Voice Activity Robust Detection of Noisy Speech in Toeplitz

Jingfang Wang

Abstract


A Toeplitz de-noising method using the maximum eigenvalue is proposed for the voice activity detection at low SNR scenarios. This method uses the self-correlation sequence of speech bandwidth spectrum to construct a new symmetric Toeplitz matrix and to compute the largest eigenvalue, and the double decision thresholds in the largest eigenvalue are applied in the decision framewok. Simulation results show that the presented algorithm is more effective in distinguishing speech from noise and has better robustness under various noisy environments. Compared with novel method of recurrence rate analysis, this algorithm shows lower wrong decision rate. The algorithm is of low computational complexity and is simple in real-time realization.

 

DOI:  http://dx.doi.org/10.11591/telkomnika.v13i1.6902 


Keywords


voice activity detection(VAD), speech bandwidth spectrum, maximum eigenvaluem, robustness, Toeplitz matrix

Full Text:

PDF

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

shopify stats IJEECS visitor statistics