<html><head><meta http-equiv="Content-Type" content="text/html; charset=UTF-8" /></head><body style='font-size: 10pt; font-family: Verdana,Geneva,sans-serif'>
<p>Trying to understand the Speex preprocessor denoising algorithm implementing the Ephraim-Malah method - is a voice activity detector determining speech and speech pause frames in any way necessary to computation of the a priori / a postereori SNRs, or is the voice activity detector output simply an output of the algorithm? </p>
</body></html>