STMicroelectronics, a global semiconductor supplier serving customers across the spectrum of electronics applications, and Sensory Inc., a provider of integrated speech recognition technology and an ST authorized partner, are collaborating on a new project.
The partnership will enable the STM32 microcontroller (MCU) user community to develop and prototype intuitive voice-based user interfaces for a wide range of smart embedded products.
The joint efforts combine ST's STM32 hardware and software with Sensory's voice control technologies – including the new VoiceHub online portal that supports the seamless creation of embedded speech recognition models using custom wake words, command sets of voice control and large natural language grammars in nearly 20 languages and dialects.
“This collaboration aims to drive the development of embedded voice user interfaces, adding frictionless command control and personalized wake word to any device, from wearables to smart home appliances,” said Ricardo De Sa Earp, executive vice president, general subgroup of VP purpose microcontrollers, STMicroelectronics. “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 knowledge, free of charge in prototypes and with favorable licensing terms.” in production. ”
The solution is based on an STM32Cube software extension package and runs on a high-performance STM32H7 MCU, taking advantage of its architecture, internal Flash, SRAM and high CPU speed. This combination plays a key role in increasing voice control accuracy and minimizing command recognition time. Hosting voice applications and speech models in the generous on-chip memory of high-performance STM32 MCUs further increases system integration and ease of use, and reduces cost of ownership.
“Sensory designed our VoiceHub so developers could quickly and easily create custom speech recognition models. However, after creating a custom model, integrating the model with hardware and moving on to licensing terms were the next hurdles that needed to be overcome,” said Todd Mozer, CEO of Sensory. “This world-class collaboration with ST creates a complete software, hardware and licensing package for voice recognition integrated across the entire STM32 family and simplifies the addition of voice UIs.”
ST's new software suite dedicated to voice user interfaces is available here.
