AIStorm, a pioneer and leader of AI-in-Sensor SoCs for edge devices, announced its development partnership with Knowles, a specialist in advanced micro-acoustic microphones and speakers, audio processing, and precision device solutions. The collaboration will focus on achieving the lowest-power, highest-performance audio solutions available to enable emerging features.
Emerging audio technologies are transforming battery-operated devices such as TWS earbuds, smart speakers, and AI-enabled remote controls, while ushering in a new era of connected IoT functionality and expanding market expectations beyond mobile phones and computing devices.
Tiny form factor devices such as TWS earbuds are challenged to perform advanced signal processing tasks such as noise cancellation, beam forming, keyword spotting (KWS), speaker identification, sound classification, and other algorithmic sound enhancements at very low power levels.
“Existing always-on implementations either use a rudimentary analog acoustic activity detection (AAD) or implement voice activity detection (VAD) that requires continuous, power-hungry digitization,” said Lisa Orlandi, VP of worldwide sales for AIStorm. “Both these solutions are not optimal from a power and accuracy standpoint.”
With AIStorm’s analog and mixed-signal IP, incoming audio data can be directly processed in the analog domain, prior to digitization.
“AIStorm and Knowles have come together to push the state of the art in audio processing technology by using AIStorm’s IP,” said Raj Senguttuvan, strategic marketing director at Knowles. “This can enable the proliferation of advanced features at lower power in tiny form factor battery-operated devices.”
