Joint speech recognition solution from STM and Sensory to ease embedded voice control
The companies say Sensory’s voice technologies and the STM32 hardware and software can be used to create speech recognition models for custom wake words, voice control commands, and natural language grammars in just under 20 languages and dialects.
The solution utilizes the STM32H7 MCU and the STM32Cube software extension portfolio, which can increase the accuracy of voice control applications and reduce command-recognition time, according to the announcement. Voice application and speech models can also be stored in the MCU’s on-chip memory for easy integration and lower total ownership costs.
“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,” says Ricardo De Sa Earp, executive vice president, General-Purpose Microcontroller Sub-Group Vice President, 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 expertise, for free in prototypes and with favorable licensing terms in production.”
The announcement does not refer to voice recognition, but Sensory also launched a cloud service platform to deliver its voice (as well as face) biometrics at the beginning of 2022.
Applications built with the joint solution could add biometrics for authentication to secure account access or voice-enabled transactions.
“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,” says Todd Mozer, CEO, Sensory. “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.”
Sensory also partnered with ArkX earlier this year to ease the integration of speech recognition and biometrics.