smart speaker News - Page 5 of 9 - CNX Software

March 2, 2020March 2, 2020 by Jean-Luc Aufranc (CNXSoft) - 8 Comments

Paranoid Mutes or Jams your Smart Speaker’s Microphone for Improved Privacy

Panaroid Smart Speaker Microphone Jammer

Smart speakers normally work by constantly listening to a wake-word, that is processed locally, before listening to your more complex command, and send the audio to the cloud for processing. That means most of the time no data is sent to the cloud, as continuously processing audio in the cloud would not be resource-efficient. However, in isolated cases, the company may want to listen to audio samples to improve their product(s) and it’s possible since the hardware is perfectly capable of doing this. Alternatively, hackers could always access your smart speaker. So if you worry about your privacy, while still wanting the convenience of using a smart speaker, a third-party solution controlling the microphone should protect your privacy. Pleasant Solutions “Paranoid” aims to provide such privacy solution by taking control of the microphone on your smart speaker. Due to the various smart speaker designs and features in the market, three […]

February 15, 2020 by Jean-Luc Aufranc (CNXSoft) - 15 Comments

Amlogic A113L Dual-Core Cortex-A35 Processor Targets Smart Audio and IoT Applications

Over two years ago, we reported about Amlogic A111, A112, A113 processors designed for audio applications such as smart speakers. A111 features four Cortex-A5 32-bit core, while A112 and A113D/A113X processors come with four Cortex-A53 cores instead. We have not heard much about those since then, but all those processors are still listed on Amlogic website, A112 is supposedly used in Xiaomi AI smart speaker, and Amlogic A113X1 Far-Field Dev Kit is still listed on Amazon’s list of devkits for Alexa voice service, but currently out of stock. Amlogic has been working on a more cost-efficient processor for smart audio and IoT applications with Amlogic A113L dual-core Cortex-A35 processor shown as Meson A1 in the Linux source code. It was just added in Linux 5.5. We don’t have much information about it, but it’s interesting as it’s the first Cortex-A35 processor from the company, and it targets the same smart […]

December 20, 2019December 27, 2019 by Jean-Luc Aufranc (CNXSoft) - 9 Comments

UNISOC V5663 Arm Cortex-M33 AIoT SoC Comes with 802.11 b/g/n/ac WiFi 5, Bluetooth 5.1

UNISOC has launched a new processor for AIoT (Artificial Intelligence + IoT) applications with V5663 dual-core Cortex-M33 processor, supports for dual-band WiFi 5, Bluetooth 5.1, and audio features such as a voice activity detector and microphone array support which should make it ideal for smart speakers, and other smart audio applications. UNISOC V5663 WiSoC specifications: CPU Arm Cortex-M33 processor @ 442 MHz with TrustZone, 32KB I-cache, 32KB D-Cache for application code Arm Cortex-M33 processor @ 416 MHz for WiFI and Bluetooth Memory – Built-in SRAM + external PSRAM interface Storage – eMMC, SDXC interfaces Connectivity – Dual-band 802.11 b/g/n/ac WiFi 5 2×2 MIMO Bluetooth 5.1 dual-mode (Classic + LE) Mesh Networking for WiFi and Bluetooth Indoor Positioning – WiFi RTT, Bluetooth direction finding (AoD / AoA) Audio – Voice Activity Detector (VAD), PDM and I2S/PCM interfaces Peripherals: USB 2.0 / 3.0, eMMC I2C, SPI, HS SPI, UART GPIO, PWM IR […]

September 6, 2019 by Jean-Luc Aufranc (CNXSoft) - 10 Comments

NXP i.MX RT106F & RT106A/L Cortex-M7 Processors Target Offline Face Recognition & Smart Audio Applications

NXP i.MX RT crossover processors combine real-time capabilities of microcontrollers with the performance of application processors thanks to an Arm Cortex-M7 core clocked at 528 MHz and more. The performance is indeed impressive as shown by Teensy 4.0 benchmarks, but so far NXP i.MX RT processor targeted general purpose applications. The company has now introduced three new crossover processors designed for AI applications. NXP i.MX RT106F is designed for offline face recognition and expression Identification, while RT106L and RT106A are made for local and cloud-based embedded voice applications. NXP i.MX RT106F Processor Highlights of the processor: CPU – Arm Cortex-M7 @ 600 MHz (3020 CoreMark/1284 DMIPS) Memory – 1 MB On-Chip SRAM plus up to 512 KB configurable as Tightly Coupled Memory (TCM) External memory interface options – NAND, eMMC, QuadSPI NOR Flash, and Parallel NOR Flash Real-time, low-latency response as low as 20 ns Industry’s lowest dynamic power with […]

