STMicroelectronics and DSP brings intelligence to MEMS Microphones
4 March, 2017
The small System-in-Package (SiP) device integrates a low-power ST MEMS microphone with DSP Group’s HDClear audio processor and Sensory’s voice-recognition firmware
STMicroelectronics, DSP Group Inc. and Sensory Inc. have revealed details for a highly power-efficient, voice-detecting and -processing microphone that delivers keyword-recognition capabilities in a compact package. The small System-in-Package (SiP) device integrates a low-power ST MEMS microphone enabled by DSP Group’s ultra-low power voice-processing chip and Sensory’s voice-recognition firmware.
Although typical wake-on-sound microphones eliminate the need for users to touch the device to wake it from sleep mode, they have a very limited processing power and not capable to bring full recognition of the received instruction. Using the HDClear ultra-low power audio processing chip from DSP Group, ST’s microphone detects and recognizes instructions without waking the main system, enabling energy-efficient, intuitive and seamless interactions for users speaking to voice-operated appliances like smart speakers, TV remotes, and smart home systems.
Understanding without Listening
“Unlike previous existing solutions, this microphone doesn’t just listen to voices – it immediately understands the commands, too, without using the power and computation resources of the main processor,” said Andrea Onetti, MEMS and Sensors Division General Manager, STMicroelectronics.
“As voice becomes the default user interface, more and more innovative products embrace smart voice-processing technology,” said Ofer Elyakim, CEO of DSP Group. “This collaboration brings to market a powerful yet energy-efficient solution with best-in-class performance – a perfect match for any smart system that needs high-quality voice capabilities.” First prototypes of ST’s new command-recognition microphone will be available by the end of Q1 2017 with volume production in early 2018.
MEMS Microphones: Smaller and Better
MEMS (Micro-Electrical-Mechanical Systems) microphone sensor is basically a variable capacitor that responds to incoming wave of the sound. It is produced in a silicon fab and consists of two silicon plates/surfaces. One plate is fixed while the other one is movable. The fixed surface is covered by an electrode to make it conductive and is full of acoustic holes which allow sound to pass through. The movable plate is able to move since it is bonded at only one side of its structure. Beside low cost, very small form factor and excellent Signal to Noise Ratio, in comes with an integrated circuit inside the package, to converts the change of the polarized MEMS capacitance into a digital (PDM modulated) or analog output according to the microphone type. This is the place where ST, DSP and Sensory added intelligence into the device.
STMicroelectronics is a global semiconductor leader. In 2016, the Company’s net revenues were $6.97 billion. DSP Group from Herzliya, Israel, provides wireless chipsets integrating DECT/CAT-iq, ULE, Wi-Fi, PSTN, HDClear, video and VoIP technologies. Sensory from the UK provides voice control firmware for mobile phones, automotive, wearables, toys, IoT and various home electronics.