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...
Arlo Faria
arlo@...
May 15, 2007 5:45 am
89
Hi, I trained a net for 4000 utterances and then forward all 4000 utterances using qnsfwd. But I found that the first 4000 utterances contain more frames than...
It comes from the fact that you have a context window of 9 frames (since you don't have the qnstrn script here, it's hard to say which one, but if the...
Eric Fosler-Lussier
fosler@...
May 22, 2007 3:07 pm
91
Thank you, Eric. When using quicknet, I didn't pad either feature file or ilab pfile. So I always set hardtarget_window_offset=0 when using qnstrn and qnsfwd....
... Yes, and train with hardtarget_window_offset=4, I would recommend. This will skip the first 4 labels (which is what you want). Otherwise, with...
Eric Fosler-Lussier
fosler@...
May 23, 2007 1:31 am
93
Well, I didn't notice the -deslen option of feacat/labcat before. Maybe there's no example in the manpage so I never thought to try it... Anyway, I learned a...
It's actually a weird feature that I had Dan Ellis put in for me. I don't know if anyone other than me uses it. :-) -EFL...
Eric Fosler-Lussier
fosler@...
May 23, 2007 2:08 am
95
I use the -deslen option all the time... maybe too much! I have to coordinate feature and label streams from ICSI, SRI, HTK, and ESPS tools, and they never...
Arlo Faria
arlo@...
May 23, 2007 8:51 am
96
With the help of many kind people (thanks a lot!) in this mail list, I finally got the correct posteriors with correct and matched frame numbers. So I guess...
Congratulations on getting a network trained -- that's the hardest part! I'm assuming that you're trying to generate Tandem-style features, rather than...
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.
