Picovoice Cobra Voice Activity Detection Engine shown to outperform Google WebRTC VAD

PicoVoice Cobra VAD

Picovoice Cobra Voice Activity Detection (VAD) engine has just been publicly released with support for Raspberry Pi, BeagleBone, NVIDIA Jetson Nano, Linux 64-bit, macOS 64-bit, Windows 64-bit, Android, iOS, and web browsers that support WebAssembly. Support for other Cortex-M and Cortex-A based SoCs can also be made available but only to enterprise customers. Picovoice already offered custom wake word detection with an easy and quick web-based training and offline voice recognition for Raspberry Pi, and even later ported their voice engine to Arduino. Cobra VAD is a new release, and, like other VADs, aims to detect the presence of a human voice within an audio stream. Picovoice Cobra can be found on Github, but note this is not an open-source solution, and instead, libpv_cobra.so dynamic library is provided for various targets, together with header files and demos in C, Python, Rust, and WebAssembly, as well as demo apps for iOS […]

Add an audio jack to Raspberry Pi 400 with the DACBerry 400

The Raspberry Pi 400 is a keyboard PC with most of the features of Raspberry Pi 4 SBC, with one of the exceptions being the lack of AV port. But you can now add a 3.5mm audio jack to the Raspberry Pi 400 through the DACBerry 400 S expansion board that connects to the 40-pin GPIO header. It’s a neater way than using a cheap USB audio dongle with microphone and headphone jacks, as it takes less space, and does not occupy any of the USB ports from the Raspberry Pi 400, and it does not prevent you from using the GPIO header.  It’s also better suited for headphones with both microphone input and analog stereo audio output into a single jack, and probably comes with better audio quality than the low-cost USB dongles. DACBerry 400 S (DBR400S) specifications: Gold-plated 3.5mm headset/headphone jack (mic in – stereo out) DAC SNR […]

Raspberry Pi smart audio devkit features AISonic IA8201 DSP, microphone array

AISonic-Raspberry Pi Development Kit

Knowles AISonic IA8201 Raspberry Pi development kit is designed to bring voice, audio edge processing, 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 is comprised 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 the full details for the development but says it enables wake-on-voice processing for low latency voice UI, noise reduction, context awareness, and accelerated machine learning inferencing for edge processing of sensor inputs. Some of the use cases include Low Power Voice Wake to listen for specific OEM keywords to wake the host processor, Proximity Detection when combined with an ultrasonic capable […]

DIY Spotify Box features custom-designed Allwinner V3s SBC

Spotify Box

The Spotify Box is a small DIY device based on an Allwinner V3s single-core Cortex-A7 camera SoC and a wooden enclosure designed to play Spotify songs, and not much else… The device serves as a bridge between the official Spotify app and your home audio system connected through the RCA jacks of the box. and allowing you to connect your smartphone to your audio setup and stream music throughout your house.  Spotify Box specifications: SoC – Allwinner V3s single-core Cortex-A7 processor @ 1.2 GHz with on-chip 64MB DDR2 Storage – MicroSD card slot for OS Audio – 2x RCA jack for left and right audio Connectivity 10/100M Ethernet RJ45 port 2.4 GHz 802.11b/g/n WiFi 4 and Bluetooth 4.2 via RTL8723DS module Misc – Push button, RGB LED Power Supply – 5V via USB-C port Evan Hailey selected Allwinner V3s over other processors such as NXP i.MX233 or Microchip SAM9N because […]

Getting started with Bluetrum AB32VG1 RISC-V Bluetooth audio board using RT-Thread

