If you haven’t noticed, social robots are here to stay. There seems to be a new social robot introduced each month claiming to be the best on the block.

One of the keys to the success of these robots is how naturally they interact with humans, both verbally and non-verbally. Home robots, for example, could entertain your children or remind you to medicine or provide an educational experience. But if that interaction doesn’t feel natural for the human, it could discourage us from continuing to use these robots.

Making these interactions, especially conversations, is no easy task. Burlington, Mass.-based Nuance Communications has been working hard to perfect the art of human-robot conversations. Since 2013, Nuance has built the voice and conversational capabilities of the popular NAO and Pepper humanoid robots from Softbank Robotics.

There’s still a long way to go, Nuance will be the first to admit that, but the progress made in the last three years is remarkable. Nuance’s Kenn Harper, VP of Devices & Ecosystem, says the next steps to improving human-robot conversation include robots being able to adapt their personality based on who it’s speaking to and to use artificial intelligence and other contextual clues for automatic inference and reasoning.

Harper joined The Robotics Trends Show to discuss the keys to a flexible voice platform for robots and how to make conversations with robots seem as natural as possible. We also discuss the importance – and inevitable demise – of wake-up phrases, when we’ll be able to upload our voices and personalities into social robots, the need for the robotics industry to be more transparent with how voice data is used, and the need to create a social robot to argue with that contrarian friend in the group.

Subscribe to The Robotics Trends Show in iTunes, Google Play, SoundCloud and Stitcher so that you never miss an episode!