Why VAD and what to choose?
Introduction
Nowadays, focusing on power consumption is crucial during battery operating SoC development. Voice activity detection (VAD) is key feature to drastically reduce power consumption in a voice user interface (VUI) application. VAD’s primary aim is to reduce power usage by disabling sections of the SoC when speech isn’t detected. This capability is particularly advantageous in markets such as IoT, wearables, or any battery-operated devices with VUI functionalities.
VAD challenges
A VAD solution allows the system to detect when someone is speaking and wake up the complete speech processing solutions. With that in mind, it is important to differentiate between voice detection, that identifies human speech patterns, and speech recognition, which is the overall function achieved by the system, ie translating wavelengths into digital computable information.
This white paper presents the different voice detection systems currently available and their respective benefits and drawbacks.