nsh - Speech Recognition With CMU Sphinx

Blog about speech technologies - recognition, synthesis, identification. Mostly it's about scientific part of it, the core design of the engines, the new methods, machine learning and about about technical part like architecture of the recognizer and design decisions behind it.

When Language Models Fail

Language modeling still have many challenging problems.


Comic by Jim Benton

на 26.7.11
Ярлыки:
Действия: 

0 коммент.:

Post a Comment

Subscribe to: Post Comments (Atom)

Blog Archive

About Me

My Photo
Moscow, Russia
Nowdays I mostly work on open source projects in speech recognition and synthesis like Festival, CMU Sphinx and Voxforge. I also support the Russian parts of those projecs, providing the leading product in ASR and TTS in Russian. In the past I used to participate in GNOME, work on embedded Linux devices and on software development technologies related to automatic software verification and modelling. If you have any questions feel free to contact me by mail nshmyrev at nexiwave dot com or find me in jabber/irc.