... I've replicated the error with the current version of cygwin. The problem is an incompatibility between libtool 1.3 and the current version of cygwin....
... Adam> --- In icsi-speech-tools@yahoogroups.com, "francisspeech" ... Adam> I've replicated the error with the current version of Adam> cygwin. The problem...
I am trying to install the SPRACHcore tool under Linux system. But it seems has system version probelm. When I type ./configure it shows: loading cache...
I am looking for help understanding the way the weights are recorded in the weights file. Specifically if anyone has a matlab script which will load them. I...
One of our former, highly missed, speech group members, Barry Chen, wrote the following: ... I'm attaching the file 'rap_weights3_read.m'. I hope this helps. ...
hey, Does anyone have a set of matlab scripts that will run a neural network in the same way quicknet does? I have code that will import the weights from the...
Greetings, I followed the the INSTALL file of feacalc-0.90, which said that farray_octl might be needed: get farray_otcl; configure it --with-dat=<dat build...
... xuchenyao> --- In icsi-speech-tools@yahoogroups.com, David Johnson ... xuchenyao> Hi David, I see no INSTALL file in the tar ball. Whoops - this is in CVS...
Thank you, David. You'd better add the INSTALL file to the tar ball release file ;--) And there's a little bug in the config file, see the following output: ...
... yaoxuchen> Thank you, David. You'd better add the INSTALL file to yaoxuchen> the tar ball release file ;--) The file will be in the tar ball next time...
... yaoxuchen> Thank you, David. You'd better add the INSTALL file to yaoxuchen> the tar ball release file ;--) The file will be in the tar ball next time...
Hi, There are 2 inputs of qnstrn and qnsfwd: ftr1_file and ftr2_file. And there are a bunch of other similar inputs, like ftr1/2_ftr_start, ftr1/2_window_len....
The history behind this is that in the bad old days, when (a) pfiles had a 2gb limit, and (b) disks were not that big, we often wanted to combine two pfiles...
Eric Fosler-Lussier
fosler@...
Apr 12, 2007 11:42 am
76
... yaoxuchen> Hi, There are 2 inputs of qnstrn and qnsfwd: ftr1_file yaoxuchen> and ftr2_file. And there are a bunch of other similar yaoxuchen> inputs, like...
"do different operations on them(. deltas .)", do you mean set ftr1/2_delta_order? Usually, if the input feature file includes delta and double delta features,...
Thanks David. David> If you trace back through the references to Morgan's work in the early 90s you'll find out what the RAP was (I don't have a reference to ...
... yaoxuchen> Thanks David. David> If you trace back through the references to Morgan's work David> in the yaoxuchen> early 90s you'll find out what the RAP...
Got the solution. Usually the frame number from labels2pfile is <= the frame number from feacalc. That it because the .phn file doesn't label all the frames in...
Hi, Using the test script in quicknet3 package, I got about 90% training accuracy, and 83% CV accuracy. But when applying quicknet on the TIMIT Speech Corpus,...
Xuchen, Your results on TIMIT seem perfectly normal. Here are two TIMIT experiments that I've run (using an old version of Quicknet in 2003): 61.7% test frame...
Arlo Faria
arlo@...
Apr 27, 2007 5:04 pm
84
Thank you Arlo. Your response really inspires me. Thank you. -Xuchen _____ From: icsi-speech-tools@yahoogroups.com [mailto:icsi-speech-tools@yahoogroups.com]...
In the last post I asked about a "normal" training accuracy, and thanks Arlo that I'm in the right way. So I started to use QuickNet for our own job, but only...
Hi Xuchen, (CC'd to the list, for reference) I looked at your log file and it seems there's no bugs. Moreover, your results seem perfectly "normal" ... when...
Arlo Faria
arlo@...
May 15, 2007 4:40 am
87
Thank you Arlo. In order to decide which is the best hidden unit size, I read the paper "Size Matters" before. The whole job contains 40M frames, with 39 input...
Your input layer has 39*9=351 units, so the formula would suggest about 4000 hidden units. If this is too big/slow, I would recommend training on a subset of...
Having problems with message search?
Fill out this form to ensure your group is one of the first to be migrated to the new message search system.
