Sensory Brings "Alexa" Wake Word to IoT Developers
Sensory has begun collaborating with Amazon's Alexa Voice Service (AVS) team to enable developers to use the wakeup word "Alexa" with its TrulyHandsfree technology. As part of the AVS for Raspberry Pi project on GitHub, Sensory will enable device manufacturers to develop prototypes that feature Alexa voice control functionality and accelerate device time to market.
Sensory has developed a suite of voice models for Alexa that are part of Sensory's TrulyHandsfree speech recognition engine. These models can range in size and performance features to handle low-power battery-operated usage to highly noise robust far-field applications with extremely high accuracy. The AVS for Raspberry Pi project allows a GitHub download of three Alexa triggers from Sensory, varying in size and performance, yet all fitting on a Raspberry Pi platform.
"Sensory's technology makes it very easy for manufacturers to integrate a TrulyHandsfree voice-controlled user experience. The key to offering an effective voice wake up word technology is ensuring that the system is not only activated when the trigger phrase is spoken, but also ensuring the system is not accidentally activated when the wakeup word is not spoken. Sensory and the AVS team have worked hard to bring manufacturers innovative voice capabilities, so it is exciting for us to be working together," said Todd Mozer, CEO of Sensory, in a statement.
"Alexa was designed to make it easy for companies like Sensory to build on the service and offer a variety of choices to manufacturers when creating voice-experiences," said Aaron Brown, director of Alexa, in a statement. "We are excited to work with Sensory on Alexa voice trigger models that enable hands-free Alexa experiences for a wide variety of products."
Third-party developers are starting to come to market with Alexa-enabled devices that use Sensory's wake up word models. One such company is Nucleus, which recently released an Alexa-enabled intercom.
"When we were developing Nucleus, we tried other speech recognition technologies; however, after experimenting with Sensory's voice models, we quickly realized why everyone says their technology is the best. The performance and accuracy benefits of Sensory's wake up voice models for Alexa have been fantastic," said Isaac Levy, founder and chief technology officer at Nucleus Life, in a statement.
Sensory has boosted the performance and accuracy of its embedded wake word and speech recognition with shallow learning.
Sensory's voice recognition software powers a voice-processing microphone for waking up smart devices.
Sensory's VoiceGenie enables a hands-free experience on Bluetooth devices through Alexa integration and embedded artificial intelligence.
TrulyHandsfree enables developers to add speech triggers and commands into apps with fewer than 20 lines of code.
Samsung's latest smartphone models offer voice trigger and speech recognition technology from Sensory.
TrulyHandsfree is now available on Intel low-power digital signal processors in Skylake, Anniedale, Broxton, Broadwell and Merrifield software-on-a-chip.