Automatic segmentation and labeling for Malay speech recognition

  • Authors:

  • S. A. R. Al-Haddad;Salina Abdul Samad;Aini Hussein;K. A. Ishak;A. A. Azid;R. Ghaffar;D. Ramli;M. R. Zainal;M. K. A. Abdullah

  • Affiliations:

  • Lab Signal Processing, Dept. Electrical, Electronic and System Engineering, Faculty of Engineering, National University of Malaysia, Selangor, Malaysia;Lab Signal Processing, Dept. Electrical, Electronic and System Engineering, Faculty of Engineering, National University of Malaysia, Selangor, Malaysia;Lab Signal Processing, Dept. Electrical, Electronic and System Engineering, Faculty of Engineering, National University of Malaysia, Selangor, Malaysia;Lab Signal Processing, Dept. Electrical, Electronic and System Engineering, Faculty of Engineering, National University of Malaysia, Selangor, Malaysia;Lab Signal Processing, Dept. Electrical, Electronic and System Engineering, Faculty of Engineering, National University of Malaysia, Selangor, Malaysia;Lab Signal Processing, Dept. Electrical, Electronic and System Engineering, Faculty of Engineering, National University of Malaysia, Selangor, Malaysia;Lab Signal Processing, Dept. Electrical, Electronic and System Engineering, Faculty of Engineering, National University of Malaysia, Selangor, Malaysia;Lab Signal Processing, Dept. Electrical, Electronic and System Engineering, Faculty of Engineering, National University of Malaysia, Selangor, Malaysia;Department Computer and Communication System Engineering, Faculty of Engineering, Putra University of Malaysia, Selangor, Malaysia

  • Venue:
  • ISCGAV'06 Proceedings of the 6th WSEAS International Conference on Signal Processing, Computational Geometry & Artificial Vision
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

This study is focused on Malay speech recognition with the intention to distinguish speech and non-speech segments. This study proposes an algorithm for automatic segmentation of Malay voiced speech. The calculations of log energy and zero rate crossing are used to process speech samples to accomplish the segmentation. The algorithms are written and compiled using Matlab. The algorithm is tested on speech samples that are recorded in different environment at three different places in Faculty of Engineering, National University Malaysia. As a result almost nearly 90% of the Malay Speech can be segmented.