Espressif ESP32 RTOS solutions Alexa supported IOT board
ESP32-LyraTD-MSC, one of Espressif’s Audio Development Boards, is
an Acoustic Echo Cancelation (AEC) solution supporting voice
recognition, near-field and far-field voice wakeup. Audio files in
the format of AAC, FLAC, OPUS and OGG can be decoded and output
without quality loss. It also supports connection to Baidu’s DuerOS
and Amazon’s AVS (Alexa Voice Service) .
ESP32-LyraTD-MSC is based on ESP32-WROVER, a BT/Wi-Fi combo module,
and a digital signal processor (DSP) that features a
three-microphone array for noise reduction, echo cancelation,
etc.ESP32-LyraTD-MSC is integrated with peripheral devices and
consists of two development boards. The upper board mainly consists
of the microphone array, function keys and LED lights. The lower
board is integrated with power management, Wi-Fi and audio modules.
1.2. Hardware Resources
1. USB power input
Provides power supply to the whole system. It is recommended that
the system be connected to a power adapter for sufficient current
2. Battery interface
Provides power supply to the whole system when the USB power
interface is not used. The development board integrates the AP5056
power management IC to support battery charging.
3. Power switch
Turn on the switch and the system will be powered on. Turn off the
switch and the system will be powered off.
4. I²S port
An I²S bus transmits audio data between ESP32 and the DSP.
5. ESP32-WROVER module
This is a powerful, general-purpose, Wi-Fi+BT+BLE MCU module,
targeting a wide variety of applications ranging from low-power
sensor networks to the most demanding tasks, such as voice
encoding, music streaming and MP3 decoding.
6. MicroSemi DSP
This audio co-processor is used for Automatic Speech Recognition
(ASR) applications. It captures audio data from an external
microphone array and outputs audio signals through its
Digital-to-Analog-Converter (DAC) port.
7. I²C/SPI port
ESP32, as an I²C master, can access slave devices via the I²C bus.
ESP32, as an SPI master, can access the DSP to read/write data via
the SPI bus.
8. Earphone jack
Used for plugging in earphones.
9. Dual speaker output port
Supports two external speaker outputs.
10. Audio driver
This audio power amplifier sends audio signals from the DSP to
external speakers for playback.
11. DC-DC boost power supply
This fixed-frequency DC-DC voltage booster powers the audio driver.
12. Micro SD card
The development board supports a Micro SD card in SPI/1-bit/4-bit
modes, and can store or play audio files in the Micro SD card.
13. JTAG port
This standard JTAG interface is compatible with the ESP32
programming board and supports debugging functions.
14. CP2102N USB-UART Chip
An upgraded version of the CP2102 chip supports USB-to-UART
15. Programming port
This programming and debugging interface of ESP32 is compatible
with the ESP32 programming board. 16. USB Communication Port
This is a normal USB communication port between PC and ESP32
1. Voice Recognition
When ESP32-LyraTD-MSC is connected to DuerOS, ESP32 supports
“Alexa” as a wake-up phrase. Saying “Alexa” to the board prompts
the following response in Chinese: “nin hao you shen me fen fu”
(meaning: “Hi! How can I help?”). Users can talk to the board and
instruct it to play songs and news, or they can perform other
similar voice interactions. Here is an operation sample:
• Say “Alexa” to the board, and it will respond in Chinese by
saying: “nin hao you shen me fen fu” (meaning: “Hi! How can I
• Then, ask the following question in Chinese: “tian qi zen me
yang” (meaning “How is the weather?”).
• The board will respond in Chinese by saying: “jin tian yin zhuan
duo yun” (meaning “It’s getting from overcast to just cloudy
• The “Play” button can be used to play or pause the audio
• The “Vol+” and “Vol-” buttons can be used to adjust the volume of
the sound. Press them repeatedly until you reach the desired sound
3. Interactive Function
1. Voice Recognition
When the device boots up and connects successfully to the Wi-Fi
network, the blue LED light will blink once, indicating that it is
ready to accept commands.
Then, you can wake it up with the “Alexa” keyword. When it is
woken-up and listening, the LED light will glow in solid blue. When
it is in a “thinking” mode, the LED light will rotate.
We presently support “Tune-In Radio” as a music service. Other
music services are not supported as of yet. You can interact with
the board, using normal free speech. Some examples can be:
• “Alexa, what is the weather like?”
• “Alexa, sing a song”
• “Alexa, stop”
• “Alexa, tell me a joke”
• “Alexa, play Radio City on ‘Tune-In Radio’ ”
2. Buttons The “Vol+” and “Vol-” buttons can be used to adjust the
volume of the sound. Press repeatedly until you reach the desired