STMicroelectronics is pairing its STM32 microcontroller (MCU) hardware and software with Sensory’s voice-control technologies to streamline the development of voice-based user interfaces on wearables, Internet of Things (IoT), and smart-home applications.
While Sensory’s VoiceHub technology allows designers to create custom speech-recognition models using custom wake words, voice-control command sets, and large natural-language grammars in almost 20 languages and dialects, integrating the model onto hardware and moving to licensing terms become major hurdles after creating a custom model. Joining hands with ST creates a complete software, hardware, and licensing package for embedded speech recognition across the STM32 microcontrollers and makes adding the voice interface a simple task.
It will also enable design engineers to deploy artificial intelligence (AI)-centric voice on edge without expertise in programming, data science, and machine learning. Users can run the STM32Cube Expansion Software package on a high-performance STM32H7 microcontroller to host speech models while taking advantage of MCU’s generous on-chip memory resources.
This new solution allows design engineers to develop and prototype intuitive voice-based user interfaces for a wide range of smart embedded products. It also allows designers to take advantage of the STM32Cube software ecosystem as well as Sensory’s new VoiceHub online portal.