Perhaps the most (or only) popular open source speech recognition tool, Sphinx is licensed under BSD and is written in Java. Sphinx also offers a mobile version called “PocketSphinx”.

“We trained multilingual speech recognition models on over 1,100 languages using a 1B parameter wav2vec 2.0 model,” Meta’s researchers explained.

There are four well-known open speech recognition engines: CMU Sphinx, Julius, Kaldi, and the recent release of Mozilla’s DeepSpeech (part of their Common Voice initiative).

Meanwhile, the Multilingual Spoken Words Corpus is said to be one of the largest audio speech datasets in the world, with keywords spoken in 50 languages. What MLCommons is trying to do is level ...

Google is planning to compete with Nuance and other voice recognition companies head on by opening up its speech recognition API to third-party developers. To attract developers, the app will be ...

The same tools that handle the speech recognition features in Google Assistant can now be used by a larger audience. The Google Cloud Speech API, which went into open beta in the summer of 2016 ...

Hot off of a AT&T Labs event held in New York City, AT&T has just announced they will be opening up their Watson speech recognition technology to developers this June. Though Watson has been open ...