News Column

Fujitsu Ten Rolls Out English-Version Prototype of 'Interactive Voice-Recognition Car Navigation Unit' with Smartphone Linkage

February 20, 2014

Fujitsu Ten Limited, developer of the "Eclipse" car navigation brand, has developed a prototype model of the English version of the "Interactive Voice-Recognition Car Navigation Unit" that performs searches through connection with the center server by utilizing a specialized smartphone application (voice-recognition agent application).

According to a release, users can speak using normal natural language and search results are returned vocally, allowing the destination to be set in this manner with no other actions. Users can add conditions while conversing with the unit, which understands the context and updates the search accordingly. Since the information a user wants to know is narrowed down simply by vocal interaction, the need to move one's line of sight to check the screen display is reduced, thereby contributing to safer driving.This prototype will be displayed as a part of the Fujitsu Limited booth at the "The 2014 GSMA Mobile World Congress", a mobile phone-related trade exhibition to be held from February 24 to 27, at Fira Gran Via in Barcelona, Spain.

A car navigation providing this same type of search by voice interaction has already been released in Japan under the Eclipse brand. Through the exhibition of this prototype, Fujitsu Ten is striving to catch up with the needs of global customers, and the company plans to continue to study and develop products aimed at worldwide commercialization while keeping an eye on consumer demand and similar trends.

By speaking into a specialized car-navigation microphone, users can search for facilities or weather information and receive answers vocally through the car-mounted speakers. All processing required for voice interaction is performed at the center server in order to provide the following features.

-To execute the extraction of the speech section required as a pretreatment of speech recognition and the noise cancellation specific to in-vehicle environment, with high accuracy

-The speech recognition in natural speech utilizing a huge amount of recognition dictionary database

-To estimate the speech contents and the intent of the speaker by use of the advanced understanding capability and an inference engine

-To execute the processing corresponding to the request from the speaker by use of various contents as well as the latest and real- time information

-To send back the execution result and the search result by natural speech, using a huge amount of speech dictionary database

Voice recognition, meaning understanding, and speech synthesis analysis use an external platform.

((Comments on this story may be sent to

For more stories covering the world of technology, please see HispanicBusiness' Tech Channel

Source: Manufacturing Close - Up

Story Tools