Please use this identifier to cite or link to this item:
|Title:||Robustness of group delay representations for noisy speech signals|
|Authors:||Krishnan Parthasarathi, S.H.|
|Keywords:||AMR VAD; Cepstral coefficients; Group delay functions; Minimum-phase signal; Noise spectra; Noisy speech signals; Speech spectra; Voice activity detection; Speech recognition; Group delay|
|Citation:||International Journal of Speech Technology, 14(4), 361-368|
|Abstract:||This paper demonstrates the robustness of group delay based features to additive noise. First, we analytically show the robustness of group delay based representations. The analysis makes use of the fact that, for minimum-phase signals, the group delay function can be represented in terms of the cepstral coefficients of the log-magnitude spectrum. Such a representation results in the speech spectrum dominating over the noise spectrum, both at low and high SNRs. Further, we experimentally demonstrate the robustness of the representation on a voice activity detection (VAD) task, comparing a group delay based VAD algorithm with standard VAD methods as well as a magnitude-spectrum based method. � 2011 Springer Science+Business Media, LLC.|
|Appears in Collections:||Articles|
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.