Beeld: NXP
Author profile picture

Imagine being able to talk to your devices as if they were your best friend. You can simply say, “Turn up the heat” or “Turn off the lights” without having to remember specific commands or wait for a cloud connection. This is what NXP Semiconductors is promising with their new VIT Speech to Intent engine. With this launch, NXP Semiconductors is taking an important step toward a future where our interaction with technology becomes more human, intuitive, and seamless.

  • VIT Speech to Intent engine is a local speech control system;
  • it uses edge computing for natural language understanding;
  • The technology enables seamless interaction with smart devices.

The new era of interacting with smart devices

The VIT Speech to Intent engine is designed to match the performance of cloud-based systems but without the need for a cloud connection. This delivers not only improved user privacy but also lower latency, reduced power consumption, and reduced costs.

Part of NXP’s Voice Intelligent Technology (VIT) software suite, VIT Speech to Intent enables people to speak naturally to smart machines in IoT, industrial, and automotive applications, rather than memorizing precise commands or phrases to control the devices.

The potential of natural language understanding

Natural language understanding, provided by VIT Speech to Intent, enables devices to understand users’ intent without the need for precise formulation or cloud connectivity. This opens up new opportunities for innovation, especially in the smart home and in places where users’ hands may not be free, such as hospitals or factory floors.

Rafael Sotomayor, Executive Vice President and General Manager, Secure Connected Edge, NXP, says that VIT Speech to Intent enables people to communicate seamlessly with smart devices without having to rely on specific keywords. This provides convenience and ease of use, reduces complexity, and alleviates user frustration.

From smart home to autonomous home

VIT Speech to Intent can be used to support natural speech interfaces with a wide range of applications, including smart watches, smart HVAC, and more. This represents another step in the transition from a smart home to an autonomous home. The system currently supports interactions in English, with support for Mandarin coming later this year. Further support is planned for Spanish, German, Korean, French, and Japanese in 2024.