The Latest Voice-operated Control System of the Mercedes-Benz S-Class
The Mercedes-Benz S-Class "LINGUATRONIC" team.
Claire Ashworth provides the "English" voice for the|
Mercedes-Benz S-Class LINGUATRONIC system.
1st September, 2009
- Whole-word destination input improved even further
- Voice recognition: analysis within milliseconds
- Each language has its own voice
- Professional speakers as dialogue partners and guides
- The Mercedes voices can also be heard on TV and radio
The latest generation of the LINGUATRONIC voice-operated control system is entering series production with the 2009
Mercedes-Benz S-Class. And the cast behind the commands has been revealed.
Instead of saying the town and street separately as before, drivers can speak the desired destination as a single
command - for example "Stuttgart, Epelstrasse". The system immediately begins to work out the route, only pausing
to enquire whether a house number is to be entered as well.
In Germany, for example, LINGUATRONIC understands around 80,000 town names and 470,000 street names entered in this
way. This new, particularly convenient destination input works in six languages and more than 15 European countries.
A dialogue with LINGUATRONIC is practically a person-to-person affair. Around a dozen female speakers and one male
speaker lent their voices to the S-Class, recording the individual words, phrases, numerical sequences and names which
the system almost instantly joins together into easily understood information and instructions as the situation
requires when interacting with the driver. The "voices of the S-Class" come from various European countries, where the
ladies - and one gentleman – concerned work for radio and TV stations or synchronising studios.
Scientists spent more than two decades working on the development of a computer-based voice recognition system. In
1996 Mercedes-Benz was the first automobile brand to offer such a system in a car - though initially only to operate
the onboard telephone.
Voice-operated control has come on in leaps and bounds since then: the times when town and street names had to be
spelled out are long gone. When controlling the telephone, audio and navigation system, the latest version of
LINGUATRONIC, which Mercedes-Benz offers in various model series, works on the principle of whole-word input.
In the case of the S-Class, Mercedes engineers use the term "one-shot input" to describe the currently most
advanced development stage of the system, where the town and street names can be spoken as a direct sequence.
This new procedure currently works for the following languages and countries:
- German: Germany, Austria and Switzerland
- English: Great Britain, Gibraltar and Ireland
- Spanish: Spain
- French: France, Monaco, Belgium and Switzerland
- Italian: Italy, San Marino, and Switzerland
- Dutch: Netherlands, Belgium
Voice-operated control is not just about understanding the driver's wishes, but also about entering a dialogue with
them. The system responds in a friendly voice if it has failed to understand something, for example, or if it wants the
driver to confirm certain operating commands.
While it would be perfectly possible to generate these voices synthetically – that is, by computer - Mercedes-Benz
holds a low opinion of such "lifeless" announcements, preferring a person-to-person dialogue for its voice-operated
Mercedes-Benz and its system partners have contracted professional female speakers and one male speaker who lend
their voices to the voice-operated control and navigation systems of Mercedes models. For each language, it takes three
days to record the words, phrases, numerical sequences and names written on around 100 manuscript pages as the basis
for the route guidance and voice operation dialogue.
The system joins thousands of individual recordings together for the dialogue
During the recording work in the studio, each of the well-over 1,000 "takes" is individually saved and encoded, so
that the computer is rapidly able to access the relevant command rapidly as the situation requires, adding other
information to it if necessary. It is therefore important for the speakers to use the same intonation throughout, so
that the information sounds immediate and natural when the system formulates its responses from various acoustic
fragments, for example, telling the driver where to turn off, which lane to take and which road to choose.
The navigation system "speaks" more than a dozen languages
The specialists at the Mercedes development centre make a fundamental distinction between the voice-operated
controls with which the car obeys its driver's every word, so to speak, and the language information used for route
guidance. The navigation system in the S-Class "speaks" more than a dozen languages, which are available in the
different national versions of the unit. These include Danish, German, English, Spanish, French, Italian, Dutch,
Portuguese, Turkish, Russian, American-English, Japanese and Chinese.
When it comes to interacting with drivers and giving them directions, Mercedes-Benz primarily uses female voices.