Bluetrum AB32VG1 RISC-V Bluetooth audio board

Bluetrum AB32VG1 is a development board based on AB5301A RISC-V microcontroller designed for Bluetooth audio applications as well as general-purpose projects that works with RT-Thread real-time operating system. RT-Thread sent me a board for review, and I’ll write about my experience in a getting started guide for Bluetutm AB32VG1 trying out the RT-Thread Studio IDE with the LED blink and audio samples, as there’s no Bluetooth sample at this time… Bluetrum AV32VG1 Unboxing The board ships with a USB-C cable for power and programming. It offers Arduino UNO headers for expansion, a MicroSD card slot, a USB host port, a 3.5mm audio jack, an IR receiver, and a few buttons. There’s nothing to do on the bottom of the board apart from a QR Core for the WeChat app. There are also several configuration jumpers, but I could not find any documentation about these and did not mess with the […]

Offline speech recognition MCU module comes with speaker, microphone, and UART connectors

offline voice recognition mcu module

We found out about Unisound US516P6 RISC microcontroller inside an offline voice assistant module last May. The module offers offline speech recognition for just $2 to $4, with good performance, and excellent privacy since no cloud service nor Internet connection is needed. That module requires some soldering, but if you’d prefer something easier to connect the “SU-10A” offline speech recognition MCU module comes with connectors for a speaker, a microphone, as well as UART connectivity to a host MCU if needed. “SU-10A” module specifications: MCU – Unisound US516P6 RISC microcontroller @ 240 MHz with FPU, DSP instruction, FFT accelerator, 242KB SRAM, 2MB flash Audio Built-in 3W mono Class AB power amplifier. 2mm pitch connector for speaker (4 Ohms up to 2.9W,  8 Ohms up to 1.8W) 2mm pitch connector for electret microphone Debugging/programming – UART port for serial console (5V or 3.3V supported) Host interface – 2mm pitch 4-pin connector […]

PICO DSP is an Arduino compatible ESP32 development board for audio and DSP applications (Crowdfunding)

PICO DSP ESP32 audio development board

ESP32 audio development boards have been around ever since ESP32 boards were introduced starting with Espressif Systems’ own “ESP32-LyraTD-MSC Audio Mic HDK“, and now ESP32 hardware and software have been certified for Amazon Alexa Voice Services. PICO DSP is another ESP32 development board for audio and digital signage processing (DSP) applications. Equipped with a Wolfson WM9878 stereo audio codec, the breadboard-friendly, Arduino compatible board includes two MEMS microphones, audio in and out jacks, a speaker header, plus other audio signals routed to a GPIO header. PICO DSP specifications: SiP – Espressif ESP32-PICO-D4 system-in-package with ESP32 dual-core WiFi 4 & BLE processor, 4MB SPI flash External storage/memory Original Edition – External 64 MB pseudo-static (PSRAM) chip, of which up to 8 MB is currently supported by ESP-IDF. Strawberry Edition – 16 MB of external NOR flash (note: the internal 4MB SPI flash will not be usable after selecting the NOR flash […]

ESP32-H2 RISC-V WiSoC announced with Zigbee 3, Thread, and Bluetooth LE 5.2

ESP32-H2 with Thread, Zigbee 3, BLE 5.2

Just a few days ago, we noted ESP32-H2 802.15.4 & BLE RISC-V SoC had shown up in the source code, and tried to derive specs and a block diagram from the info seeing it was similar to ESP32-C3, but swapping the WiFi radio for an 802.15.4 radio. We don’t need to guess anymore, as Espressif Systems has just announced ESP32-H2 RISC-V WiSoC with support for Zigbee 3.x, Thread 1.x through the 802.15.4 radio, as well as Bluetooth LE 5.2. So overall it’s very close to what we discussed from the information in the source code with ESP32-H2 highlights including: CPU – 32-bit RISC-V core (at up to 96 MHz) RAM – 256 KB SRAM Storage – External flash support Wireless connectivity IEEE 802.15.4 radio with Zigbee 3.x and Thread 1.x support, Matter protocol Bluetooth 5.2 (LE) radio designed in-house, with support for direct connection, Bluetooth Mesh, Bluetooth LE Audio Future […]