Smartphone Speech Recognition is More Accurate and 3 Times Faster Than Humans

August 24, 2016
Speech to Keyboard

The research team, which included computer scientists from Stanford, Baidu Inc. and the University of Washington, devised an experiment that pitted Baidu’s Deep Speech 2 cloud-based speech recognition software against 32 texters, ages 19 to 32, working the built-in keyboard on an Apple iPhone.

The results from the new experiment suggests that speech recognition can be used to compose text messages faster and more accurately than humans can type on mobile phone screens.

The results were clear no matter the language. For English, speech recognition was three times faster than typing, and the error rate was 20.4 percent lower. In Mandarin Chinese, speech was 2.8 times faster, with an error rate 63.4 percent lower than typing.

James Landay, a professor of computer science and co-author of the new study says, “We should put speech in more applications than just typing an email or text message. You could imagine an interface where you use speech to start and then it switches to a graphical interface that you can touch and control with your finger.”

Read the entire Stanford News article by Bjron Carey HERE.

More From James Landay:
Presentation from #mediaX2015 Conference: From On Body to Out of Body User Experience

Presentation from Science & Technology of Feedback: Balancing Design & Technology in Feedback for Change