration error. The proposed method has a good improvement compared with common moving average smoothing method. © 2011 IEEE.