Duration: 24 months
Kickoff: Januar 2015
Virtual Voice Assistant for intelligent, context-sensitive speech dialogs.
The ZIM cooperation project's goal was to build a "virtual voice assistant for intelligent, context-sensitive speech dialogs". At the Innovation Day for SMEs 2019 on May 9 in Berlin, the project by the Heidelberg-based companies Aristech GmbH and sovanta AG was honored by the German Federal Ministry for Economic Affairs and Energy as the ZIM Cooperation Project of the Year.
The voice assistant enhances voice commands with linguistic algorithms to natural language phrases and thus enables voice control through a natural dialogue. Queries and input confirmations are requested by means of natural text-to-speech voices. The developed speech dialog platform is an innovation for the business sector. For example, field staff can use non-productive time, i.e. car journeys, to follow up on customer appointments directly and do not have to spend time in the office or on a laptop entering data into a system. Users can navigate applications and make entries via chat or voice. In HR, recurring employee inquiries can be answered more easily.
Industry and company-specific terminology can be integrated, and you can achieve greater efficiency by taking advantage of unproductive time. In addition, the speech technology platform can be used on all major mobile devices and operating systems, simplifying data maintenance and bypassing complicated and unpopular maintenance processes. Also, high recognition rates and natural speech interaction make it fun to use.
The Aristech GmbH was able to add a highly innovative, novel dialog platform to its existing product range based on the project. This provides it with clear unique selling points in the areas of IVR, voice assistance systems and artificial intelligence, among others.
Partner:
Sponsored by:
- ZIM - Zentrales Innovationsprogramm Mittelstand
- Federal Ministry for Economic Affairs and Climate Action
The ZIM publication on our project can be found as a German PDF online.