Infineon has recently released the AIROC CYW20829 Bluetooth LE (Low Energy) 5.4 family which now includes SoCs and modules. These SoCs include two Cortex-M33 MCU cores: one 48 or 96 MHz application core for the peripherals, security, and system resources, and one communication core for the 2.4 GHz RF transceiver with up to 10 dBm transmit power and -98 dBm receive sensitivity. This high integration reduces bill-of-material (BOM) costs for a wide variety of applications, including PC accessories, low-energy audio, wearables, solar micro inverters, asset trackers, home automation, and others. Back in 2021, we saw Infineon release the AIROC CYW5557x family of Wi-Fi 6/6E SoCs for IoT and streaming devices with features like enhanced range and improved network efficiency. More recently, Infineon announced the PSOC Edge E81, E83, and E84 MCU based on Cortex-M55/M33 microcontrollers. Feel free to check those out if you are looking for Infineon-specific MCUs. Infineon AIROC […]
ANAVI Dev Mic is a digital omnidirectional microphone based on Raspberry Pi RP2040 MCU (Crowdfunding)
The ANAVI Dev Mic is an open-source microphone board from ANAVI Technology in Plovdiv, Bulgaria powered by the Seeed Studio XIAO RP2040 module and an omnidirectional digital microphone from STMicroelectronics. It is a compact and affordable product that outperforms USB microphones in artificial intelligence and machine learning voice applications. The design is simple and unassuming, with the Seeed Studio XIAO RP2040 module in the center, surrounded by a USB-C port for power and programming and 9 GPIO pins for extensibility. The STMicroelectronics MP23DB01HP microphone (MK1) is mounted on the top of the board with a small hole on the bottom. It is a compact, low-power, digital MEMS microphone capable of capturing sounds from different directions with very low distortion. It uses a PDM (Pulse-Density Modulation) interface created via the programmable inputs/outputs (PIO) on the RP2040. The ANAVI Dev Mic is applicable for conducting AI/ML research, building a voice recognition platform, […]
Linamp – A Raspberry Pi 4-based audio box with Winamp look and feel
Linamp is a media player box based on Raspberry Pi 4 SBC and a touchscreen display with a GUI that replicates the popular Winamp media player’s GUI that older readers may remember from the late 90s and early 2000s when it was one of the most popular music players for Windows. Rodmg found some renders of what a real Winamp player could look like online, and it inspired him to create his own. As its name implies Linamp runs on Linux (DietPi) instead of Windows, and the hardware is based on a Raspberry Pi 4, a 7.9-inch touchscreen display, a USB DAC, and various connectors and cables, all housed in a custom-designed metal enclosure and a 3D-printed front cover both designed with Onshape. Here’s the complete list of off-the-shelf items used for the build: SBC – Raspberry Pi 4 with a 32 GB microSD card, a set of passive heat […]
ReSpeaker Lite Voice Assistant Kit combines XMOS XU-316 and ESP32-S3 for advanced voice processing, Home Assistant integration
Seeed Studio’s ReSpeaker Lite Series includes the ReSpeaker Lite 2-Mic Array and Voice Assistant Kit, featuring the XMOS XU-316 AI sound chip for advanced voice processing and integration with Home Assistant via ESPHome. It’s perfect for smart home control with far-field voice capture and noise cancellation. The kit combines the ReSpeaker Lite dual-microphone array with the XIAO ESP32S3 module for voice recognition, noise reduction, and processing. It supports WiFi, BLE 5.0, and has a 2.4GHz rod antenna. It also offers I2S and USB connectivity for use with microcontrollers and SBCs, making it ideal for smart voice assistants and home automation. We’ve previously covered the NXP i.MX RT106F & RT106A/L, where NXP i.MX RT106A can run voice assistant software with features like acoustic echo cancellation, ambient noise reduction, beamforming, barge-in, and playback processing. We’ve also written about other ReSpeaker boards, such as the ReSpeaker 4-Mic Array board, ReSpeaker Core board, and […]
