This is a second part which describes voicemail transcription for Asterisk administrators. See previous part which describes how to setup Pocketsphinx hereSo you have configured the recognizer to transcribe voicemails...

So we are in. Great to know that. For more information seehttp://cmusphinx.sourceforge.net/2011/03/cmusphinx-at-gsoc-2011/I think it's a big responsibility and a big opportunity as well. Of course we don't consider this as...

Another practical question is - how do you integrate fillers? There is silence class introduced in A GENERALIZED CONSTRUCTION OF INTEGRATED SPEECH RECOGNITION TRANSDUCERS by Cyril Allauzen, Mehryar Mohri, Michael...

Interesting thing about Sphinxtrain models is that it uses word position as a context when looking for a senone for a particular word sequence. That means that in theory a...

A bit of openfst troubleshooting when you try to build WFST with Juicer. Say you are runningfstcompose ${OUTLEXBFSM} ${OUTGRAMBFSM} | \fstepsnormalize | \fstdeterminize | \fstencode --encode_labels - $CODEX | \fstminimize...

Here is the question - a perfectly looking sound file which is transcribed with 10% accuracy. Sounds crazy, isn't it? Click on it to enlarge. No noise, no accent.Because of...

In addition two the previous post, two more tricks for log_diag_eval.Floats instead of doubleIf accumulator is float, SSE could be used more effectivelyHardcode vector lengthThe most common optimizaition is loop...

I spend quite significant amount of time training various models. It feels like alchemy, you add this and tune there and you get nice results. And while training you can...

With Russian voice from Voxforge DB. Yay! Try it on the web:http://mary.dfki.de:59125/Mary is definitely superious system comparing to Festival. Graphical UI, modern design, support for various things like automatic dictionary...

So I finally finished testing of the stress-aware model. It took me few month and the end I could say that lexical stress is definitely better. It provides better accuracy...