Speech Recognition Gets an Upgrade

By Ken Briodagh August 06, 2015

As we’ve reported before, speech recognition software holds a lot of potential for intuitive control of devices within the IoT, but the technology needs improvement to gain mass adoption. Well, one vendor says it’s on the way.

Sensory Inc., a Silicon Valley-based company focused on improving the user experience and security of consumer electronics through embedded voice and vision technologies, recently announced its TrulyHandsfree 4.0 embedded small-footprint voice user interface platform. This new version of the platform offers improved performance and up to an 80 percent increase in word accuracy, thanks to a feature called “deep learning.” According to Wikipedia, “Deep learning (deep machine learning, or deep structured learning, or hierarchical learning, or sometimes DL) is a branch of machine learning based on a set of algorithms that attempt to model high-level abstractions in data by using model architectures, with complex structures or otherwise, composed of multiple non-linear transformations.”

TrulyHandsfree includes filterbank features and all-new phrase spotting techniques, in addition to a neural nets engine that supports deep learning acoustic models, dramatically improving speech recognition accuracy in real-world noise. It takes advantage of deep learning to achieve acoustic models an order of magnitude smaller than the present state-of-the-art. Also, new spotting techniques ensure that the core part of a spoken request can be recognized in the middle of speech, or when surrounded by ambient noise.

Image via Shutterstock

“TrulyHandsfree was an industry-first that literally changed the way people interact with devices of all kinds,” said Todd Mozer, CEO of Sensory Inc. “TrulyHandsfree 4.0 takes performance to a whole new level with an accuracy, footprint and power consumption that others just can’t touch.”

Bringing machine listening into the IoT through deep learning is a new approach, but on that must be taken seriously. We’ll be watching. And if you want to see revolutionary tech like this, don’t miss the IoT Evolution Expo, August 17 to 20 at Caesars Palace in Las Vegas. 

Edited by Maurice Nagle

Author Info

SHARE THIS ARTICLE

Source: Speech Recognition Gets an Upgrade

Via: Google Alert for Deep Learning