September 6, 2019September 6, 2019 by Jean-Luc Aufranc (CNXSoft) - No Comments

MediaTek MT8516 2-Mic Development Kit is Designed for Alexa Voice Service (AVS)

MediaTek has just announced the MT8516 2-mic development kit for Alexa Voice Service (AVS) that aims to help developers build voice-assistant products faster, at reduced costs, and with advanced features such as multi-room music (MRM). The kit is based on MT8516 quad-core ARM Cortex-A35 application processor, which integrates audio front-end and post-processing technologies, as well as Wi-Fi and Bluetooth connectivity. MediaTek MT8516 2-mic development kit specifications: SoC – MediaTek MT8516 quad core Cortex-A35 processor @ 1.3 GHz System Memory I/F – LPDDR2, DDR3, LPDDR3, DDR3L Video Output – HDMI 1.4 with ARC Audio 2x DMIC Amazon Alexa support MediaTek PowerAQ Multi-Room Audio 2x 4-channel I2S S/PDIF TDM in/out up to 8 channels 2-channel PDM inputs 2-channel audio DAC and DAC Connectivity – Fast Ethernet, WiFi 4, Bluetooth 4.2 LE USB – 1x micro USB 2.0 OTG port MediaTek MT8516 supports the following technology components, although note that a license […]

September 2, 2019September 2, 2019 by Jean-Luc Aufranc (CNXSoft) - 1 Comment

Espressif ESP-Skainet Voice Assistant Offers Wake Word Engine and Speech Commands Recognition for Embedded MCUs

Skynet is finally here! OK, not quite, but at least we do have ESP-Skainet now courtesy of Espressif Systems. ESP-Skainet is an intelligent voice assistant that features the company’s WakeNet wake word engine and MultiNet speech commands recognition. WakeNet WakeNet has been specifically designed for low-power MCUs such as ESP8266 or ESP32 with a low memory footprint (20KB RAM) and a high calculation speed that makes it capable of achieving a high success rate for wake word detection even in noisy environments. Tested in the company’s upcoming LyraT-Mini audio board that combines an ESP32-WROVER-B module and a codec, WakeNet achieves a 97% wake word success rate at a one-meter distance, and 95% three meters away in a quiet environment. ESP-Skainet wake-up engine ships with the wake-up word “嗨乐鑫” (Hi Lexin), which translates in “Hello Espressif”, and supports up to five wake words. You can use customize wake words as well, […]

August 30, 2019 by Jean-Luc Aufranc (CNXSoft) - 19 Comments

Using Sony PS3 Eye Camera as an Inexpensive Microphone Array

Almost exactly two years ago to the day, we published an article showing how microphone arrays performed against a single USB microphone, and the latter started to have a poor wake word detection success rate at around 3 meters array even in a silent room, and it got worse with white noise or background music, while the microphone arrays would pick up the wake word with a much higher success rate in all conditions. The price of smart audio development kits varies a lot from $500 for Intel Speech Enabling Developer Kit to $129 for an Allwinner R18-based 3-Mic Far-Field Amazon AVS Development Kit, and $99 for ReSpeaker Core v2. If you’ve already got a Raspberry Pi 3/4 board, you can get cheaper options such as ReSpeaker 4-Mic Array for $25, but nothing beats the price of Sony PS3 Eye camera that comes with a 4 microphone array and sells […]

August 19, 2019August 19, 2019 by Jean-Luc Aufranc (CNXSoft) - 43 Comments

Allwinner R328 Smart Speaker & System-on-Module Spotted in China

Earlier this year, Allwinner introduced some AIoT (AI + IoT) processors including Allwinner R328 dual-core Cortex-A7 processor for “low-cost voice interaction solutions” aka low-cost smart speakers. I did not pay too much attention at the processor at the time, but since then, the company has released a product brief with some more details about the processor. We can see it integrates 64MB to 128MB DDR3 memory which should be enough to run Linux without external memory, and truly provide a low-cost solution for smart speakers, and I was told the chip may cost around $3. I was also asked whether Allwinner R328 smart speakers were already shipping. A Google search in English did not help, so I had to switch to Chinese, and after visiting several sites, I could see some Allwinner A328 platforms including a smart speaker and a system-on-module were showcased at some event in China. We’ve got […]