Knowles AISonic IA8201 Raspberry Pi Development Kit is designed to bring voice, audio, and machine learning (ML) listening capabilities to various systems, and can be used to evaluate the company’s AISonic IA8201 DSP that was introduced about two years ago.
The kit consists of three boards with an adapter board with three buttons connecting to the Raspberry Pi, as well as the AISonic IA8210 DSP board itself connected via a flat cable to a microphone array.
Knowles AISonic Raspberry Pi Development Kit
Knowles did not provide full development details, but says it enables voice wake-up processing for a low-latency voice UI, noise reduction, context awareness, and accelerated inference. of machine learning for on-board processing of sensor inputs.
Some of the use cases include Low power voice wake-up to listen for specific OEM keywords to wake up the host processor, Proximity detection when combined with an ultrasonic capable speaker and microphone, Security system for example to detect broken glass, smoke detectors, etc.
Programming is done through the “DSP SDK” with Knowles and Xtensa HiFi 3 instruction sets enabling voice and audio processing, voice user interface and ambient sound processing. There is also a partner program called âOpen DSPâ which brings third party algorithms to the ecosystem. The myKnowles portal is supposed to offer resources, including solution kits, product sheets, discussion forums, etc. But it requires registration, which I did, and manual approval, which I’m still waiting for.
The Press release offers some additional information regarding software, including support for Amazon Alexa, Sensory, Retune, and Alango voice services, as well as TensorFlow Lite Micro SDK for AI / ML applications. We also learn that the kit actually comes with two microphone arrays, one with two microphones and the other with three microphones to allow developers to evaluate and select the optimal solution for their specific application.
AISonic IA8201 Audio & ML DSP
Although we have limited information on the development kit itself, there are some fashion details on the AISonic IA8201 DSP with the following specs:
- MCU cores
- Xtensa LX5 128-bit floating point SIMD DSP “DeltaMax” kernel, with Knowles instruction set extensions optimized for frame-based audio processing and DNN acceleration
- Xtensa LX5 “HemiDelta” 64-bit bidirectional floating point SMID DSP core, with Xtensa HiFi 3 and Knowles instruction sets, optimized for low power consumption
- Memory – 1.44 MB of RAM of which 1 MB is available for the user
- Audio interfaces
- Up to 4x digital PDM microphones – 1 stereo input, 4x mono inputs and 1 stereo output, supporting clock rates up to 6.144 MHz
- Up to 3 I 2S / TDM ports supporting 8 channels each of 32-bit audio data using 24.576 MHz input clock
- Control interfaces – SPI, I 2 C, UART, GPIO available.
- Clock up to 175 MHz
- Voltage supply requirements
- IA8201BC – 1.8 V Vdd
- IA8201CQ – 1.8 V Vdd and 3.3 V Vdd
- Temperature range -20 to 85 Â° C
- Packing options
- eWLB 3.00 Ã 2.6 Ã 0.715mm, 0.4 pitch, 42 balls (IA8201BC)
- QFN 6.00 Ã 6.00 Ã 0.75mm, 0.5 pitch, 40 threads (IA8201CQ)
The DSP and devkit can be used for a variety of applications including smart home, home entertainment, smart buildings, residential and commercial security, as well as inference engines for the industrial and commercial sectors.
The Knowles IA8201 Raspberry Pi Development Kit is now available to order, but you will need to contact the company if you are interested, AFAICS, it is not sold online. More details can be found on the development kit and AiSonic processors pages, with the latter also including the quad-core AISonic IA8508 DSP adding Cortex-M4 and SSP (single sample processor for echo cancellation, sample rate conversion) cores to the DeltaMax and HemiMax cores of the DSP IA8201.
Going through LinuxGizmos
Jean-Luc started CNX Software in 2010 on a part-time basis, before stepping down as head of software engineering and starting writing daily news and reviews full-time later in 2011.