Speeding development for voice applications with intelligent technology

14-04-2022 | NXP | New Technologies

NXP Semiconductors has launched Voice Intelligent Technology (VIT), the first comprehensive, local voice control software package and online training tools that are free for customers, regardless of end application production volumes. Based on advanced deep learning, it is a ready-to-use library that offers a far-field audio front end supporting up to three microphones, an always-on wake word engine, and a voice command engine. The company's free online tools allow customers to define a wake word and voice commands themselves, utilising simple text entry and with no need for voice recordings.

Implementing reliable, on-device voice control can be highly challenging. Developers not only need to select the appropriate hardware but also need to navigate complicated speech processing software. This frequently demands managing an audio front-end beamformer and a separate wake-word and voice command engine, often from different software vendors. VIT streamlines development by delivering a comprehensive, flexible software solution that may be customised for specific applications and includes all the elements required to develop 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."

Related product news