HLK-V20 is the latest high-performance pure offline speech recognition module for a large number of pure offline control scenarios and products. It can be widely and quickly applied to smart homes, various smart small appliances, 86 boxes, toys, lamps, industrial, medical, Products that require voice control, such as the Internet of Things, automobiles, security and lighting.
The module uses a 32bit RSIC architecture core, and adds a DSP instruction set specifically for signal processing and speech recognition, an FPU arithmetic unit that supports floating-point operations, and an FFT accelerator. The audio signal is trained and learned through the neural network to improve the voice signal Recognition ability.
The solution supports offline recognition of 150 local commands, freely customizable wake-up words, command words and response broadcast words, and has a wealth of peripheral interfaces.
Product Parameter:
Processing kernel:
32bit RISC core, running frequency 240M
Support DSP instruction set and FPU floating point operation unit
FFT accelerator: supports up to 1024 points of complex FFT/IFFT operations or 2048 points of real FFT/IFFT operations
Customized voice algorithm operator
Storage:
Support 1 analog Mic input
Support dual-channel DAC output
Support 12S input/output
Power supply and clock:
Built-in 5V to 3.3V, 3.3V to 1.2V LDO power supply for the chip
RC 12MHz clock source and PLL phase-locked loop clock source
Set POR (Power on Reset), low voltage detection and watchdog
Peripheral interface:
Support up to 10 GPIO
All GPIO can be configured as external interrupt input and call source
1 standard SPI Master interface, the highest speed car is 30MHz
1 SPI Slave interface with a maximum rate of 30MHz
1 full-duplex UART maximum rate 3Mbps
I I2C master/slave controller with a maximum speed of 400kHz
2 PWM outputs
1 12-bit SAR-ADC maximum 450Khz sampling rate
Custom voice (provided by customers, customized by factory)
Customized start-up announcement
Custom voice wake-up words
Custom voice command words
Custom TTS voice broadcast
Support up to 10 wake-up-free words (no need to wake up, direct recognition of command words)
The module has a wealth of system peripherals, including UART/I2C/SPI/PWM/I2S/DAC/GPIO/DMic/AMic
The module has 16 pins, including power amplifier output, differential input and serial port.
B8 (I): General purpose input/output
B7 (I/O): General purpose input/ output
B6 (I/O): General purpose input/ output
A27 (I/O): General purpose input/ output
A26 (I/O): General purpose input/output
SPK+(0): P terminal of power amplifier differential output
SPK-(0): N terminal of power amplifier differential output
VCC (PWR): power supply (3.3V-5V)
GND: GND
B2 (I/O): General purpose input/output
B3 (I/O): General purpose input/output
A25 (I/O): General purpose input/output
MIC-(I): MIC1 differential input N terminal
MIC+(I): MIC1 differential input P terminal
RX (I/O): Uart rx
TX (I/O): Uart tx
Function description:
HLK-V20 supporting test board is convenient for customers to intuitively experience voice control LED lights, serial port output protocol data after voice recognition.
Demo firmware supports voice wake-up words
Local voice commands to control LED lights
1. Use the USB data cable to power the test board, and connect the speaker and microphone.
2. After the module wakes up, use the command word "Turn on the air conditioner", LED3 on the bottom panel will light up, use the command word "Turn off the air conditioner", and the LED3 light will go out.
3. Use the command word "turn on the light" to turn on the LED2 of the Xin board, and use the command word "turn off the light" to turn off the LED2. Use the command word "Turn on the switch", the bottom panel LEDI lights up, use the command word "Turn off the switch", LEDI lights off.
Serial port output protocol data after local voice recognition
1. Use a USB data cable to power the test board, connect to speakers and microphones,
2. Open the serial port tool on the PC, and the Shenkou configuration is 115200-8-1.
3. Use the wake-up word to wake up. After the module recognizes the wake-up word and command word, the serial port outputs protocol data
Application example:
The module can be used with the serial port of the MCU. After the voice module recognizes the voice command, it outputs protocol data through the serial port, and the MCU serial port receives the voice module serial port data for processing.
The module can be used as the main control, used in voice control of LED lights, voice control of Wei electrical appliances and other scenarios,
The module can be used in the following scenarios: voice-activated chandeliers, voice-activated wall lights, voice-activated bath heaters, voice-activated switches, voice-activated spotlights, voice-activated ceiling lamps, voice-activated desk lamps, wall switches, shop control panels, LED desk lamps, panels, clothes dryers, electric curtains, Fans, smart door locks, sweeping machines, smart Taiwan hits, smart air conditioners, smart teapots, story machines, smart curtains, smart fans, sound energy speakers, car audio controls.
Current waveform:
Standby power consumption:
5V power supply, average standby power consumption 63mA
Wake-up recognition power consumption:
5V power supply, with speaker (8Ω 1W)
Wake-up recognition, average power consumption 77mA
Package Included:
1 X HLK-V20 Serial Port IIC I2C
1 X microphone
1X speaker