Eric Fosler-Lussier

I'm mulling over different solutions for this. Input welcome, particularly from @ramonsanabria and/or @fmetze - The simplest solution is to print out a warning in tf_test if subsampling > 1....

Last night's run, using only SWB grammar and giving the forward pass --subsampled_utt 1 (which basically will select the first copy it sees), resulted in 20.0 WER, which is the...

Side note: I just realized some of my questions (e.g. role of nnet.py) arose because I had broken out stuff from decode_ctc_lat_tf.sh and put it directly in run_ctc_phn.sh when I...

Thought I would bump this thread - the tf_clean branch for v1-tf still doesn't come with a decoder in run_ctc_*.sh scripts (just exits after forward pass on the AM). My...

Should I bother trying to put the two back together? It would not be hard but if it's not on the critical path then I'm not going to bother. It...

What's the current status on this? I'm starting the (crazy) sabbatical project and it's pretty clear that some sort of online decoding mechanism is going to be necessary. I can...

@fmetze 's comment was that CTC seems to be relatively dependent on the LSTM recurrent connections (which makes sense when I think about it). CNN with a wide enough window...

This seems like a reasonable step (student-teacher) and simple to implement. Re: python in the loop - I'm working on an eesen-in-the-browser project in order to enable some other stuff...

Our experience is that log filterbanks do work somewhat better than MFCCs, but if you're mostly working on pipeline at the moment the hit you'll take on MFCCs will not...

Lol, yeah, I was just being a bit lazy. My usual MO is to run a virtual machine on my mac with Linux. Trying to compile OpenFST on my mac...