Loading...

An efficient real-time voice activity detection algorithm using teager energy to energy ratio

Hadi, M ; Sharif University of Technology | 2019

438 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/IranianCEE.2019.8786643
  3. Publisher: Institute of Electrical and Electronics Engineers Inc , 2019
  4. Abstract:
  5. We define a new feature called Teager Energy to Energy and mathematically show that it provides distinguished values for pure tone and white noise signals. We then employ the Teager Energy to Energy feature to propose an efficient procedure for voice activity detection and use simulation results to evaluate its performance in different noisy environments. Furthermore, we experimentally demonstrate the performance of the proposed voice activity detection technique in a real-time voice processing embedded system. Experimental and simulation results show that the introduced procedure provides more reliable results with a reasonable amount of computational complexity in comparison with its conventional counterparts and can extract voice frames from a -5 dB SNR noisy voice signal with a success probability of 89.4%
  6. Keywords:
  7. Cross Correlation ; Teager Energy ; Energy efficiency ; Mathematical transformations ; Signal detection ; Signal to noise ratio ; White noise ; Cross correlations ; Energy feature ; Hilbert transform ; Noisy environment ; Real-time voice ; Reliable results ; Voice activity detection ; Speech recognition
  8. Source: 27th Iranian Conference on Electrical Engineering, ICEE 2019, 30 April 2019 through 2 May 2019 ; 2019 , Pages 1420-1424 ; 9781728115085 (ISBN)
  9. URL: https://ieeexplore.ieee.org/document/8786643