Have you looked into http://www.metadecks.org/software/sweep/ ? I know nothing about it, but it seems like it does a lot. ecasound has some filters in it, too, but it seems like sox has more. --- Matthew Lawson <http://www.1control.com/~matt> wrote: > Just another semi-related thought. > > Has anyone played around with using sox to pre-process the audio data > before sending it to a voice recognizer? It can do all sorts of fun > things like companding, frequency filter, volume modification, etc. The > goal is to get the strongest voice signal separated from the background > noise, particularly when the mic is farther away and/or in a noisy > environment. > > Has anyone tried something like this? And if so, have you found any > particular parameters that work well? > > - Matt