STMicro, Sensory Team Up for Cloud-Free On-Device STM32 Voice User Interface Development
Aims to speed prototyping using the new X-CUBE-LocalVUI extension on an STM32H747I-DISCO development board.
STMicroelectronics has announced a partnership with Sensory to bring the latter's VoiceHub technology to the former's STM32 microcontroller family — providing a streamlined development process for voice-based user interfaces for the Internet of Things (IoT), wearables, and more.
"This collaboration sets to jump-start the development of embedded-voice user interfaces, adding friction-free command control and custom wake word to any device, from wearables to smart-home appliances," claims STMicro's Ricardo De Sa Earp. “The unique combination of ST and Sensory technologies will enable the STM32 user community to deploy 'Voice AI on the edge' without any programming, data-science, or machine-learning expertise, for free in prototypes and with favorable licensing terms in production."
"Sensory designed our VoiceHub so developers could quickly and painlessly create custom speech-recognition models. However, after creating a custom model, integrating the model onto hardware, and moving to licensing terms were the next hurdles that needed to be cleared," adds Sensory chief executive Todd Mozer. "This world-class collaboration with ST creates a complete software, hardware, and licensing package for embedded speech recognition across the STM32 family and makes adding Voice UIs, simple."
The partnership sees Sensor's voice control technologies ported to the STMicro STM32H2 microcontroller, including the VoiceHub online portal for model creation — allowing users to quickly create or tweak embedded speech recognition models with custom wake words, voice command sets, and expansive grammars.
Dubbed X-CUBE-LocalVUI, the initial port — which includes a demonstration home automation application, though STMicro claims "is ready to be tuned into any other UI a user may need" — is built around STMicro's STM32H747I-DISCO developer kit. The models are hosted in-memory and on-device, allowing for what STMicro says will be a speedy command-recognition time and cloud-free operation. Those looking towards deployment, meanwhile, can port the software to other models in the STM32 family — providing they have audio capabilities.
More details are available on the X-CUBE-LocalVUI product page.
Freelance journalist, technical author, hacker, tinkerer, erstwhile sysadmin. For hire: freelance@halfacree.co.uk.