Knowles’ Raspberry Pi development kit brings voice, audio edge processing, and ML listening to a vast number of applications and market segments. The kit, which leverages the company’s OpenDSP-based AISonic IA8201 audio edge processor, bundles all of the hardware, add-on open software, and algorithms needed to test, prototype, and debug voice and audio functionality for applications ranging from smart home to industrial inference engines.
The audio edge processor combines two Tensilica-based audio-centric DSP cores. One core targets high-power compute and AI/ML applications, while the other core handles low-power, always-on processing of sensor inputs. The IA8201 packs 1 MB of on-chip RAM that allows for high-bandwidth processing of always-on contextually-aware ML use-cases.
Also included in the development kit is a library of onboard audio algorithms and AI/ML libraries. Far-field audio designs can be built using low-power voice wake, beamforming, custom keywords, and background noise elimination algorithms from partners such as Amazon (Alexa), Sensory, Retune, and Alango. In addition, the supplied TensorFlow Lite Micro SDK enables prototyping and product development for AI/ML applications.
Two microphone array boards, with the option for either two or three preintegrated Knowles Everest microphones, help users select the appropriate algorithm configurations for their end product. The built-in microphone arrays support the audio and voice capabilities of the IA8201 DSP, giving designers an all-in-one development solution from a single supplier.
The AISonic IA8201 Rasberry Pi development kit is available for order with support through Knowles.
Find more datasheets on products like this one at Datasheets.com, searchable by category, part #, description, manufacturer, and more.