I've been conducting some research lately on Speech Enhancement of the ITU-T Recommended G.729 Voice Activity Detection (VAD) algorithm for GSM Speech coders.
It has been suggested in the literature to measure the performance of speech enhancement algorithms using Perceptual Evaluation of Speech Quality (PESQ), and Short Time Objective Intelligibility (STOI).
So far I have been able to compute these measures including Signal-To-Noise Ratio (SNR).
But what bugs me is this post on Wikipedia, that says:
"VAD is essential for enhancing system capacity by reducing co-channel interference and power consumption in portable digital devices."
So, I have been wondering how I would go about measuring the performance of the system/channel capacity in terms of co-channel interference and power consumption using an enhanced speech sample.
I have been researching this issue for the past 3days now, and all that I could find was this article, though it doesn't clearly address my issue.
Please does anyone have any idea/suggestion on what I could do to go about measuring the co-channel interference and power consumption level of an enhanced speech signal?