Hi all! I just tried to get in sphinx3, cmu's speech recognition system. I downloaded the offered an4 and rm1 databases to train a model. But it fails me. I have a tutorial, acompanied by some perlscripts. They prepare thet data (computing mel cepstra format from audio-signals, training models, building tress). But while building tress (if anyone's got the same tutorial), it fails in directory 07. Any ideas on that? Anyone having experience with it? I start to get desperate for help! Kindest regards Julien -------- Music was my first love and it will be my last (John Miles) ======== FIND MY WEB-PROJECT AT: ======== http://ltsb.sourceforge.net - the Linux TextBased Studio guide