The only exception is Turkey, where drivers prefer to receive directions from a male voice.
The "voices of the S-Class" also work for radio stations, synchronise films, do voiceovers for advertising spots,
read talking books and perform in theatres.
Voice-operated control technology: From spelled-out words to direct input
To ensure that the LINGUATRONIC voice-operated control system obeys the driver's every word, it was subjected to a
highly involved learning process during its development. It was then tested in all the languages, and by Mercedes
customers in all language regions.
It is very important for LINGUATRONIC not only to understand every word, but also every male or female driver.
Every person has his or her own pronunciation, tone and individual speech cadences. To make the dialogue perfect, the
Mercedes system offers an "after-training" function: a personal conversation with Ms Ashworth or one of her colleagues,
during which the driver can individually adapt the voice recognition to the sound of his/her voice and intonation.
Around ten years ago, drivers were only able to operate the onboard telephone with voice commands. Since 2000
LINGUATRONIC has been capable of more, and now controls the car radio and CD-changer as well. Since 2002 the
Mercedes-Benz navigation system has also been optionally controllable by the voice recognition system. The
first-generation system only required a processor with a memory capacity of 512 kilobytes, but more than ten megabytes
are necessary nowadays.
For some time drivers were obliged to enter the destination by spelling out the town and street names. This changed
in 2002, in the E- and S-Class, where it was now possible to input around 650 place names in Germany by whole-word
voice command. Nowadays LINGUATRONIC not only understands all town and street names when destinations are entered, but
also whole words when selecting a radio station or names from the personal telephone directory. The driver only needs
to say the destination, whereupon the system searches its electronic memory for the relevant town and street. If there
are several similar-sounding names, the display shows a selection.
Destination input: the driver says the town and street names directly in sequence
In the new-generation S-Class, due for release in Australia this October, Mercedes engineers have improved the
whole-word voice input function even further. They call this new development a "one-shot" function, and it makes
voice-operated control even easier and faster. After speaking the command "Enter destination", the driver says the
desired destination as a single command - for example "Stuttgart, Epplestrasse". The system immediately begins to
work out the route, only pausing to enquire whether a house number is to be entered as well. There is then a verbal
acknowledgement: "Stuttgart, Epplestrasse confirmed. Route guidance starting now."
The largest active vocabulary is to be found in the LINGUATRONIC system of Mercedes models in the US state of
California, where whole-word input of around 220,000 street names is possible. In Germany around 80,000 towns and
more than 470,000 street names can be input by voice command.
LINGUATRONIC is a major Mercedes-Benz contribution to road safety, as drivers no longer need to take their hands
off the wheel to operate the car phone or audio equipment. They are therefore better able to concentrate on the
Mercedes-Benz also uses speech synthesis technology to read out important traffic information affecting the
route, or SMS messages.
Voice recognition: LINGUATRONIC "listens" for phonemes
During the brief dialogue between the driver and LINGUATRONIC, the sound signal is digitised, converted into a
frequency range and finally analysed. Within milliseconds, the computer extracts various characteristics from the
speech signal in order to recognise what are known as ‘phonemes’. To the linguistic scientist these are the
smallest sound components of a language, and they are decisive for understanding the words. The control system is
able to recognise words by combining the phonemes and comparing the result with the contents of a phoneme dictionary
stored in memory. Each language has its own, typical phonemes; LINGUATRONIC uses around 40 for the German language.
LINGUATRONIC processes the phonemes as digital codes. The electronics instantly check each sound, join the different
phonemes together and also verify the acoustic probability of the word.
So that even fine nuances in pronunciation are recognised reliably, Mercedes engineers have interposed a special
background noise suppression feature. This enables voice commands to be well recognised even at higher speeds. Up to
a certain speed, this means that LINGUATRONIC even works when the roof of a cabriolet or roadster model is open.
The voices of the Mercedes-Benz S-Class
Around one dozen female speakers – and one male – guide Mercedes drivers to their destinations.
Their voices are heard from the loudspeakers during dialogues with the voice-operated control system, and when the
navigation system gives its route instructions. Every major language has its own voice at Mercedes-Benz - and English
even has two, to distinguish between British and American pronunciation.