NXP SAF9000 and SAF9100 Automotive Audio DSP bring AI to car infotainment
NXP has recently launched the SAF9xxx Automotive Audio DSP family, which currently includes SAF9000 and SAF9100 AI audio DSPs. Built around Cadence’s latest generation high-performance Tensilica HiFi 5 DSPs, these new chips not only feature AI and ML capabilities, but also include features like driver’s voice pitches and accent recognition, noise cancellation, voice recognition, emergency siren detection, and more. Additionally, the SAF9000 chip includes a software-defined radio option with up to five integrated tuners (controlled by an integrated Arm Cortex-M7 core) that covers all major global broadcast radio standards, including DAB, HD Radio, DRM, CDR, and AM/FM into a single chip solution. SAF9xxx Automotive Audio DSP specifications DSP – Tensilica HiFi 5 DSPs with dedicated neural network engines Integrated Controller – Arm Cortex-M7 core for tuner and audio control middleware Radio Features (SAF9000 only) Supports AM, FM, DAB, DAB+, DMB, HD Radio, DRM for AM, DRM for FM (DRM+), CDR […]
picoLLM is a cross-platform, on-device LLM inference engine
Large Language Models (LLMs) can run locally on mini PCs or single board computers like the Raspberry Pi 5 but with limited performance due to high memory usage and bandwidth requirements. That’s why Picovoice has developed the picoLLM Inference Engine cross-platform SDK optimized for running compressed large language models on systems running Linux (x86_64), macOS (arm64, x86_64), and Windows (x86_64), Raspberry Pi OS on Pi 5 and 4, Android and iOS mobile operating systems, as well as web browsers such as Chrome, Safari, Edge, and Firefox. Alireza Kenarsari, Picovoice CEO, told CNX Software that “picoLLM is a joint effort of Picovoice deep learning researchers who developed the X-bit quantization algorithm and engineers who built the cross-platform LLM inference engine to bring any LLM to any device and control back to enterprises”. The company says picoLLM delivers better accuracy than GPTQ when using Llama-3.8B MMLU (Massive Multitask Language Understanding) as a […]
Rockchip RK2118G/RK2118M dual-core Star-SE Armv8-M microcontrollers target smart audio applications
Rockchip RK2118G and RK2118M smart audio microcontrollers based on a dual-core Star-SE Armv8-M processor, an NPU for smart AI audio processor, three DSPs, 1024KB SRAM, optional DDR memory in package, and a range of peripherals. I first noticed the RK2118M in slides from the Rockchip Developer Conference 2024 last March, but I did not have enough information for an article at the time. Things have now changed since I’ve just received a bunch of datasheets including the one for the RK2118G and RK2118G microcontrollers, which look identical except for the DDR interface and optional built-in 64MB RAM for the RK2118G. The datasheets have only one reference to Arm with the string “Arm-V8M” and nothing else, and Cortex is not mentioned at all. But the slide above reveals the STAR-SE core looks to be an Arm Cortex-M33 core. We also learn the top frequencies for the “STAR-M33″/”STAR-SE” core (300MHz) and the […]
$23 C790 HDMI to MIPI CSI adapter adds HDMI and audio input to Raspberry Pi SBCs
C790 is an HDMI to MIPI CSI-2 board compatible with Raspberry Pi single board computers featuring a 40-pin GPIO header that adds both HDMI input up to 1080p60 and I2S audio input to the popular Arm SBC. The solution can be useful for IP KVM solutions as we’ve seen with the PiKVM v3 and PiCast portable KVM switch, or to capture video and audio from a camera that outputs HDMI with audio through the board’s MIPI CSI camera interface and I2S input signals on the GPIO header. C790 specifications: Supported SBC’s – Raspberry Pi Zero, 3B, 3B+, 4B, CM3, CM4 with MIPI CSI-2 input port (Note: Raspberry Pi 4 is limited to 1080p50 due to 2-lane MIPI CSI-2, CM4 supports 1080p60) Main chip – Toshiba TC358743XBG HDMI to CSI-2 bridge chip up to 1920×1080, 60 FPS Video and audio input – HDMI port up to 1080p60 Video Output – 2-lane […]