Sensory's VoiceHub Aims to Simplify the Development of Custom Wake Word and Voice Command Systems
Claims its free tools allow for development "in minutes" and can scale from wearable platforms all the way to high-power edge AI appliances.
Silicon Valley edge AI specialist Sensory has announced the launch of VoiceHub, a platform via which it aims to ease the development of voice-enabled products and services — building custom wake word and voice control models, it claims, in mere minutes.
"Sensory applied decades of experience and lessons learned with shallow net technologies to create its highly accurate machine learning models, which are trained with a mix of real and probabilistically-derived synthetic data," says Todd Mozer, Sensory chief executive, of the TrulyHandsfree technology driving the platform. “VoiceHub benefits from all of this work and removes any friction related to developing voice UIs for testing purposes.
"Furthermore, our VoiceHub models set the bar very high for accuracy and overall performance. We are excited to share these tools and capabilities with the speech tech community and beyond and believe VoiceHub will serve as a catalyst for rapidly accelerated innovation of new voice-enabled experiences."
The free VoiceHub tools, Sensor claims, allow users to create custom wake-word and voice-command sets for any applications within minutes; training of the models then takes place on the Sensory servers, with the trained models available for download in a matter of hours. These models can then be used with a companion Android application for rapid prototyping, or downloaded as code for specific digital signal processors 9DSPs) — targeting everything from ultra-low-power wearable platforms to high-performance edge AI appliances.
VoiceHub is now available upon application on the Sensory website.