Sensory, a vision and biometrics AI company, announced new capabilities for TrulyHandsfree, the company’s wake word engine. It enables support for multiple wake words from leading brands, custom branded wake words, small vocabulary command sets, or even user defined wake words. The technology supports Amazon, Voice Interoperability Initiative (VII), and allows brands to get a jumpstart on the development of products that feature multiple simultaneous voice services.
Sensory has already collected the data and built deep learned models for Hey Cortana, Alexa, OK Google, Hey Siri, Hi Bixby, Xiao-du Xiao-du, and over 2 dozen other assistants. These wake words have been approved for market with ultra-low power applications like wearables and mobile phones, in addition to high-performance applications like vehicles, smart speakers, and home appliances.
TrulyHandsfree employs a new technique to enable multiple wake words without linearly increasing the error rates. With traditional approaches, adding a new wake word meant the sum of the error rates of each individual wake word, but with TrulyHandsfree the accuracy doesn’t degrade as fast, offering support for more wake words with less false accepts and false rejects.
Sensory will be showcasing TrulyHandsfree at CES 2020, supporting multiple wake words for today’s most popular voice assistant platforms.
For more information, visit https://email.sensory.com/sensory-at-ces-2020
About the AuthorFollow on Twitter Follow on Linkedin More Content by Perry Cohen