I believe you thought about that a lot of times, but...
what about application of DNNs in acoustic modeling?
Is it planned to be implemented in Sphinx?
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
DNN gives nice results on speech recognition tasks, however, there are unsolved problems too. For example, it's not easy to adapt DNNs. DNN is not our top priority.
Hi,
I believe you thought about that a lot of times, but...
what about application of DNNs in acoustic modeling?
Is it planned to be implemented in Sphinx?
DNN gives nice results on speech recognition tasks, however, there are unsolved problems too. For example, it's not easy to adapt DNNs. DNN is not our top priority.
Our plans for release are covered on a wiki page
http://cmusphinx.sourceforge.net/wiki/releaseschedule