Human-electronic device communication

Imagine a world where humans can communicate with electronic devices in the same way they talk to other human beings. Imagine a world where people could tell their vehicles what music they want to hear in the morning, and then have it automatically changed for them in the evening. Imagine "smart" vehicles that will drive themselves to their owners' destination whilst calling the grocery store for the family's daily needs.

Much of this technology is already a reality - and the rest could soon follow if Swiss company SVOX AG has its way. SVOX is a university spin-off founded in the year 2000 by a group of researchers at the Federal Institute of Technology Zurich.

SVOX solutions are used for devices such as infotainment systems and hands-free car kits to enable turn-by-turn directions, command and control functionality, music track selection, handsfree dialing and similar actions. The company's Automotive Textto-Speech solutions are tailored for noisy car environments and are available in 24 languages and 35 voices.

The company designed the SpeechCreate development tool after receiving feedback from car manufacturers and Tier One suppliers.

Automotive Industries (Al) asked Martin Reber, CEO of SVOX AG to explain the reasoning behind the recent acquisition of a speech processing unit from Siemens.

Reber: Our goal is to make SVOX a one-stop destination for embedded speech. Whilst the company's roots are in speech output (TTS), the acquisition has enabled us to offer a complete range of speech solutions including speech recognition (ASR) and speech dialog. The ASR technology we have acquired is proven and mature.

Al: The SVOX speech solution recently became part of the Android mobile phone platform. Do you see Android and similar platforms becoming relevant for the automotive industry?

Reber: Demand for open-source software platforms is spreading. Initiatives such as Continental's AutoLinQ and GENIVI are good examples of this. We see it as part of a bigger "convergence" trend, where the line between mobile devices and in-car telematics is becoming increasingly blurred. We are ready to work with all of these new players to speech-enable their platforms.

Al: Tell us about the Microsoft and SVOX speech technology solutions.

Reber: Our focus is firmly on embedded speech. Since the Microsoft Auto platform is already such a big success (with Ford Sync shipments already exceeding one million units), SVOX has made it a priority to optimize its offering for this platform. The suite allows customers to differentiate themselves by making their Microsoft in-car products more intuitive to use.

Al: What new automotive solutions is SVOX working on?

Reber: The next "big thing" in speech user interfaces is flexible dialog - a solution that allows the user to communicate with the car as if it were a human being. For example, a user may say "I would like to read something in the evening," and the system will reply with, "Would you like to download a book or visit a book store?" The dialog will then continue until the task is accomplished.

Al: How big is SVOX's global reach so far, and how do you hope to further expand its influence?

Reber: Our business is global by nature. Our clients are major international OEMs and Tier Ones. We currently have offices in Switzerland , Germany and the USA and the team is truly international. There are more than 15 nationalities amongst our 100 employees. For SVOX, the most obvious next step would be expanding into other major regions such as Asia.

[Sidebar]

"Our focus is firmly on embedded speech, and the solutions that we offer are highly portable and platformindependent."

Martin Reber, CEO of SVOX AG