Espressif ESP-SR enables on-device speech recognition framework on ESP32-S3 and ESP32 WiSoCs

ESP SR ESP32 on device speech recognition AFE

Espressif ESP-SR is a speech recognition framework enabling on-device speech recognition on ESP32 and ESP32-S3 wireless microcontrollers with the latter being recommended due to its vector extension for AI acceleration and larger, high-speech octal SPI PSRAM. The ESP-SR framework was first released on December 17, 2021 with version 1.0, before the v1.20 update was introduced in March of this year, but I only found out about ESP-SR offline speech recognition solution through a tweet by John Lee showing an ESP-SR demo video by @ThatProject. Comrades of the world, liberate your hands from the chains of typing and touching germy switches! Embrace the revolutionary power of speech recognition with ESP32-S3 + ESP-SR. Let your words flow freely, for the proletariat shall not be silenced by keyboards or bourgeois input… pic.twitter.com/bm3udteB3o — John Lee (@EspressifSystem) July 15, 2023 I initially was confused since ESP32 boards have supported speech recognition for years using […]

Qualcomm S3 Gen 2 Sound Platform supports LE Audio and Auracast broadcast audio

Qualcomm S3 Gen 2 Sound Platform

The Qualcomm S3 Gen 2 Sound Platform (QCC5181) is a Bluetooth 5.4 audio solution designed for dongles and adapters with ultra-low latency (<20 ms) and support for the latest LE Audio and Auracast broadcast audio standards. The platform was introduced last year, but the company says it has now launched a “newly enhanced solution” optimized for gaming that “combines Snapdragon Sound and LE Audio to deliver ultra-low latency of less than 20ms for lag-free wireless audio with voice back-channel for in-game chat”. The new solution also focuses on USB dongles and adapters since few hosts support Bluetooth 5.4 at this time. Qualcomm S3 Gen 2 (QCC5181) Sound Platform specifications: CPU – Dual-core 32-bit microcontroller clocked at up to 80 MHz DSP – Qualcomm Kalimba DSP @ 240 MHz with 384 kB program RAM, 1,024kB data RAM Storage – External QSPI flash  Connectivity Bluetooth 5.4 qualified Bluetooth Low Energy, Bluetooth Classic, […]

Arylic H50 wireless stereo amplifier supports Airplay2, Amazon Alexa (Sponsored)

Arylic H50 wireless stereo amplifier

Arylic H50 is a new wireless stereo amplifier with an ESS9023p Sabre DAC and support for Airplay2, Amazon Alexa, and services such as Spotify Connect and Tidal Connect. It offers dual-band WiFi 4 connectivity, and Bluetooth 5.2 audio support through a Qualcomm QCC3040 SoC with aptX HD, supports 50W stereo speakers, and plenty of audio input sources from analog and digital audio ports to HDMI ARC, as well as NAS (DLNA) function and USB mass storage. Arylic H50 specifications: SoC – Qualcomm QCC3040 with 32-bit application processor @ 32 MHz, 32-bit system processor @ 32 MHz, Kalimba DSP @ 120 MHz, Bluetooth 5.2 and aptX HD support. DAC – ESS9023p Sabre DAC Display – 2.23-inch OLED display panel Connectivity 10/100M RJ45 port Dual-band (2.4GHz/5.0GHz) WiFi 4 (802.11 b/g/n) Bluetooth 5.2 with up to 15m range, suppport for aptX-HD, aptX-LL, aptX-AD, SBC, AAC Streaming Protocols – Works with Alexa, Spotify Connect, […]

OpenEarable open-source hardware earable platform leverages Arduino Nano 33 BLE Sense ecosystem

TECP Open Earable open source hardware device

OpenEarable is an open-source hardware earable, sometimes also called hearable, that fits around your ear and is based on the same u-blox NINA-B306 module found in the Arduino Nano 33 BLE Sense board. Besides the Nordic Semi nRF52840 Arm Cortex-M4-based Bluetooth LE module, the design also features a speaker and ultrasonic microphone, a 6-axis IMU and a pressure sensor, as well as the circuitry for the battery, two LEDs, and a push button. OpenEarable specifications: Wireless module – U-blox NINA-B306 module powered by a Nordic Semi nRF52840 Arm Cortex-M4F microcontroller @ 64MHz with 1MB Flash, 256KB RAM, Bluetooth 5.0 LE connectivity Audio – Built-in speaker and ultrasonic microphone (Knowles SPH0641LU4H-1) Sensors STMicro LPS22HBTR pressure and temperature sensor STMicro LSM6DSRTR 6-axis IMU with accelerometer and gyroscope USB – Micro USB port for power and programming Debugging – Solder pads for SWD interface Misc – Push button, charging LED, one programmable PWM […]

