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,” says 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,” says 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.”
Knowles Corporation uses its leading position in SiSonic MEMS (micro-electro-mechanical systems) microphones and strong capabilities in audio processing technologies to optimize audio systems and improve the user experience in mobile, ear, and connected applications.
AIStorm is a pioneer in AI-in-Sensor charge domain processing, which eliminates the latency, power and cost associated with competitive AI solutions at the edge. AIStorm is headquartered in Houston, Texas, with offices in Graz, Austria; Budapest, Hungary; Chardon, Ohio; Nashua, New Hampshire; Toronto, Canada; and Hsinchu, Taiwan.
www.aistorm.ai
www.knowles.com
