Based on advanced deep learning, VIT is a ready-to-use library that provides a far-field audio front end supporting up to three microphones, an always-on wake word engine, and a voice command engine.
Free online tools will help customers to define a wake word and voice commands themselves, using simple text entry and without the need for voice recordings.
The implementation of reliable, on-device voice control can be extremely challenging as developers not only need to select the appropriate hardware but have to navigate complicated speech processing software. This frequently requires managing an audio front-end beamformer, as well as a separate wake-word and voice command engine, often from separate software vendors.
VIT streamlines development by providing a comprehensive, flexible software solution that can be customised for specific applications and incorporates all the elements needed to create a highly accurate, on-device voice control solution.
“Voice is the interface of choice for many smart technologies, including those in smart homes, smart cities and smart factories,” said Joe Yu, Vice President and General Manager, IoT Edge Processing Product Line, NXP. “By reducing the complexity of voice application development, we’ve made it easier and faster to bring new, on-device voice control to market.”
The VIT library is delivered as a ready-to-use library in the MCUXpresso SDK and the online training tool is available from the NXP website.