Sonatino – A Raspberry Pi Zero-sized ESP32-S3 audio board

Raspberry Pi Zero ESP32-S3 audio board

Lumination Labs’ Sonatino is an ESP32-S3 board designed for audio applications that follows the Raspberry Pi Zero dimensions so that it can be used with some of the cases designed for the Raspberry Pi Zero. The wireless audio board features Cirrus Logic WM8524 audio DAC and WM8782 audio DAC capable of 24-bit 192kHz stereo output and mono input respectively, a speaker amplifier and two pins for speaker connection, a 3.5mm audio jack, as well as a microSD card slot for the storage of audio or other data. Sonatino specifications: Wireless Module – ESP32-S3-WROOM-1 with SoC – ESP32-S3 dual-core LX7 microprocessor @ up to 240 MHz with Vector extension for machine learning Memory – 2MB PSRAM Storage – 16MB flash Connectivity – WiFi 4 and Bluetooth 5 LE/Mesh Storage – MicroSD card slot (SPI) Audio 3.5mm audio jack supporting input and output (TRRS, CTIA standard) Speaker connection: onboard pins, optional screw […]

Buy Arylic smart audio equipment up to 20% off during Mother’s Day sale (Sponsored)

Arylic smart audio mother day 2023

Arylic has just launched a Mother’s Day sale for their smart audio equipment where you can get up to a 20% discount with coupon mother20 on specific products namely Up2Stream Amp Sub multiroom wireless subwoofer amplifier board, SA100 50W wall-mounted amplifier, WBC65 multiroom wireless ceiling speaker, and the new Arylic BK501/BK651 2-way bookshelf speakers that were introduced last month. The company also offers up to 15% off with the coupon mother15 on a wider range of Smart Audio products that include the S10 WiFi music stream, Arylic A30+ 30W WiFi mini stereo amplifier, Arylic A50+ streaming amplifier (See Arylic S50+ review for details), and the Qualcomm QCC3350-based B50 Bluetooth stereo amplifier with a built-in audio transmitter. Other discounted smart audio products that qualify for the 15% discount part of the Mother’s Day sale include several Up2Stream boards for DIY connected speakers, Arylic S50+ pre-amplifier, and various speakers. Arylic products ship […]

Linux 6.3 release – Notable changes, Arm, RISC-V and MIPS architectures

Linux 6.3 release

Linux Torvalds has just announced the release of Linux 6.3 on the Linux Kernel Mailing List (LKML): It’s been a calm release this time around, and the last week was really no different. So here we are, right on schedule, with the 6.3 release out and ready for your enjoyment. That doesn’t mean that something nasty couldn’t have been lurking all these weeks, of course, but let’s just take things at face value and hope it all means that everything is fine, and it really was a nice controlled release cycle. It happens. This also obviously means the merge window for 6.4 will open tomorrow. I already have two dozen pull requests waiting for me to start doing my pulls, and I appreciate it. I expect I’ll have even more when I wake up tomorrow. But in the meantime, let’s enjoy (and test) the 6.3 release. As always, the shortlog […]

Offline voice recognition module supports Arduino programming, custom voice commands

Offline Voice Recognition Arduino

We’ve already covered inexpensive offline voice recognition modules based on US516P6 or TW-ASR ONE microcontrollers that allow people to add smarts to their projects without a network connection for improved privacy and lower latency. Those are great in theory, but at the time (April 2022) documentation was lacking or only in Chinese, and they were fairly hard to use based on some of the comments in my earlier posts. But today, I’ve noticed DFRobot is now selling the “Gravity: Offline Voice Recognition Sensor – I2C & UART” module with support for Arduino programming, and it looks fairly easy to customize as we’ll see further below. Gravity Voice Recognition DF2301QG module specifications: Voice recognition module – WS-2520-TR module with MCU – TBD 121 commonly used fixed voice commands, one-fixed wake word Support for 1 learned wake-word, 17 user-defined commands Audio Output – Built-in speaker and external speaker interface Input – Dual […]

EmbeddedTS embedded systems design