Turkey is another exception. Though Mercedes customers almost everywhere in the world are happy to receive their
route instructions from a female voice, Turkish drivers prefer the voice to be male.
Turkish: Selçuk Birdal
Selçuk studied drama as well as training as a speaker, therefore he is not only employed as a radio presenter in
his native country, but also for synchronised cinema films and TV series. At first he was surprised to be the only
male in the Mercedes voice team, but he certainly has no objection. On the contrary: "Having so many nice female
colleagues is a lot of fun."
Cristina Mambretti is a young Italian. As a trained singer, she is currently making a name for herself in the
Italian classical music and jazz scene. She sings with Eric van Aro, the son of Caterina Valente, on the new album
"Desert Motel", has appeared at the Montreux Jazz Festival with the Swiss artist Marco Cortesi, and recently showed on
regional TV in northern Italy that she not only has a voice, but also acting talent. Around four years ago she was
selected as a speaker for the Mercedes navigation system and the voice-operated control system of the S-Class. "I took
part in the auditions and was chosen from a large number of applicants – according to the motto: "Italy is looking for
the Mercedes voice", she recalls.
Spanish: Zoraya López
In addition to her profession as a speaker, Zoraya López has two great passions: drama and dance. When she is not
sitting at the microphone in a sound studio recording voiceovers for films or safety announcements for airline
companies, she works as a dance teacher. Born in Spain, she has even taken specialist training as a teacher of
oriental dance, and is therefore an expert bellydancer.
Zoraya López came to Germany 30 years ago, and now lives in Berlin. Which is why she has a special language talent:
in addition to perfect German she is able to deliver German with a Spanish accent or Spanish with a German accent. She
has already demonstrated this versatility on TV.
German: Gabriele Libbach
Ornella Muti and Lara Croft are two famous names in the biography of Gabriele Libbach. Now living in Hamburg, she
has given both screen entertainers their German voices on several occasions.
Since the market launch of the C-Class in 2007, the pleasant, friendly voice of Gabriele Libbach has been heard on
board all new Mercedes passenger cars equipped with an ex-factory navigation system. This means that day-after-day,
many hundreds of thousands of drivers trust her to guide them to their destinations. In the voice-operated control
system which Mercedes-Benz includes as standard with the current Audio 50 APS and COMAND APS systems, German-speaking
drivers likewise 'chat' with Gabriele Libbach.
Hanover-born Gabriele Libbach already began her career as a professional speaker as a teenager. "I was twelve years
old, and mainly did synchronised voiceovers for boys' voices – somehow that suited me well."
Later she was commissioned for classic radio plays, and also synchronised a supporting role on TV.
Compared to roles like this, navigation instructions such as "Left turn ahead" or "Please take the centre lane" are a
complete linguistic contrast for this trained teacher. "But that is what I like about this profession – there are always
new and interesting jobs to do", she says.
Danish: Jette Sieversten, the Shakespearean actress
Jette Sophie Sievertsen from Copenhagen beat more than 20 other candidates in the auditions, and was chosen as the
Mercedes speaker for Danish. Until the mid-80s she performed in plays by Shakespeare and Molière, then appeared in
various films and TV series.
She has also demonstrated her acting and linguistic versatility in the synchronisation studio, where she has lent her
voice to the well-known film "The Lion King".
Dutch: Constanze Kamps guides visitors through museums and exhibitions
"Zegt de plaats en de straat." A driver hearing this request from the loudspeakers of the S-Class, and entering the
desired destination, is talking to Constanze Kamps. She comes from the Netherlands, but worked in Cologne for many years
in editorial offices. Today Constanze Kamps is a sought-after speaker for advertising and industrial films by well-known
companies, and also records for the audio-guides used by visitors to museums and exhibitions. "A very interesting job",
she says. "I learn an awful lot when doing this."
Portuguese: Fátima de Oliveira Baptista used to present TV shows
Radio was also the professional home of Maria de Fátima de Oliveira Baptista.
