Google AIY Projects Kits are Easier to Use in 2018 with Raspberry Pi Zero WH and All Accessories Included

Tweet Google launched two AIY Projects kits last year with a Voice Kit that took a Raspberry Pi 3 to create a smart speaker, and a Vision kit for hardware accelerated computer vision using a Raspberry Pi Zero W board. Google reports the kits are popular, especially for STEM education,  but educators/parents had to buy the Raspberry Pi boards and micro SD cards themselves, as well as flash the firmware to the cards. So the company decided to redesign both kits to work with the Raspberry Pi Zero WH (RPi Zero W with headers), and include it inside the box with cable and pre-provisioned SD card, so kids can get started faster with experimentation with having to setup the kits. So that means we now have AIY Projects Voice Kit v2 with RPi Zero WH and micro SD card with firmware, as well as  AIY Projects Vision Kit v1.1 with RPi Zero WH, a Raspberry Pi Camera v2, and a micro …

Rockchip Reveals RK3308 & RK3326 Evaluation Boards for Smart Speakers and Smart Displays

Tweet Rockchip introduced RK3308 & Gemini quad core Cortex-A35 processors for smart AI solutions last month, and now the company has shared one more tweet about evaluation boards based on RK3308 and RK3329 (Gemini) processors for respectively smart speakers and smart displays. EVB-VA-RK3326 is a smart display evaluation platform powered by Rockchip RK3326 processor with four Cortex A35 core and a Mali-G31 MP2 GPU. It comes with a main board, a microphone array, some speaker, and a display. EVB-RK3308 looks very similar with instead feature a main board powered by RK3308 quad core Cortex A35 processor which supports  DDR3/DDR3L/LPDDR2/DDR2 memory, and comes with an audio codec with 8x ADC/2x DAC, support for 8-channel I2S/TDM, and USB 2.0 host + OTG interface(s). That’s the only information we have since the company has not published any details on their website. If you represent a company and are interested in developing products based on those solutions, you should be able to contact Rockchip …

ESP32-LyraT Speech Recognition Board Sold for 22 Euros

Tweet Just last week, we wrote about Espressif ESP-ADF Audio development framework that can be used to develop smart speakers and other audio applications with ESP32 boards. There was only one board with documentation at the time however: ESP32-Lyra-T. One tiny problem: it was not for sale just yet, but today Olimex has announced the board is in stock, selling it for 22 Euros. Main features: Wireless module – ESP32-WROVER module with WiFi and Bluetooth LE Audio Many audio inputs – Wi-Fi, BT-audio, DLNA, 3.5mm audio Line-in 3.5mm headphone jack 2x microphones Speaker connectors Storage – micro SD slot Debugging – JTGA header, USB UART Misc  – Touch sense buttons, function/boot/reset keys,  DIP switch for configuration Power – 5V via micro USB port; battery header + charger chip You’ll find documentation on Espressif website (user guide) as well as on Github’s ESP-ADF (getting started guide). Tweet Just last week, we wrote about Espressif ESP-ADF Audio development framework that can be used …

Banana Pi BPI-AI-Voice is a $169 Speech Recognition Development Kit based on MicroSemi ZL38063

Tweet SinoVoIP has just launched BPI-AI-Voice development platform for speech recognition on Aliexpress for $169, and excluding the different PCB color, it is a clone of the official $299 Microsemi AcuEdge Development Kit for Amazon AVS, which is based on MicroSemi ZL38063 audio processor and comes with two microphones. BPI-AI-Voice key features: Audio Processor – MicroSemi ZL38063 Storage – U2 SPI flash to store ZL38063 firmware Audio 4x on-board digital microphones (AKU441) supporting a 2 microphone configuration for 180° and 360° audio pick-up. 2x low cost class D audio amplifier (NCP2820) Expansion Headers JMMA1 audio header for digital microphone, analog out, and 3 GPIOs JM1-4 digital microphone headers for off-board microphones 40-pin P2 header to connected to Raspberry Pi 3  (I2S, SPI and 8x GPIO used) Debugging – JAIB2/2 auto tuning headers, micro USB port. Power Supply – 5V via micro USB port Dimensions – 70 mm × 66 mm Temperature Range – −40° C to 85° C The original …

