Archive | Code

RSS feed for this section

OpenEars 2.5 and all plugins out now!

22 February

¿Qué Hay De Nuevo? After a just-slightly-longer-than-expected incubation period (ahem), it is my pleasure to introduce OpenEars 2.5: Hear All The Languages. Image by Allie Brosh Well, perhaps not all of the languages. Many of the languages! I’ve developed a language-agnostic grapheme-to-phoneme algorithm which works from a file format fast enough for a phone, and […]

OpenEars 2.04 and compatibility versions of all plugins out now, with no more uppercase requirements

10 May

Today I’m happy to announce that OpenEars 2.04 and all plugins are out now. This is primarily a bugfix release to reduce memory overhead in OEPocketsphinxController and RapidEars while listening, and to prevent a very rare crash that could happen when stopping listening with RapidEars when a lattice search is still working. However there is […]

Comments Off on OpenEars 2.04 and compatibility versions of all plugins out now, with no more uppercase requirements Continue Reading →

OpenEars 1.3.0 out now with Pocketsphinx and Sphinxbase .8

14 June

Just a quick note that after months of testing of OpenEars 1.3.0 preview including Pocketsphinx and Sphinxbase .8 and no issues coming up with those new libraries, OpenEars 1.3.0 is now the release version of OpenEars and has been released in a non-preview version with a couple of bugfixes. As always, ask questions and let […]

Comments Off on OpenEars 1.3.0 out now with Pocketsphinx and Sphinxbase .8 Continue Reading →

OpenEars 1.2.3 and NeatSpeech 1.0!

25 October

It’s my pleasure to introduce NeatSpeech, a new plugin for the OpenEars platform which adds better TTS/text-to-speech voices to OpenEars’ voice synthesis. NeatSpeech is a plugin for OpenEars that adds fast, higher-quality speech synthesis (TTS) including multithreaded speech queueing to speak very long phrases without any lag. It uses HTS voices which are ideal for […]

OpenEars 1.2.1, RapidEars 1.1, Rejecto 1.0

20 September

Another big release day! OpenEars 1.2.1 is out, adding the very-suddenly-required armv7s slice and fixing the bug in which speech from right before a call to suspendRecognition will be processed after recognition is resumed. Downloadable at Also released today is RapidEars 1.1, which further refines many improvements of the past few versions and is […]

OpenEars 1.1, plugins, and RapidEars live recognition for iOS!

18 June

OpenEars 1.1, the OpenEars plugin system, and RapidEars 1.0, a plugin for OpenEars for live recognition! Today is a big release day for Politepix: OpenEars 1.1 and the introduction of the OpenEars plugin system! Featuring RapidEars, a plugin for OpenEars that does recognition on live speech. I am very happy to be introducing multiple Cool […]

OpenEars 1.01 is out

10 April

I’ve released OpenEars 1.01 today, a bugfix update for the following three issues: • Leaks in the dynamic language model generation process could crash the device, • When using a very small model, the discounting method used by the language model generation process could occasionally result in certain words having a probability that is so […]

SpeexKit: Speex on the iPhone, from Politepix

25 March

SpeexKit: Speex for iPhone It is my pleasure to announce a new Politepix framework product for developers: SpeexKit 1.0. What is Speex? Speex is one of the best codecs for voice audio transmission available, with clear quality and excellent compression characteristics. It is a great match for mobile speech applications given the need for top-notch clarity […]

New OpenEars version .912 out now

17 July

I’m happy to announce the release of OpenEars .912, 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) […]

New OpenEars version .91 is out now

23 May

Hello, I just uploaded the new version of OpenEars, featuring the following new stuff among other things: • All audio functions (Flite speech and Pocketsphinx recognition) handled in-memory • Low-latency Audio Unit audio driver for Pocketsphinx • Switching between all the Flite voices on the fly • Dynamically creating ARPA language models in-app • Switching […]