Advertisement

Chinese Speech Syllable Segmentation Algorithm Based on Peak Point and Energy Entropy Ratio

  • Zhirou Zhao
  • Yubin ShaoEmail author
  • Hua Long
  • Chuanlin Tang
Conference paper
  • 29 Downloads
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1060)

Abstract

In this paper, we propose a syllable segmentation algorithm based on peak point and energy entropy ratio. Firstly, the peak and valley of time-domain waveform envelope and energy entropy ratio are employed to segment the syllables of continuous speech, and then, the two segmentation results are fused to determine the starting and ending points of each syllable. Experimental results reveal that the algorithm can accurately segment syllables in low signal-to-noise ratio (SNR) environment. And the method has higher robustness and higher accuracy.

Keywords

Peak point Energy entropy ratio Syllable segmentation 

References

  1. 1.
    Villing R, Ward T, Timoney J. Performance limits for envelope based automatic syllable segmentation. In: IET Irish signals and systems conference; 2006. p. 521–6.Google Scholar
  2. 2.
    Li J, Shen F. Automatic segmentation of Chinese Mandarin speech into syllable-like. In: International conference on Asian language processing, IEEE; 2015. p. 57–60.Google Scholar
  3. 3.
    Sheikhi G, Almasganj F. Segmentation of speech into syllable units using fuzzy smoothed short term energy contour. In: 18th ICBME, IEEE; 2011. p. 195–8.Google Scholar
  4. 4.
    Räsänen O, Doyle G, Frank MC. Pre-linguistic segmentation of speech into syllable-like units. Cognition. 2018;171:130–50.CrossRefGoogle Scholar
  5. 5.
    Jittiwarangkul N, Jitapunkul S, Luksaneeyanavin S, et al. Thai syllable segmentation for connected speech based on energy. In: IEEE, APCCAS 1998; 1998. p. 169–72.Google Scholar
  6. 6.
    Prasad VK, Nagarajan T, et al. Automatic segmentation of continuous speech using minimum phase group delay functions. Speech Commun. 2004;42(3–4):429–46.Google Scholar
  7. 7.
    Pan F, Ding N. Speech denoising and syllable segmentation based on fractal dimension. In: 2010 ICMTMA, IEEE; 2010. vol. 3, p. 433–6.Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Zhirou Zhao
    • 1
  • Yubin Shao
    • 1
    Email author
  • Hua Long
    • 1
  • Chuanlin Tang
    • 1
  1. 1.School of Information Engineering and AutomationKunming University of Science and TechnologyKunmingChina

Personalised recommendations