Low Power Voice Interface Chip

Voice interaction with computing devices has been growing more sophisticated and more common. Power requirements have been a major obstacle. A new low power speech recognition chip design is about to change that. If the power savings suggested for this chip are actually realized, it could open up the potential for voice interfaces in everything we use. The techniques used in the chip to save power may also find applications in other areas, such as: image processing, complex decision chains, and more.

Voice control everywhere – [mit.edu]

The butt of jokes as little as 10 years ago, automatic speech recognition is now on the verge of becoming people’s chief means of interacting with their principal computing devices.

In anticipation of the age of voice-controlled electronics, MIT researchers have built a low-power chip specialized for automatic speech recognition. Whereas a cellphone running speech-recognition software might require about 1 watt of power, the new chip requires between 0.2 and 10 milliwatts, depending on the number of words it has to recognize.

In a real-world application, that probably translates to a power savings of 90 to 99 percent, which could make voice control practical for relatively simple electronic devices. That includes power-constrained devices that have to harvest energy from their environments or go months between battery charges. Such devices form the technological backbone of what’s called the “internet of things,” or IoT, which refers to the idea that vehicles, appliances, civil-engineering structures, manufacturing equipment, and even livestock will soon have sensors that report information directly to networked servers, aiding with maintenance and the coordination of tasks.

Comments are closed.