Date: Fri, 11 Aug 2017 15:00:00 +0000
<p>Thanks to our sponsor <a href="http://bit.ly/datasciencelearn">Springboard</a>.</p> <p>In this week's episode, guest Andre Natal from Mozilla joins our host, Kyle Polich, to discuss a couple exciting new developments in open source speech recognition systems, which include <a href="https://voice.mozilla.org/">Project Common Voice</a>.</p> <p>In June 2017, Mozilla launched a new open source project, Common Voice, a novel complementary project to the <a href="https://github.com/mozilla/DeepSpeech">TensorFlow-based DeepSpeech</a> implementation. DeepSpeech is a deep learning-based voice recognition system that was designed by Baidu, which they describe in greater detail in their <a href="https://arxiv.org/abs/1412.5567">research paper</a>. DeepSpeech is a speech-to-text engine, and Mozilla hopes that, in the future, they can use Common Voice data to train their DeepSpeech engine.</p>
