VODIS is the abreviation for 'Voice Operated Driving Information System'. The aim of the project is to develop a voice operated interface for the Blaupunkt Berlin RCM202A Navigation System.

The voice interface operates the navigation system, the GSM phone, CD Player and the radio. The group in Karlsruhe is responsible for the natural language understanding component and the data collection scenario. We are also involved in the HMI Specification, Speech Recoginition and Robust Phonetic Modeling.


Click on the image to get a closer view
The main objective of this leading-edge application project is to integrate and further develop the enabling technologies required for the design and implementation of voice-operated human machine-interfaces (HMI) for applications inside the automobile.

The goal of such a vocal interface is to enhance both the usability and functionality of newly developed driver assistance-and information systems (or services) in the sense that it facilitates the access to the information provided, due to the fact that spoken language is the most natural form of human interaction. At the same time, it is expected that such devices contribute to increase the road transport safety, since the driver's attention is not longer distracted by complex tactile and visual interfaces.

The BERLIN RCM303A

In order to address actual needs, the work will be focused on the voice-operation of a commercially available state-of-the-art driver information system, namely the BERLIN RCM303A from Bosch, that presently integrates a route guidance (navigation) computer, traffic-messaging (RDS/TMC) , mobile telephone (GSM) and more conventional equipment as car radio and audio/video entertainment sources, thus demanding a high amount of driver interaction, both for command-and-control functions and database queries. An example of the latter is the process of entering the name of the city and the particular location (street, public building, etc.) a driver needs to be guided to. However, the speech technologies and evaluation methods developed within the project are of generic nature and can be used for a multiplicity of systems and services beyond the particular application, not only in the automobile but also in other acoustically hostile scenarios.

Research Topics

  • noisy acoustic environment
    Given the noisy acoustical environment inherent to the driving scenario and the noise-sensitiveness of phonetically-based recognizers, considerable effort will be devoted to the speech signal enhancement, acoustic echo cancelling and noise reduction algorithms are needed.

  • recognition
    From the recognition point of view, the work concentrates on continuous word systems, to be demonstrated in a car-environment for the first time. Effort on phonetic modeling, finite-state grammars and keyword-spotting is required therefore. Special interest will be devoted to the open vocabulary problem. To accommodate to the needs of a significant group of potential users, the recogniser development will take recently developed rules for non-native-speaker pronunciation, especially of geographical and proper names into account.

  • natural language
    The component requires very large task-oriented speech corpora to be collected for both languages (french and german).

  • human machine unterface
    To yield an ergonomically adapted HMI, input modules have to be developed under the constraint that speech output capability is available, thus allowing for a certain amount of clarification dialogues. A dialogue management module is to structure the interaction with the user in accordance to the limitations of the recognition modules and the language generation unit. The output speech signals are synthesised by a state-of-the-art text-to-speech system.

The Main Benefit

The main benefit for the driver community as the target users of the present application is the easier and human friendlier access to the information provided by present and future IT-systems in the automobile. With this kind of HMIs even elder people or those maintaining a sceptical attitude towards modern technologies will be able to benefit from the new services offered. In this sense, vocal HMIs will support different EU-policies as Mobility in Europe (e.g. by multilingual voice-operation of route guidance systems) , the Information Society (e.g. by vocal queries to GSM-accessible databases while underway) and Environmental Protection (e.g. by easy-to-access Traffic Management Information). Further benefits for the users are an enhanced road transportation safety and an improved driving comfort.

KEYWORDS natural language modeling, continuous speech recogintion, navigation system, human machine interface
to topback to top
Site maintained by:
Céline Morel