VoiceDrive

An automotive infotainment system to say what you want and get what you need

VoiceDrive is a concept prototype of an automotive infotainment system, which explores interactions with Natural Language Processing, and Speech Recognition from the purview of Design and Human Factors. Comprehensive research was carried out to outline the advantages and drawbacks of Speech Recognition, how it is implemented in the automotive environment, how it has grown and its future in the domain. The research is an investigation on the possible feedback mechanisms the car might give if being interacted with predominantly by speech, and explorations in diminishing the dependencies of humans on a visual interface.

Multiple prototypes were created using various tools, to simulate and understand Voice Recognition and its Human Factors. The interface works mostly around clearly labelled buttons which also act as visual queues to reduce the learning curve with new users, to slowly try to reduce dependency on the screen, so the user can pay attention to the road ahead, in comfort.

Further, breaking away from the strictly closed and guide-lined realm of embedded automotive HMI design, VoiceDrive proposes a new, more open ecosystem, To allow 3rd party developers and other players to co-create newer applications in the Automotive Space accessing some of 150+ sensors on board.

The final prototype was implemented on Android, with a custom Keyword based algorithm, built on the Google Voice API. This project was done at Tata Elxsi, as my Undergraduate Thesis.




Year

  • 2012

Team

  • Nick Talbot (Mentor), Satish Patil (Mentor), Madhavan Ayyavu (Android Development Help), Me

Role

  • Research, Concept Design, Development

Medium

  • Interactive Prototypes:Initial prototype was created using VVVV, with Microsoft Speech to text application. Final prototype was an Android Application created using Google Voice APIs.
  • Project Book: Printed Book detailing the process and concept.