QNX builds in-car speech framework with AT&T's Watson, knows our true intentions

QNX wants to put an end to in-car voice systems that require an awkward-sounding syntax to get the job done. As part of its CES launches, it's rolling out a framework for its speech recognition technology leaning on AT&T's Watson engine. By offloading the phrase interpretation to AT&T's servers, any infotainment system with the framework inside can focus on deciphering the speaker's intent — letting drivers spend more time navigating or playing music, instead of remembering the necessary magic words. QNX will roll out the voice element as part of its CAR platform at an unspecified point in 2013. We'll have to wait until car and head-end unit designers implement the platform in tangible hardware, but the new speech system will hopefully lead to more organic-sounding conversations with our cars.

Follow all the latest CES 2013 news at our event hub.

Show full PR text

QNX Announces New In-Car Speech Recognition Framework to Understand a Speaker's Intent

New intent framework to bring power of AT&T Watson(SM) speech recognition engine to wider variety of in-car systems and applications

OTTAWA, ONTARIO (Marketwire) 01/07/13 QNX Software Systems Limited, a global leader in software platforms for in-car electronics, has announced a powerful new framework that will allow speech recognition systems in cars to understand a speaker's intent. The framework extracts meaning from the driver's spoken words, enabling in-car systems to create calendar appointments, dictate email or text messages, set complex navigation destinations, and even perform general Internet searches.

The framework, which is a component of the QNX CAR(TM) application platform, allows in-car applications to access AT&T Watson(SM) speech recognition technology. AT&T Watson(SM) is AT&T's pioneering speech services platform, which enables the development of next-generation technologies that go beyond speech to power more advanced natural language understanding and automatic speech recognition, among other capabilities. The multimodal and multilingual speech engine runs on a cloud-based server to provide extremely high-quality recognition with low latency.

Determination of the intent behind the driver's speech starts on the server, where the AT&T Watson speech engine begins to analyze words and fits them to known patterns. The results are then handed from the cloud to the car, where the in-vehicle intent engine from QNX Software Systems performs the remainder of the speech analysis to determine how to act.

"Sharing the workload across client and server offers automotive manufacturers and end-users the best of both worlds," said Andy Gryc, automotive product marketing manager, QNX Software Systems. "The server-side analysis, provided by AT&T Watson, is optimized for complex scenarios, such as a navigation application in which the driver may verbalize destinations in hundreds of different ways. The QNX client-side analysis grants car makers greater flexibility, enabling them to adapt the AT&T Watson results for a variety of in-car applications, regional aspects, or personal tastes."

"For many of us, the most natural way to communicate is with our voice. By working with QNX and opening access to our rich set of speech technologies developed at our labs, we're making it possible for more people to use the power of their voice to stay safely connected in their vehicles," said Mazin Gilbert, assistant vice president of technical research, AT&T Labs. "Delivering this type of next-generation virtual assistant applications for the connected car is especially important as we look at how technology can help drivers keep their eyes on the road and hands on the wheel."

The intent system from QNX Software Systems is dynamically pluggable, which allows the recognized vocabulary to change depending on what applications are active, and to support new apps that are downloaded to the car.

"Enabling natural, intuitive, user experiences is fundamental to our vision of the connected vehicle, and providing our automotive customers with the tools to create those experiences is fundamental to our product strategy," said Linda Campbell, director of strategic alliances, QNX Software Systems. "By providing a framework that enables our customers to take greater advantage of AT&T's phenomenal speech engine, the new intent system should help accelerate the adoption of speech recognition across a broad range of vehicles."

The QNX CAR application platform from QNX Software Systems is a comprehensive, pre-integrated software stack designed to help automotive companies reduce the time and effort of building highly sophisticated and connected infotainment systems.

QNX Software Systems has licensed its software technology for millions of in-vehicle systems worldwide, including digital instrument clusters, hands-free systems, multimedia head units, connectivity modules, and 3D navigation systems.

Developed at AT&T Labs, AT&T Watson(SM)has been powering advanced speech services in the marketplace for years. The technology reflects more than one million hours of research and development in speech technologies that has led to more than 600 U.S. patents and patent applications.


The intent system will be offered as a component of the QNX CAR application platform in 2013. Release 2.0 of the platform will be available to the automotive community this month. Separate licensing from AT&T will be required to use AT&T Watson components.

Panel participation at AT&T Developer Summit

Today, at the AT&T Developer Summit, Andrew Poliak, director of automotive business development at QNX Software Systems, will participate in the panel "Navigating the Connected Vehicle Vision." The session will be held from 3:00 to 3:45 pm, at the Palms Casino Resort.