She presented her own shows on Portuguese radio for around 17 years, and also appeared in TV shows as a presenter. She
is now self-employed, has homes in Lisbon and Washington and organises PR events and shows on behalf of her clients. She
was discovered as a Mercedes voice via the Internet: her web site has a number of sample speech clips which the
developers of the navigation system found particularly attractive. So she was invited to Stuttgart to speak the Portuguese
texts for the COMAND system.
Russian: Margarita Kalz broadcasts on short wave
Anybody wanting to hear Margarita Kalz must switch to short wave and tune in to the Russian programme broadcast by
Deutsche Welle. This is where she presents news programmes, music and lifestyle magazines which are popular in Russia,
White Russia and the Caucasus region.
"We present information about Germany", says Moscow-born Margarita Kalz.
"We broadcast news and background reports in Russian, report on the German show business and celebrity scene, and
play current popular music. This means 14 hours of programmes every day."
Margarita Kalz was no stranger to the studio even before moving to Cologne, as she used to work as a news presenter
for a Russian TV station and was on-screen almost every day. She has a simple explanation for the success of
Mercedes-Benz in her home country, and she presents it with typical Russian humour: "Those are all my fans and friends.
They buy the cars because they want to hear my voice again."
Chinese: Zhang Danhong works for the radio
At Deutsche Welle, Margarita Kalz practically works next door to Zhang Danhong, who is likewise employed there as an
editor. Zhang Danhong studied German in Beijing, and came to Germany 20 years ago to continue her studies at the
University of Cologne. Deutsche Welle was looking for China specialists, so her career as a radio journalist began.
Today the 43 year-old is the Mercedes voice that guides Chinese drivers to their destinations.
"We made the first recordings for the navigation system just over three years ago", recalls Zhang Danhong, who
was pleased to be given the task.
"Previously there were only English-language instructions in navigation systems. The fact that Mercedes has
developed a separate version for China shows how important this market has become."
French: Christine Ott was a dancer in Paris
Christine Ott has a lot to tell when talking about her life and professional career. The latter began in 1977, in
Paris, where she appeared on stage.
In 1982 this helped her to secure a position in the famous Reinhild Hoffmann dance theatre, which initially performed
in Bremen, then in Bochum until 1995. This was where her voice was also discovered, and Christine Ott began a second
career as a speaker which led her to Mercedes-Benz in 1999.
"I enjoy working in the sound studio, although it is often harder than one thinks because the texts always have to
be spoken and repeated with the same intonation. This takes a lot of discipline – and this is where my dance and drama
training stands me in good stead", says the Paris-born Mercedes voice, who now lives in the Ruhr region.
English: Claire Ashworth - Working for a bank in London
Claire Ashworth is the "natural talent" among the voices of the S-Class. She has no training as a speaker, and has
never been an actress or radio presenter. In fact this Englishwoman comes from a quite different sector, as a she is a
team leader for a large bank in the City of London. A banker with a beautiful voice?
"Well, I suppose so," she says. "At any rate I was chosen from quite a number of other candidates, and
offered this interesting part-time job."
Two to three times each year, Claire Ashworth leaves her workplace by the Thames for a few days and flies to
Stuttgart to record new takes for the navigation and voice-operated control system.
"My parents always insisted that I speak clearly, with no regional accent. Now this is obviously paying off",
says Claire Ashworth, though she admits that making the recordings can sometimes be very tiring.
"Everything must always be said in an absolutely neutral way, with as little emphasis as possible – completely
Sound technology: driving to the sound of beautiful voices
These and many other subtleties during the recording sessions for LINGUATRONIC and the navigation system are watched
over by sound engineer Peter Hardt from Jankowski Soundfabrik in Esslingen. He has done this job for Mercedes-Benz for
many years, and knows exactly what is required.
"The most important rule is to speak with the same intonation all the time, for in the car the system almost
instantly assembles the individual words, phrases, letters or numbers into the route guidance instructions and
information", Peter Hardt explains.
During the recording work, each of the thousands of "takes" is individually saved and encoded, so that the COMAND
system's computer is rapidly able to access the relevant command rapidly as the situation requires, adding other
information to it if necessary. Peter Hardt: "The end result has to sound immediate and natural – as if the speaker
were sitting in the car, next to the driver."