Sensory simplifies voice biometrics and UI development for edge devices
Sensory, Inc., a developer of AI and voice processing technologies and software, wants to awaken demand for voice user interface development with a new online portal called VoiceHub. The VoiceHub portal enables developers to create wake word models and voice control command sets in multiple languages in a short amount of time, enabling more rapid prototyping of devices and services for use in biometric security as well as various consumer applications.
Sensory’s VoiceHub is a free tool for developers, who can now go online and create voice command sets with varying model sizes in a matter of an hour or so. A companion Android application can then be used to prototype the voice command and wake word models that are created by VoiceHub, or developers can use code to run on specific digital signal processors (DSPs). The company notes that one of the advantages of using the tool is the ability to create custom branded voice recognition models in addition to ones based on popular voice assistant platforms.
“Sensory applied decades of experience and lessons learned with shallow net technologies to create its highly accurate machine learning models, which are trained with a mix of real and probabilistically-derived synthetic data,” said Todd Mozer, CEO at Sensory in a prepared statement. “VoiceHub benefits from all of this work and removes any friction related to developing voice UIs for testing purposes,” he said, adding that “We are excited to share these tools and capabilities with the speech tech community and beyond and believe VoiceHub will serve as a catalyst for rapidly accelerated innovation of new voice-enabled experiences.”
The market has already been catalyzed to a degree, thanks in part to marketing around devices such as Amazon’s Alexa range of smart devices as well as those from Google, Apple and others. The worldwide market for smart home devices is expected to grow 4.1 percent year over year in 2020 with shipments totaling more than 854 million units, according to the International Data Corporation (IDC) Worldwide Quarterly Smart Home Device Tracker. The Smart Speaker segment of the market alone represents 15.6 percent of the total devices to be shipped.
Sensory’s announcement comes as a number of companies have been focused on developing faster processors for edge AI applications like voice recognition. Amazon itself recently announced a new chip for use in its Echo devices, while startups like Hailo have been busy integrating new power efficient AI processors integrated into complete motherboard packaging for easier inclusion in devices such as video cameras, edge gateways for video processing, and other devices used in biometric identification. Sensory’s approach comes at the same issue—making voice recognition more ubiquitous—by making it easier for developers to create and train the models that underpin services.
“Many of the brands building on Audio Weaver have been using Sensory’s TrulyHandsFree technology to power voice UI for years, so we anticipate a lot of interest in VoiceHub,” said Chin Beckmann, CEO of DSP Concepts, a Sensory, Inc. partner. “Adding VoiceHub to Audio Weaver gives brands the ability to integrate custom voice commands more efficiently than ever—instantly bringing the full vision of their branded customer experience to life at the prototype phase through to deployment,” he said in a prepared statement.
AI | biometric identification | biometrics | biometrics at the edge | IoT | research and development | Sensory | voice biometrics | voice recognition