by Angela Guess

A new press release states, “Nuance Communications, Inc. today announced that ROOBO will be leveraging the Nuance Mix NLU development platform, which provides voice and natural language (NLU) capabilities, to create conversational and cognitive interfaces for ROOBO robots and devices. Additionally, Nuance and ROOBO will be collaborating on future integrations of advanced Artificial Intelligence (AI) to advance conversational interfaces for intelligent IoT devices. ROOBO’s current integration of Nuance’s voice capabilities will be showcased at the China Hi-Tech Fair in Shenzhen. Based in Beijing, China, ROOBO is a global platform for the incubation and distribution of intelligent hardware and software through open platforms for AI and robotics, including the recently launched Domgy and Pudding consumer robots. These robots integrate Nuance’s voice recognition, NLU and text-to-speech – giving them the ability to listen, understand and respond, and ultimately create a more human connection through a conversational interface.”

The release goes on, “ROOBO will initially integrate Nuance Mix as part of its open robotics and AI platforms, providing developers with access to voice recognition, NLU, text–to-speech, wake-up word, voice biometrics and signal enhancement capabilities – making possible a customizable end-to-end conversational interface. Nuance Mix leverages AI to enable ROOBO apps and services to quickly and easily understand inquiries and deliver outcomes, be it information, content or task completion. Nuance Mix gives ROOBO and its developer ecosystem the ability to create customized language models that provide a domain-specific conversational interface – because no two robots will be the same. The language and needs of an educational robot are very different from the needs of a smart home personal robot. Through Deep Learning and data-driven AI, Nuance Mix gives robots the ability to quickly expand their vocabulary and their breadth of understanding – learning along the way just as humans do through the application of both speech and contextual data.”

Read more at Business Wire.

Photo credit: Nuance