Embedded voice, vision and biometrics artificial intelligence (AI) company Sensory has announced that its wake word engine, TrulyHandsfree, has new capabilities that will allow for multiple wake words from any combination of supported devices, without affecting performance.
According to a release, the new technology supports Amazon as well as the Voice Interoperability Initiative (VII), which was announced in September. The tech will allow for brands to develop products that have multiple simultaneous voice services.
“Multiple simultaneous wake words provide the best option for customers,” Amazon Founder and CEO Jeff Bezos said at the time.
Sensory CEO Todd Mozer said the new technology helps to move the barometer on voice assistants.
“We are lucky to have worked closely with most of the leaders in voice services to help create products with their wake words embedded. Because of this, we already have all of the data in place to combine multiple models,” Mozer said. “However, everyone in the industry has found that combining two or more wake word models into a product poses a significant challenge in maintaining optimal performance. The new capabilities we added to TrulyHandsfree overcomes some of the accuracy challenges without significantly boosting MIPS and memory requirements.”
Sensory has already built deep learned models for some of the most well-known wake words, like “Hey Cortana,” “Alexa,” “OK Google,” “Hey Siri,” “Hi Bixby” and “Xiao-du Xiao-du.”
“Also, on our roadmap for a 2020 release is multi-wake word adaptation that will allow devices to know who is talking to them and to adapt the voice model to better work with each individual user,” Mozer said.
The company’s TrulyHandsfree technology uses a new technique to let multiple wake words happen without increasing error rates, which has been a traditional problem when trying to run a lot of wake words on one device.
“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,” the company said in the release.