... Eric> Hi all, I started looking at all of the new options (woo Eric> hoo) in v 3.20, and am curious: is there a way on the Eric> command line to take a...

Yes, Matlab-formatted weights are definitely the way to go. ... In addition to Barry's HATs setup, you can do neat things like "bottleneck" features from Brno:...

... Wow! That ain't rocket science! Thanks for the tip. ... Very cool, looking forward to it. -Eric...

... aha. I still have old rap3 weights (from qnstrn) so I can use qncopywts to convert to matlab. I guess I could hack the rap3 weights file rather easily...

... Rejecting frames is no joke! We've recently found that it's a great way to speed up training if you reject them in such a way as to leave a subset of data...

... Arlo> Rejecting frames is no joke! We've recently found that it's Arlo> a great way to speed up training if you reject them in such Arlo> a way as to leave...

... Yeah, that's similar to the kind of thing that Jun Hou and Larry Rabiner were seeing in their TDNN trainings, if I interpret what you're saying to mean...

... Yes, that's the idea in principle. In practice, I actually somewhat over-sample the more frequent classes for performance reasons. ... I randomly sample...

... Eric> Or, does someone have some code to munge the weight files Eric> for me? ... Eric> aha. I still have old rap3 weights (from qnstrn) so I can Eric>...

Hi Eric, ... Arlo already proposed a good solution. I cooperate with Brno guys on the new shiny Bottle-Neck features :) (hopefully more in ICASSP'08 paper) and...