Supporting voice-driven commands In small, low-power microcontrollers.
With the widespread use of voice-activated virtual assistants, such as Apple’s Siri, Amazon’s Alexa, Microsoft’s Cortana, and the Google Assistant, voice has become an everyday way to interact with electronics. We’re talking to our devices more than ever, using speech to initiate searches, issue commands, and even make purchases.
There are a number of reasons why using your voice to control an electronic device is a good idea. It’s almost always easier to talk than to type, and having voice activation means electronics can be controlled entirely hands-free. Devices can also have highly intuitive user interfaces, even if they don’t have a display, and can operate in challenging environments where a keyboard would be problematic.
In developing the mechanisms for voice activation, designers have found that neural networks, which are modeled on brain function, are better at understanding us than traditional speech-processing networks. This is partly because neural networks, also known as “deep learning” algorithms, can be trained and can learn from experience, so they become more accurate over time.
To read more, click here.
 |
 |
 |
 |
 |
 |
Leave a Reply