I have recently read an article on improving recognition accuracy of any speech recognition system (http://www.google.com/patents?id=mZ2jAAAAEBAJ&dq=Pattern+recognition+accurac...) where the voice input signal, x, has two modified copies made of itself before reaching the recognition engine. The 3 lists of possible utterances derived from each of these signals is looked at to determine the best choice for what the utterance could have been. This technique is claimed to reduce recognition errors up to 80% and obviously will slow down performance but is implemented in call centers that utilize Fluency Voice technology. The technique seems simple. Basically, one variant of the original voice signal, x, is "expanded" or amplified in a nonlinear way so that weaker signal component strengths are magnified more so than stronger ones. In the other variant, the signal x is expanded so that stronger signal component strengths are magnified to a greater extent than weaker ones. Also, there are gain factors applied to these new signals to account for overall signal strength changes. At least that's my take on the article. The formula used for signal expansion is just a simple power function of the form y = g*x^c, where y is the new signal, g is the gain factor and c is the the power. Expected values of c vary from 0.6 to 1.4 and g is around 20 for c=0.6 and g=0.1 for c=1.4 (See the cited article for more details). Now, this is just one example and there maybe better or other ways to do improve pocketsphinx (PS) accuracy for phone signals. So my interest is about ways one could do pre-processing of signals in FS before they "hit" pocketsphinx. I presume that the generated lists are an issues that PS folks would have to help me with. Any guidance on this and how to implement some form of signal pre-processing in FS would be much appreciated. Mark.