
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 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."
Most Popular Stories
- SEO Traffic Lab Celebrate Wins at Digital Marketing Event 'Internet World 2013' in London
- Social Media Initiatives Should Follow Customers' Lead
- Apple CEO: Offshore Units Not a 'Tax Gimmick'
- U.S. Senate Accuses Apple of Large-scale Tax Avoidance
- UTEP Water Recycling Project Wins Venture Titles
- Marketo Makes a Mint in IPO: Stock Shoots Up More than 50 Percent
- Bieber Booed at Billboard Awards
- Crude Oil Up, Gasoline Down
- Austin Startup Compare Metrics Raises $3.5 Million for Expansion
- Why So Many Top 'Car Guys' Are Actually Women
News-To-Go
Advertisement
Advertisement
News Column
QNX Announces New In-Car Speech Recognition Framework to Understand a Speaker's Intent
Jan 7 2013 12:00AM
Marketwire
Advertisement
Story Tools



