audio News - CNX Software - Embedded Systems News

July 30, 2021July 30, 2021 by Jean-Luc Aufranc (CNXSoft) - No Comments

Amazon Alexa certified ESP AFE leverages ESP32-S3 AI & DSP instructions

While most Amazon Alexa certified products are hardware designs, Amazon website also includes a Software Audio Front End (AFE) Dev Kits section that lists software algorithms that optimize audio detection in noisy environments, and the latest addition is Espressif’s Audio Front-End algorithms, or ESP AFE for shorts, that have recently been qualified for Amazon Alexa devices. It’s not the first Alexa certified solution from Espressif Systems, as both companies have worked together in the past with audio products like the ESP32-PICO-V3-ZERO Alexa Connect Kit Module or ESP32-Vaquita-DSPG board The algorithms were created by Espressif’s AI Lab team who used the AI and DSP instructions inside ESP32-S3 processor to optimize the code. The algorithms only utilized 12 to 20% of the CPU, as well as 220 KB of internal and 240 KB of external memory, leaving extra resources for other applications running in the wireless SoC. The ESP AFE is said […]

July 16, 2021 by Jean-Luc Aufranc (CNXSoft) - No Comments

Innatera neuromorphic AI accelerator for spiking neural networks (SNN) enables sub-mW AI inference

Most AI accelerators currently rely on CNN (convolutional neural network) to perform AI inference in a much faster and efficient way than on CPU cores, or even GPUs. But there’s another type of neural network, namely spiking neural networks (SNN) that uses the timing of spikes in an electrical signal to perform pattern recognition tasks in a way similar to neurons in the brain. The claims in terms of efficiency are quite unbelievable, with up to 10,000 times more performance per watts than in microprocessor and digital accelerometer, 500 times lower energy, and 100 times shorter latency. Several companies are working on neuromorphic AI accelerators for spiking neural networks, with notably Prophesee focusing on image processing, and Innatera that is working on an ultra-low-power AI accelerator handling audio, health, and radar for sound and speech recognition, vital signs monitoring, elderly person fall sensors, etc… Innatera recently provided additional information about […]

April 7, 2021 by Jean-Luc Aufranc (CNXSoft) - 4 Comments

Google releases the source code for Lyra low bitrate speech codec

Google showcased Lyra audio codec for high-quality voice calls at a low 3 kbps bitrate last February. But at the time, it was only for our eyes to see, or rather our ears to listen to, as the company did not release any software, but only audio samples with excellent quality compared to Speex @ 3 kbps or Opus @ 6 kbps. Google has now released the Lyra source code, written in C++ for optimal speed, efficiency, and interoperability and relying on both the Bazel build framework and the GoogleTest framework. The beta release provides the tools and APIs needed for Lyra encoding and decoding, and is currently optimized for the 64-bit Arm Android platform, but can also be run in Linux x86 64-bit. There is also an example app – lyra_android_example – that integrates with the Android NDK and offers a minimal GUI with two buttons to either record […]

March 9, 2021March 9, 2021 by Jean-Luc Aufranc (CNXSoft) - 1 Comment

Bluetrum AB32VG1 board features AB5301A Bluetooth RISC-V MCU, runs RT-Thread RTOS

Bluetrum, a Shenzhen-based fabless company focusing on audio chips, has designed the AB32VG1 board based on its AB5301A Bluetooth RISC-V MCU for general-purpose and audio applications. The board comes with a MicroSD card, a USB port, a 3.5mm audio jack, and Arduino UNO compatible headers for easy prototyping. Bluetrum AB32VG1 board preliminary specifications: MCU – Bluetrum AB5301A RISC-V MCU @ 120 MHz (overclockable to 192 MHz) with 192KB RAM, 1MB flash, Bluetooth 5.0 connectivity and FM radio; LQFP48 package Storage – MicroSD card slot Audio – 3.5mm audio jack, 3-pin microphone header Connectivity – Bluetooth 5.0 with PCB antenna USB – USB 2.0 host port, USB Type-C port for power and programming Expansion – Arduino UNO header with 1x I2C, 6x ADC, 6x PWM Misc – IR receiver, 3x user buttons, 1x reset button, RGB LED, power LED, status LEDs, various configuration jumper Power Supply – 5V via USB Type-C […]

March 7, 2021March 6, 2021 by Saumitra Jagdale - No Comments

QuickLogic’s Hearable Reference Design enables Alexa Voice-Initiated Devices

Working with QuickLogic's Smart Hearable Reference Design

Last year we saw QuickFeather board featuring EOS S3 Cortex-M4F MCU with embedded FPGA, which was a crowdfunding project. This year the company has launched its smart hearable reference design based on a similar processor by QuickLogic. The device is dedicated to “Voice-Initiated, Hands-Free, Alexa Built-In Devices with Close-Talk Support.” QuickLogic’s smart hearable reference design is based on the company’s Open Reconfigurable Computing (QORC) which supports a complete open-source set of development options for the MCU and FPGA devices. It is also built on the EOS S3 Voice Processor and the QuickFeather open source development kit. This can enhance the user experience with a longer battery life of the device. The EOS S3 Arm Cortex- M4 processor features Low Power Sound Detection (LPSD) technology along with DSP Concepts’ TalkTo noise suppression and beamforming technology for the directional transmission of signals. It also comes with Alexa Wake Word engine technology, an […]

February 28, 2021February 28, 2021 by Jean-Luc Aufranc (CNXSoft) - 18 Comments

Lyra audio codec enables high-quality voice calls at 3 kbps bitrate

We’re often writing about new video codecs like AV1 or H.266, and recently, we covered AVIF picture format that offers an improved quality/compression ratio against WebP and JPEG, but there’s also work done on audio codecs. Notably, we noted Opus 1.2 offered decent speech quality with a bitrate as low as 12 kbps when it was outed in 2017, the release of Opus 1.3 in 2019 improved the codec further with high-quality speech possible at just 9 kbps. But Google AI recently unveiled Lyra very low-bitrate codec for speech compression that achieves high speech quality with a bitrate as low as 3kbps. Before we go into the details of Lyra codec, Google compared a reference audio file encoded with Lyra at 3 kbps, Opus at 6 kbps (the minimum bitrate for Opus), and Speex at 3 kbps, and users reported Lyra to sound the best, and close to the original. […]

February 17, 2021February 18, 2021 by Jean-Luc Aufranc (CNXSoft) - 3 Comments

MaaXBoard Nano SBC targets audio and edge IoT with NXP i.MX 8M Nano SoC

Avnet has launched several Raspberry Pi-inspired MaaXBoard SBCs based on NXP i.MX processors through their Embest subsidiary starting in 2019 with MaaXBoard single board computer powered by an NXP i.MX 8M processor, and following by MaaxBoard Mini with NXP i.NX 8M Mini SoC in 2020. The latest model is MaaXBoard Nano SBC with an NXP i.MX 8M Nano quad-core Cortex-A53 processor best suited to audio and edge IoT applications. MaaxBoard Nano SBC specifications: SoC – NXP i.MX 8M Nano quad-core Arm Arm Cortex-A53 processor @ up to 1.5GHz with Cortex-M7F core @ 750MHz, 2D GPU, 3D GPU, but no video hardware decoding. System Memory -1GB DDR4 SDRAM Storage – 16GB eMMC flash, 256 Mbit QSPI Flash, MicroSD Slot Display Interface – MIPI DSI display Interface Audio – 3.5mm audio jack, 4x built-in microphones Camera I/F – MIPI CSI Camera Interface Networking – Gigabit Ethernet, 802.11 b/g/n/ac WiFi 5, Bluetooth 4.2/5 […]