Knowles Corp. has introduced the AISonic IA8201 Raspberry Pi Development Kit that bundles hardware, add-on software, and algorithms to deliver voice, audio edge processing, and machine learning (ML) listening capabilities to IoT devices and systems across a range of industries. The kit gives OEM/ODM product designers and engineers a single tool to streamline design, development, debugging, and testing for prototyping devices for new use cases.
At the heart of the development kit is the ultra-low-power and high performance AISonic IA8201 audio edge processor OpenDSP that meets a range of audio processing requirements. The audio edge processor combines two Tensilica-based, audio-centric DSP cores; one for high-power compute and AI/ML applications, and the other for very low-power, always-on processing of sensor inputs. The IA8201 has 1 MB of RAM on-chip that allows for high bandwidth processing of advanced, always-on contextually aware ML use cases and memory to support multiple algorithms.
Click for a larger image. (Source: Knowles)
Using the Knowles openDSP platform, the kit includes a library of onboard audio algorithms and AI/ML libraries. Developers have access to Knowles’ algorithm partners, including Amazon Alexa, Sensory, Retune, and Alango that provide algorithms such as ultra-low-power voice wake, beamforming, custom keywords, and background noise elimination.
Recommended
Audio edge processors deliver context-aware audio experiences
The Raspberry Pi development kit also features TensorFlow Lite-Micro SDK for prototyping and product development for AI/ML applications. The TensorFlow-Lite SDK allows for porting models developed in larger cloud Tensor Flow frameworks to an embedded platform at the edge, usually with limited compute and lower power consumption, said Knowles. One example cited is AI inference engines for anomaly detection in industrial and commercial markets.
The kit also offers options for either two or three pre-integrated Knowles Everest microphones and includes two microphone array boards to help select the right algorithm configurations for the end application. Applications range from smart home and home entertainment to smart buildings, residential/commercial security, and inference engines for industrial and commercial.
Support is available through the Knowles Solutions Portal for configuration tools, firmware, and algorithms that come standard with the kit.
Advertisement
Learn more about Knowles
