i got this to build last week on osx with with pd-lib-builder. it DOES work. uses pocketsphinx. it needs to send translated speech to an outlet. right now it only prints translated speech to the console...

https://github.com/megrimm/pd-recog

would be great to get others to help get it all working! 

cheers
m



On Wed, Feb 28, 2018 at 2:53 PM, Dan Wilcox <danomatika@gmail.com> wrote:
Again, not within Pd, but we had some success using the CMU Sphinx 4 Java library and Processing for this project:

http://danomatika.com/projects/trust-me

I'm not sure if a Java app will be too heavy for an embedded board though, but I can send along the compiled Processing library wrapper I made for Sphinx 4 if you want.

Otherwise you can look into the earlier CMU sphinx implementation, but it wasn't quite as god as we need it. The fact of the matter is that speech recognition is not very good overall unless you send it off to some giant server farm ala Siri or Google, privacy issues notwithstanding.

Hi,

I'm planning to work on a project that will use a microphone to query on
freesound database, and we are planning to use speech recognition to send
the queries.  We will use pure data installed in a Bella board and
e-textile sensors to process the sound.

I'm considering send audio and do the speech recognition in a server using
the Google API or use Sphynx to do the recognition in Pure data. Does
anyone here has any experience with this recently and can make a suggestion?

thanks a lot!

Best,
Ariane



_______________________________________________
Pd-list@lists.iem.at mailing list
UNSUBSCRIBE and account-management -> https://lists.puredata.info/listinfo/pd-list




--
____________________
m.e.grimm, m.f.a, ed.m.
syracuse u., tc3
megrimm.net
____________________