Voice Interaction Control

This tutorial is a comprehensive experiment combining multiple peripherals. You can first understand a single peripheral and then conduct this experiment.

1. Software-Hardware

• STM32F103CubeIDE

• STM32 Robot Development Board

Intelligent Voice Interaction Module: External

• Type-C Data Cable or ST-Link

Download or simulate the development board

2. Brief Principle

1. Hardware Schematic

2. Introduction to Voice Interaction Module

1. Introduction to Voice Interaction Module

CI1302 is a new generation of high-performance neural network intelligent voice chip developed by Qiying Tailun, integrating Qiying Tailun's self-developed brain neural network processor BNPU V3 and CPU core, with a system frequency of up to 220MHz, built-in SRAM up to 640KByte, integrated PMU power management unit and RC oscillator, integrated dual-channel high-performance low-power Audio Codec and multi-channel UART, IIC, IIS, PWM, GPIO, PDM and other peripheral control interfaces. The chip only needs a small number of peripheral devices such as resistors and capacitors to realize various intelligent voice product hardware solutions, with extremely high cost performance.

Using 3rd generation hardware BNPU technology, supporting neural networks such as DNN\TDNN\RNN\CNN and parallel vector operations, it can realize voice recognition, voiceprint recognition, command word self-learning, voice detection and deep learning noise reduction. The chip solution also supports multiple global languages such as Chinese, English, and Japanese, and can be widely used in home appliances, lighting, toys, wearable devices, industry, automobiles and other product fields to realize voice interaction and control and various intelligent voice solution applications.

The CI1302 chip has a brain neural network processor core (BNPU), supports offline NN accelerated computing and voice signal processing hardware acceleration, etc. The CPU main frequency can reach 220MHz, can be offline far-field voice recognition, built-in 2MB FLASH storage, and can support 300 command words.

2. Working Principle

The module adopts the command mode to wake up. The user needs to say the set wake-up word to activate the voice interaction module first. After activation, voice recognition can be performed. The default wake-up keyword of the factory firmware is "Xiaoya Xiaoya". If no voice is recognized after 20 seconds, the module will enter sleep mode and need to be re-awakened when used again.

When the CI1302 chip recognizes the corresponding voice entry, it will be sent out through the serial port and IIC interface, and feedback will be broadcast; the IIC chip will store the received voice command and send it out through the IIC slave protocol.

The module supports wake-up word modification, command word modification and custom entry. You can learn how to operate in the tutorials ** "2. Modify wake-up words and command words" and "3. Customize protocol entry production" ** tutorials.

3. Notes

Use 5V voltage for power supply. Exceeding 5V will damage the module

The usage scenario should be quiet. A noisy environment will affect the recognition effect

When speaking the entry, the voice should be loud and the speed should not be too fast. It is recommended to keep within 5 meters of the module

4. Hardware interface description

5. Control principle

Serial communication:

UART (Universal Asynchronous Receiver Transmitter) is a full-duplex universal asynchronous serial receiver/transmitter module, mainly used for printing program debugging information, communication between the host and the slave, and ISP program download. UART requires at least two data lines for both parties to transmit data in both directions at the same time. The simplest UART interface consists of three lines: TxD, RxD, and GND. Among them, TxD is used to send data, RxD is used to receive data, and GND is the signal ground line. Serial communication between two chips is realized through cross connection.

6. Physical connection diagram

Voice module wiring:

Motor wiring:

3. Control principle

Procedure Flowchart

After we power on, we need to wake up the voice interaction module first. After we say "Xiao Ya Xiao Ya" in voice, the voice module will send a data frame to the MCU, but the host does not need to send data back to the module. Then the voice module will voice broadcast "Yes". After we hear the broadcast, we can send voice commands to the voice module. The voice module and the MCU will send data frames to each other for communication.

Voice module: After receiving the voice command, send a data frame to the MCU serial port.

MCU part: Receive the data frame and then judge each byte of the data frame. Our data frame protocol is a hexadecimal byte stream, the format is: AA 55 00 XX FB (active broadcast), AA 55 FF XX FB (passive broadcast), where the frame header is the starting two bytes AA 55 and the frame tail is a fixed byte FB. The third byte in the middle controls the active and passive broadcast of the voice module, and the fourth byte is the command data we need. We return the fourth byte data, and then process the data to make the car give corresponding feedback. After the car has given feedback, the MCU will send the specified content to the voice module, and the voice module will broadcast it after receiving it.

3. Main functions

Function: Get_Cmd

Function: Change_RGB

4.Voice module instructions

5. Experimental phenomenon

After successfully downloading the program, connect the voice interaction module and wake up the voice interaction module. The wake-up method is to say "Xiao Ya Xiao Ya" to the voice interaction module, and the module will reply "Yes".

After we hear the reply, we can issue instructions to the car. This tutorial mainly controls the indicator lights on the expansion board, and the car motion control instructions are not available (The interval between issuing instructions and instructions needs to be within 20 seconds, otherwise the voice interaction module needs to be re-awakened.)

After each instruction operation, the voice interaction module will have a corresponding broadcast reply.

For program download, please refer to [Chapter 2: Development Environment Construction and Use → 2.6 Program Download and Simulation]

6. Voice Module Firmware Burning

xxxxxxxxxx
Burning the CI1302_ EN _ SingleMic_ V00916_UART1_115200_2M.bin file we provide can realize the relevant cases of this car's intelligent voice interaction module, without multiple burning.

1. Download the voice module firmware CI1302_ EN _ SingleMic_ V00916_UART1_115200_2M.bin we provide

2. Connect the Type-C of the voice module to your PC and push the slider of the voice module to pin 1. 1 represents the firmware burning of the voice chip (that is, the left side)

3. Open the voice chip firmware burning tool

4. Select the CI1302 chip and click "Firmware Upgrade"

5. Find the factory firmware “CI1302_ EN _ SingleMic_ V00916_UART1_115200_2M.bin” and select the corresponding firmware

6. Find the corresponding serial port number and click to select

7. Press the RST button on the board and the firmware will be automatically downloaded to the voice module（After the burning is completed, bend the slider to the right, that is, the pin2 position）