OpenEars Changelog

To install the current version, follow the instructions at Getting Started with OpenEars.

0.913 – October 11th, 2011
A bugfix release that fixes an issue that could prevent compilation on an upcoming OS version.

0.912 – July 17th, 2011
A bugfix release fixing the following issues:

• OpenEarsEventsObserver was never receiving a delegate message when a language model was being changed (thanks to Aleksey for finding this bug)
• LanguageModelGenerator was not finding alternate pronunciations of a word (thanks to Sarinsukumar for finding this bug)
• AudioSessionManager will now correctly reset audio session settings that a media player object (such as an AVPlayer or MPMusicPlayerController among others) overrides if startAudioSession is run a second time afterwards. If a PocketsphinxController object is already instantiated and its loop has been started at the time that a media player object has overridden its audio session settings, after AudioSessionManager startAudioSession is run the second time, you _may_ also need to restart the listening loop if the media player’s audio session override gave PocketsphinxController an interruption signal that caused it to make a controlled exit from the listening loop.

I strongly recommend upgrading to this version immediately if you use dynamic language model generation since it will improve recognition across different accents.

0.911 – June 23rd, 2011
Primarily a bugfix release fixing the following issues:

• Occasional crash in level metering after > 20 minutes of use
• There is now no limit on the size of the language model that can be generated by LanguageModelGenerator other than the time required. Very large language models will no longer crash, medium-sized language models will generate a bit more slowly, small-sized language models should be largely unaffected.
• An issue with codesigning on the device should be resolved.
• An issue with code display in Xcode should be resolved.
• An issue preventing running the simulator with the -all_load linker flag should be resolved

And adding the following feature:

Pitch, speed, variance control for text-to-speech.

0.91 – May 23rd, 2011
Now supports in-app creation of ARPA language models, switching between ARPA language models in the middle of the recognition loop, generates text-to-speech out of a memory object instead of an audio file, has a new low-latency in-memory audio driver for speech recognition, experimental bluetooth support, can be built with the linker flag -all_load, and many other changes.

0.9.02 – January 22nd, 2011
Maintenance release: workaround for compile with thumb bug in OS 4.2.1, fix for audio session becoming un-restartable when the OS takes over the audio session settings, addition of a meaningful confidence score for recognition, and OpenEars now supports JSGF grammars.

0.9.01 – September 17th, 2010
Simplification of library and fix for beta SDKs and Xcode prerelease versions.

0.9.00 – September 7th, 2010
First version.

To install the current version, follow the instructions at Getting Started with OpenEars.