Keeping in touch. Wireless onboard systems will be able to communicate with household systems.
advanced techniques to blank out back- ground noise. For example, their use of so- called array microphones has substantially in- creased word recognition. Array microphones comprise two, four or eight small micro- phones installed, for example, in the rearview mirror. Whenever the driver speaks, the sound signal takes varying lengths of time to reach the individual microphones. On the ba- sis of these different propagation times, the array microphone is able to locate the sound source — in other words, the driver’s mouth
and suppress all other signals.
In Munich, CT researchers are working on a new system that employs lip-reading tech-
Using a video camera, software is able to combine a driver’s lip movements with spoken commands, thus increasing accu- racy even in the noisiest environments.
nology. This involves the use of a small video camera that monitors the driver’s face. Using, among other things, a special color-classifica- tion technique to scan the video images for different skin tones, the system localizes the driver’s lips and then deciphers the speech content on the basis of their movement. “It’s still early days, but we’re progressing well,” says Hoffmann. “This technology will further enhance the VSR’s performance in very noisy environments such as convertibles.”
Voice-activated modules in tomorrow’s vehicles will not only need to be able to in- terpret commands, they’ll also have to have speech capability of their own. This is already
(prosody) to be adopted. On the basis of this analysis, it searches out the right speech fragments from a sound catalog, modifies them and combines them into intelligible speech.
Dialog with Diane. “We’ve already devel- oped such a system for extremely small platforms such as mobile phones,” says Dr. Michael Lützeler, who is responsible for implementing Papageno at CT. Lützeler’s goal is to make voice quality more natural and therefore suitable for more demanding tasks. “We need to improve the quality of individual speech elements and of prosody,” he says. Like his colleagues in voice recognition, Lützeler is counting on the extra processing power and memory capacity that onboard
In the future, drivers will be able to converse naturally with cars.
the case with today’s navigation systems, which give drivers directions. In addition, the onboard infotainment systems of the future will also be able to read text messages, e-mail and text from the Internet so that drivers can access information while concentrating on the road.
Papageno, for example, is a highly com- pact voice synthesizer currently being devel- oped by Siemens researchers. The software first transcribes written words into phonemes and then determines the type of sentence to be spoken — for example, a question or short statement. In the process, it identifies the correct speech rhythm
systems possess in comparison to mobile phones.
Genuinely natural conversations with a virtual passenger will become a reality only when voice recognition and voice synthesis are linked using dialog components. It will then be possible to ask complex questions in a completely normal way — “Where’s the fuel cap?” or “Direct me to the nearest cheap gas station” — and the system will be able to un- derstand and answer many of them on the basis of information already on board or sourced from the Internet. Here, CT is pinning its hopes on the Diane dialog machine, which has already proved itself in applications for telephony, such as in answering systems.
And Siemens has even bigger plans for cars that can talk. For example, in conjunction with onboard systems, personalized voice recognition — as already used in certain phone applications — could prevent unau- thorized use of the vehicle. Such systems could also be equipped with a module to rec- ognize different languages. That way, rental cars would be able to switch automatically from one language to another, depending on the nationality of the driver. And, last but not least, speech styles could even be matched to the driver’s age — as determined by the sound of his or her voice — and thus switch from a laid-back to a more dignified way of talking. In other words, Krekel’s virtual pas- s e n g e r c o u l d a l m o s t b e i n d i s t i n g u i s h a b l e ■ R o l f S t e r b a k from the real thing.
Onboard electronics and software are making cars more comfortable, safer, and more environmentally acceptable.
We’ve Upgraded Your Car
Systems requiring maxi- mum reliability are prolifer- ating in vehicles. A new, open standard developed by the automobile industry will ensure that such sys- tems speak the same lan- guage and can be economi- cally combined and upgraded. A new software architecture from Siemens is designed to do the same for automotive infotain- ment systems.
I n the split second before a crash, multiple systems in your car could hold a confer- ence, evaluate the circumstances, and decide on a course of action that could save your life. The scenario, which is just a few years away, would look something like this: One of the tires on the car ahead of you suddenly blows out. Radar in your car calculates a dra- matic and continuous reduction in the dis- tance to the next vehicle, wheel sensors de- termine that your car is starting to slide, the braking system works to eliminate loss of control, shoulder and seat belts tighten, a processor primes the air bag sensor for deployment, and the car’s GPS-based naviga- tion system transmits an emergency mes- sage that notifies downstream vehicles as to the location of your car and the need to reduce speed.
The successful coordination of these events not only relies on advanced sensors, actua- tors and high-speed processors, but also on the ability of all reliability-related systems to exchange information — in short, to function based on an open communication standard. That standard is now taking shape in the form of the Automotive Open System Architecture, otherwise known as AUTOSAR. In stark con- trast to the current automotive environment, AUTOSAR will set the stage for standardized interfaces for software components and oper- ating systems, thus enabling economical scal- ability and transferability of functions.
The need for an open standard for systems critical to vehicle dependability is growing for a number of reasons. Nose-diving memory chip costs and the resulting migration of func- tionalities from electromechanical devices to
Pictures of the Future | Fall 2005