CMU Sphinx, a Speech Recognition System, is transitioning to Open Source. The distribution contains a library (libsphinx2) and some small examples that link against it.
|Tags||multimedia Sound/Audio Speech|
|Operating Systems||Windows POSIX Linux|
Release Notes: This release adds support for Python 3.x, MinGW, and the Jack sound system.
Release Notes: Assorted bugfixes and enhancements.
Release Notes: Trigram cache flushing was added to constrain dynamic memory usage. A divide-by-zero in pitch extraction code was avoided. Segfaults, memory leaks, and handling of imports were fixed in the JSGF code. --without-python compilation was fixed. The system is now tolerant of missing backoff weights in ARPA format language models.
Release Notes: Major fixes to the frontend, mfcc, and search code, and stable ports to more platforms.