Nuance Adds Speech to Aldebaran's NAO Robots

Aldebaran Robotics will integrate conversational voice capabilities from Nuance Communications into its NAO humanoid robots, which are also equipped with motion, vision, tactile, and audio capabilities.

NAO measures in at just a little less than two feet tall and can walk, track and recognize faces and objects, express and understand emotions, react to touch, and interact by voice. It has an active sensor network that includes two cameras, four microphones, a sonar rangefinder, two IR emitters and receivers, an inertial board, nine tactile sensors, and eight pressure sensors, as well as various communication devices, including the Nuance voice synthesizer and speech recognition engines, LED lights, and two high-fidelity speakers.

Today more than 5,000 NAOs are in use throughout the world as research and educational tools in 70 countries.

Aldebaran, which is based in Paris, will take advantage of Nuance's cloud-based voice recognition and expressive text-to-speech through Nuance's NDEV developer program. Combined, these technologies allow people to have truly natural conversations with the robot in 19 languages. Further, NAO robots will become even more personalized through a custom text-to-speech voice that was specifically developed to match the robot's personality. NAO robots featuring Nuance's Natural Language Understanding and text-to-speech will ship in early 2014.

Steve Chambers, president of sales and marketing and an executive vice president at Nuance, says Nuance's speech recognition and text-to-speech technologies will help NAO "listen and speak better, to make the overall experience better."

Nuance, Chambers said in a video on the company's Web site, moves with "a sense of pride that our technology is going to fulfill part of [Aldebaran CEO and founder Bruno Maisonnier's] vision, which is more natural, emotive, and personal interaction.

"By working with Aldebaran, we're creating unique and compelling possibilities in the space of robotics, where people can connect with NAO as if they were connecting with another human being, and that's simply powerful," Chambers said.

Another element of NAO's development has been aligning changes in voice and body gestures with the spoken dialogue. According to Maisonnier, that involves "emotional intelligence rather than artificial intelligence."

"Interaction is at the core of what people do with these robots," he said in the video. "Communication is not just with the voice but with the emotions and body language."

This expressivity, he says, is a very important part of NAO's programming. "Developing natural, conversational interactions with humanoid robots is a challenging and pioneering area of robotics. Our robots have to express and understand emotions, and for this, there needs to be expression in their voice that speaks to their personality, and matches their body language," Maisonnier said at a recent Nuance event. "Nuance and Aldebaran have combined our voice and robotics innovations to showcase what's possible for human-robot communication. Our vision is to create even more intuitive and human-like interactions between man and machine as part of the NAO experience, in turn creating a wealth of new application opportunities for NAO and the next generation of robotic companions."

The purpose, he points out, though, "is not to mimic another person," but just to improve the quality of the human-robot interaction.

"As we move into an exciting new era where robot companions will partner and collaborate with humans in all sorts of helpful societal roles, conversational voice interaction will be critical to their ultimate success and adoption," says adds Fatima Vital, director of automotive marketing at Nuance. "As it has with devices, applications, services, and systems, Nuance looks forward to being an integral part in this latest advancement in the relationship between people and technology."