Linguatronic
Product-Level Speech System for Mercedes-Benz Cars
Paul Heisterkamp
DaimlerChrysler AG
Research and Technology
Speech Understanding
Wilhelm-Runge-Str. 11, D-89081 Ulm, Germany
Tel. +49 731 505 2152
Paul.Heisterkamp@DaimlerChrysler.com  
1. INTRODUCTION
A recent press release (Murray 2000) indicates that many car
manufacturers have announced speech recognition and voice-
operated Command&Control systems for their cars, but so far
have not introduced any. They are still struggling with
technology, both in reliability and pricing. The article finishes by
a quote from an industry person saying:
"The reality is that today’s systems are still failing
in a lot of different modes. [...] But the technology will
get better before it reaches the market. Right now, we
just don’t know when that will be."
In the light of this statement, we consider it appropriate in the
context of a scientific conference, to draw the attention of the
speech and language community to the fact that in-car speech is
on the market, and successfully so, since fall 1996 in Germany
and since May 1999 in the USA.
2. LINGUATRONIC
In the S-Class car of 1996, Mercedes-Benz introduced the first
generation of Linguatronic. Linguatronic is the brand name used
in Europe of a speech dialogue system that allows completely
hands-free operation of the car’s mobile phone, including number
dialing (with connected digit dialog), number storing, user-
defined telephone directory entry name, name dialing, and
directory editing. Linguatronic I has a vocabulary of about 30
speaker-independent words (digits and control words). The
second version has a vocabulary of about 300 words, and, in
addition, allows for operation of comfort electronics (radio, CD-
player/changer, air condition etc). The system is now available for
German, US English, UK English, Italian, Spanish, French and
Swiss-German. Japanese and Dutch are currently under
development.
3. ORGANIZATION
The basic algorithms incorporated in Linguatronic are developed
by the Speech Understanding group of DaimlerChrysler Research
and Technology in Ulm, Germany. These algorithms then are
taken up by the Speech Processing Division of DaimlerChrysler’s
TEMIC business unit and put into products. These products are
first marketed exclusively to the Mercedes-Benz premium brand
of DaimlerChrysler, but in time, they are available to other brands
and manufacturers as well. This reflects the Mercedes-Benz
philosophy that safety-enhancing technology should be deployed
by everybody. Thus, the speech technology from Temic is
currently also available in BMW’s and Audi’s, with other car
makers and suppliers to follow shortly with their top products..
4. TECHNOLOGY
The recognizer used in Linguatronic is speaker independent
HMM-based. For the user definable telephone directory, an
additional DTW recognizer is used. A key issue for speech
technology in the car, noise reduction, is achieved by an
integrated signal pre-processing that reduces the influence of
noise and other sources of interference to improve the quality of
the  recognition. Furthermore, the system automatically and
imperceptibly adapts itself to the characteristics of the speaker's
voice or the acoustic background within vehicles. So, the key
technology features are:
• Noise Robustness
• Echo Cancellation for hands-free telephone applications
• Continuous speaker independent speech recognition
• Speaker dependent recognition
• Active vocabulary of about 300 words
• Background adaptation
• Dynamically loadable vocabulary
Now, from the recognizer side, that doesn’t seem too much
different to what other speech companies and research groups
offer. Yet, recognition accuracy is at a very high level. What is it,
then, that makes the difference? Obviously, training of speech
data plays a major role here, but others (e.g. the SpeechDat-Car
project) have done major data gathering exercises as well. So,
we’ll point here to some items that are not naturally in the focus
of the scientific community, viz. integration, co-operation and
engineering.
5. INTEGRATION
All upper-level cars of the major European makers these days are
equipped with a data bus system, sometimes still over copper
wire, but mostly using fiber optics. The Temic system supports the
most common automotive bus systems like D2B, CAN, I-Bus and
in the near future MOST. This means that a multitude of devices
on the bus can be addressed and operated using a single and uni-
form speech dialogue module, and there is no need to put extra
wiring in the car. Furthermore, the push-to-activate (PTA) button,
muting of the audio and use of the car’s loudspeakers are
facilitated, and, very important, the same microphone can be used
for both speech commands and telephone. The quality of the
microphone (or an array), its characteristics and its positioning are
extremely important.
6. CO-OPERATION
This kind of close integration can only be achieved in an equally
close co-operation with the car manufacturer. The speech
Command&Control has to fit smoothly into the overall human-
machine-interface for the driver. From the position of the PTA
button or lever, via the cancellation function to the analogous
behavior of speech and tactile operation of devices, everything has
to be done to ensure that speech is an integrated and natural part
of the interaction. Fallback modes must be made available in case
speech fails. The auto maker must also be aware that even if
recognition were one-hundred-percent accurate, people do not
always say what they mean or know what they can say, so there
will be failures.
7. ENGINEERING
And, of course, the car manufacturer also knows which price
people are willing to pay. The key issue now is the engineering
task to deliver a product with a certain quality standard for a
certain price. Besides software solutions, Temic currently offers
two harware versions of its Command&Control system for cars,
one as a plug-in board the size of a credit card, the other as a self-
contained box that interfaces directly to the bus and does not
require any host processor. Both not only do the recognition, but
also store the speech output for the dialogue. And: at a
recognition rate that convinced not only Mercedes-Benz, but also
others who have a reputation for quality, Linguatronic, under the
label ‘voice recognition’ sells in the US as part of a mobile phone
package for a retail price of $480.00; the majority of integrated
phones in Mercedes-Benz cars in the US is ordered with this
option. Up to the end of the year 2000, Temic has sold more than
170,000 units for automotive applications..
8. OUTLOOK
The scientific community is well aware that speech in cars is the
enabling technology to interactively and selectively bring news
and information to mobile environments without causing a safety
hazard (cf., e.g. ElBoghdady 2000). Yet, we all have seen tides of
enthusiasm and reluctance towards the real-life viability of speech
technology. With telephony applications now firmly established,
any discussion as to whether speech technology is a commercially
viable option also for use in vehicles can be abbreviated by
pointing at the Linguatronic example. Speech technology is there,
and it will grow. More auto makers, but also system-providers like
Bosch will soon be out with more complex applications,
navigation address entry being the point in question, more cars
will have speech control as an option, and, in our area of research,
we are pushing the limits of what can be done in research projects
both internal and co-operative, e.g. in the DARPA Communicator.
9. REFERENCES
[1] ElBoghdady, Dina (2000): Feds fear high-tech car gear.
Detnews.com, 23 January 2000.
[2] Images thanks to http://www.temic.com/speech
[3] Murray, Charles J. (2000): Automakers struggle with
speech recognition technology (03 December 2000).
http://www.eet.com/story/industry/systems_and_softwa
re_news/OEG20001201S0109
