Baidu launches ‘voice first’ keyboard app powered by AI
Why type on your phone’s tiny keyboard when you can tell it what to type instead?
That’s the thinking behind a new keyboard app called TalkType released today by the Chinese web services giant Baidu Inc. The company calls it “the world’s first voice-centric, full-function keyboard.”
The new app, which is now available on Android devices through the Google Play Store, is focused on speech-to-text and takes advantage of Baidu’s powerful speech recognition artificial intelligence.
The new app includes a few of the usual Android keyboard staples like swipe texting, keyboard themes, location sharing and emojis, but Baidu is putting a heavy focus on TalkType’s speech recognition capabilities—it is in the name, after all.
“TalkType is the first full-function Android keyboard that is ‘voice first,’ not ‘voice also,'” said Bijit Halder, head of Baidu’s Silicon Valley AI Lab (SVAIL) product team. “Unlike conventional keyboard designs, where voice is targeted for occasional use and delegated to a small icon, TalkType is designed for voice as the primary input mode.”
TalkType is currently available for Android only, and Baidu has not said if or when an iOS version might be coming.
Much faster than typing
Earlier this year, researchers from Baidu and Stanford University released a study that claimed that speech-to-text programs are now not only three times faster than typing on mobile devices, but they are actually more accurate.
The study compared Baidu’s Deep Speech 2 software and iOS’s built-in QWERTY English and Mandarin (Hanyu Pinyin) keyboards, and the researchers determined that the speech program is both three times faster and 20.4 percent more accurate than typing in English. They also found that typing in Mandarin is 2.8 times faster and an incredible 63.4 percent more accurate. This same technology is what is being used to power Baidu’s new TalkType app.
“At the core of TalkType is Baidu’s speech recognition engine, built using deep learning,” said Baidu Chief Scientist and deep learning pioneer Andrew Ng, who is also an associate professor of computer science at Stanford. “High-accuracy speech recognition makes it possible to achieve speeds up to three times faster than before. As speech recognition continues to make dramatic improvements, it’s natural that speech will become a more and more popular way to communicate with devices.”
James Landay, professor of computer science at Stanford and co-author of the speech recognition study, added, “In the past two to three years, speech recognition has improved a lot, benefiting from big data and deep learning to train its neural networks to produce faster, more accurate results. I believe that TalkType is just the beginning of a spate of a new mobile apps that will be designed from the ground up to use speech as their primary input method.”
You can watch a video of Baidu’s new TalkType keyboard app below:
Image courtesy of Baidu
A message from John Furrier, co-founder of SiliconANGLE:
Your vote of support is important to us and it helps us keep the content FREE.
One click below supports our mission to provide free, deep, and relevant content.
Join our community on YouTube
Join the community that includes more than 15,000 #CubeAlumni experts, including Amazon.com CEO Andy Jassy, Dell Technologies founder and CEO Michael Dell, Intel CEO Pat Gelsinger, and many more luminaries and experts.
THANK YOU