Espressif ESP-ADF Audio Development Framework for ESP32 Supports Baidu DuerOS, and Soon Amazon Alexa, Google Assistant, etc…

Tweet Espressif Systems have been working on audio applications like Smart Speakers based on ESP32 WiSoC with hardware development kits like ESP32-LyraTD-MSC Audio Mic HDK, and I could test it with Baidu DuerOS using Mandarin language. However, at the time (February 2018), there was not much else that could be done with the hardware kit, since no corresponding ESP32 audio software development kit had been made available. This has now changes since Espressif has just released ESP-ADF Audio Development Framework on Github. The framework will support the development of audio applications for the Espressif Systems ESP32 chip such as: Music player or recorder handling MP3, AAC, WAV, OGG, AMR, SPEEX … audio formats Play music from network (HTTP), storage (SD card), Bluetooth A2DP/HFP Integration with Media services such as DLNA, Wechat, etc.. Internet Radio Voice recognition and integration with voice services such as Alexa, DuerOS, Google Assistant As we can see from the diagram above, the first release supports Baidu …

Samsung Aurora Smart Speaker Prototype is Powered by a Smartphone, Features an Hologram-like Character

Tweet Samsung Electronics has showcased a smart / A.I. speaker prototype at SXSW 2018 trade show last month, that can be manufactured at low cost since it relies on a smartphone to provide a processor, microphone, and other equipment. The smart speaker also uses the smartphone’s screen to show an hologram to greet users. Meet Samsung “Aurora”. The smartphone is placed horizontally (blue above) in a slot in the upper part of the speaker, and a hologram-like character floats above the Bluetooth speaker included of the kit. The part on the top surface is an optical mechanism using the smartphone’s camera for image recognition. The smart speaker also charges the phone, but it’s unclear how you are supposed to answer phone calls once it is inserted in the speaker… The concept looks similar to Vinclu Gatebox which we covered in 2016, except it relies on a smartphone. Samsung is said to have started development six months ago, and Aurora is …

ReSpeaker Core v2 is a 6-Mic Array Audio Development Kit Powered by Rockchip RK3229 Processor

Tweet Seeed Studio launched ReSpeaker Core board designed for voice interaction in 2016. The board was based on a Mediatek MT7688 MIPS WiSoC running OpenWrt, and came with a single built-in microphone, although a microphone array board with 7 microphones and 12 LEDs was also offered as option. The company is now back with a more powerful update of the board – called ReSpeaker Core v2 – featuring Rockchip RK3229 quad core Cortex A7 processor, running Debian Linux, and with 6 on-board microphones. Beside WiFi connectivity, the board also adds Ethernet and Bluetooth 4.0, as well as a USB hot port compared to the previous version. ReSpeaker Core v2 specifications: SoC – Rockchip RK3229 quad core Cortex A7 processor @ up to 1.5 GHz with Arm Mali-400MP2 GPU System Memory – 1GB DDR3 RAM Storage – 4GB eMMC flash, micro SD card slot Video Output – HDMI 2.0 (but drivers not available yet) Audio 6x Microphone Array with 5 meters …

Rockchip Unveils RK3308 & Gemini Cortex-A35 Processors for Smart Speakers

Tweet Rockchip has posted a tweet about smart speakers, specifically about Midea AI speaker based on Rockchip RK3229, but the second image is what caught my eyes, as it reveals two new Arm Cortex A35 processor designed for “Smart AI solutions”, namely RK3308 and “Gemini” Processor. Rockchip RK3308 “mainstream” processor specifications: CPU – Quad core Cortex A35 processor GPU – TBD (maybe none?) Audio Integrated 8-ch ADC and hardware VAD (Voice Activity Detection) module Multi-channel PDM/I2S/TDM audio interface Rockchip Gemini “high-end” processor specifications: CPU – Quad core Cortex A35 processor GPU – Mali Dvalin MP2 GPU Audio – “high-end smart audio solution”; multi-channel PDM/I2S/TDM audio interface Video I/O – LCD screen & camera support Rockchip will provide support for Android Thing and Linux for the processors, as well as integration with MIC arrays boards and popular voice services such as Amazon Alexa, Google Assistant,  Baidu DuerOS, and others. Arm Cortex A35 64-bit processor was unveiled in 2015 as a replacement …