With the extensive use of high-tech skills in the military field, weapons and equipment are gradually being developed in high, sophisticated, and sophisticated areas. Because of the long training time, high training cost, and narrow training space, traditional military exercises often fail to achieve the expected role of practice, and can no longer satisfy the needs of modern military exercises. To solve the above problems, imitation exercises came into being.
In order to further improve the role of practice, this article uses a smart voice interactive chip to plan a teaching and playback system that imitates an exerciser. The teaching system provides the operator with a vivid demonstration of the standard operation process and the corresponding operation appearance, which greatly shortens the practice time for the operator and improves the practice effect. The playback system records the passwords, sound intensity, actions, time, operation appearance, etc. of each operator during the operation training process, and then repeats the training process after the operation training, so that the operator can correct his own problems in time. The teaching system can also be understood as the playback of the standardized operation practice process. The system does not require the support of virtual reality skills and can be completed on a small embedded system.
1 System principle
The imitation exerciser consists of a measurement and control computer and multiple slave devices. As shown in Figure 1. Only one slave device is introduced here. Its hardware system is mainly composed of a measurement and control computer, an Arduino mega2560 controller, a voice recognition unit, a sound intensity detection unit, a voice component unit, a panel control unit, and an instrument panel. The panel control unit is more complicated and contains a variety of control circuits. In the simulation exercise, it acts as the slave device under the control of the Arduino mega2560 controller to complete the entire exercise process. In the teaching and playback system, the other party only completes the practice of the operation operation. The detailed circuit plan will not be introduced here.
The voice recognition unit is used to identify the operator's operation password; the sound intensity detection unit is used to detect the size of the sound intensity and used as the basis to determine which slave device operator's password; the Arduino mega2560 controller is used to supervise the status of each component of the instrument panel to identify The actions of the operator, and then complete the record of the operation practice process. The operation appearance of each instrument is compiled in advance according to the operation action and need not be recorded. During the operation playback process, the measurement and control computer reproduces the recorded operation process through the Arduino mega2560 controller of the corresponding slave device according to the recorded data.
2 Unit system planning
2.1 Voice recognition unit planning
At that time, the development of speech recognition skills was very rapid, according to the type of recognition target can be divided into specific and non-specific person speech recognition. A specific person refers to a person whose recognition target is specialized. A non-specific person refers to a recognition target aimed at most users. It is usually necessary to collect more of their own voices for recording and practice, after learning, and then reach a higher recognition rate.
The LD3320 speech recognition chip selected in this article is a chip based on non-specific person speech recognition (Speaker Independent AutomaTIc SpeechRecogniTIon, SI ASR) skills. The chip integrates high-precision A / D and D / A interfaces, eliminating the need for external FLASH and RAM, that is, it can complete voice recognition, voice control, and man-machine dialogue functions, providing a true single-chip voice recognition solution . Moreover, the list of recognized key words can be edited dynamically.
The voice recognition unit selects ATmega168 as the MCU to control the LD3320 to complete all tasks related to voice recognition, and upload the recognition results to the Arduino mega2560 controller via the serial port. All operations on the LD3320 chip must be completed through the operation of the register. There are two methods for register read and write operations (standard parallel method and serial SPI method). Choose parallel method here, connect the data port of LD3320 with I / O port of MCU.
The voice recognition process uses the suspension method. The operation process is divided into initialization, writing key words, beginning recognition, and response suspension. The MCU program is written in ARDUINO IDE. After the debugging is completed, it is burned through the serial port. The LD3320 is controlled to complete the voice recognition, and the recognition results are uploaded to the Arduino mega2560 controller.
2.2 Sound intensity detection unit planning
When performing voice recognition, it is necessary to determine the password of a certain slave operator. Therefore, a sound intensity detection unit circuit is planned for this circuit. This circuit only needs to be able to identify the size of the relative sound intensity, and there is no need to detect the sound level. low.
The capacitive MIC sound sensor converts the external sound signal into an electrical signal, which is expanded by the NE5532 expansion circuit, and converts the input weak audio signal into a voltage signal with a certain amplitude. The voltage signal is installed by the AC / DC effective value conversion circuit. After the change, it is expanded again, and finally the A / D of the Arduino mega2560 controller is used for sampling. During this period, D1 is connected to the A / D of the Arduinomega2560 controller, and INT1 is connected to the external stop of the Arduinomega2560 controller. 1. When the external sound signal is greater than the preset threshold, the transistor turns on and the INT1 terminal changes from high level to low level. External suspension, the controller responds to the suspension and performs A / D sampling. The sampled data is retained after the average filtering, and the sound intensity data is uploaded when the computer to be measured and inquired is queried.
2.3 Planning of voice components
TTS (Text To Speech) text-to-speech skills are the trend of human-machine intelligent dialogue. The voice system based on TTS skills can detect and form voice for broadcast at any time without prior recording, and then greatly reduce the workload of system maintenance. Using this skill, the voice chip pronunciation can be controlled by MCU or PC.
This article uses SYN6658 Chinese voice composition chip for voice composition. SYN6658 accepts the text data to be composed through the UART interface or SPI interface communication method, and completes the conversion of text to speech (or TTS speech). The controller and the SYN6658 voice component chip are connected through a UART interface. The controller sends control commands and text to the SYN6658 voice component chip through serial communication. The SYN6658 voice component chip combines the received text into a voice signal output, and the output signal is passed through the LM386 After the power amplifier is expanded, it is connected to the speaker for broadcast.
The SYN6658 voice composition circuit uses the typical use circuit provided by the chip hardware data manual for planning. It will not be described here. The power expansion circuit uses the audio power amplifier LM386 produced by National Semiconductor for expansion.
Initially initialize the voice composition, including speaker selection, digital processing strategy, speech rate adjustment, intonation adjustment, volume adjustment, etc.
Because the system needs to imitate multiple people's pronunciations, different slave devices set different speakers and intonation and speech rate to facilitate the distinction. After initialization, wait for the voice composition command of the measurement and control computer. After receiving the command, the chip will send a 1-byte status back to the host computer. The host computer can judge the current operating status of the chip based on this return.
3 System software planning
The software planning of the teaching and playback system includes the software planning of the measurement and control computer and the software planning of the Arduino mega260 controller of each slave device.
The measurement and control computer is the control center of the entire system. Its software is written in C #. In the teaching and playback system, the operation data is mainly recorded in order to accurately playback the operation process according to the recorded data. The data required to record include: each From the operation password, operation action, password and action time of the equipment operator, the corresponding operation appearance of each operation. In order to simplify the recording of data, each event code is compiled in advance, and the recording process only records the code, which greatly improves the efficiency of the program.
In the course of operation practice, the measurement and control computer controls and polls the lower computer every 50 ms, and records the reaction data. When the data is recorded, 50 ms is used as a unit. Use the timer to control the time. During the playback process, the current time and the recorded time are first compared. When the recorded time coincides with the current time, the measurement and control computer controls the lower computer to perform the matter and complete the playback of the matter.
The Arduino mega2560 controller is used to accept the control instructions of the measurement and control computer and execute the instructions, read the results of voice recognition, collect and process the sound intensity data, and control the voice composition unit for voice composition. The Arduinomega2560 controller selects the serial port suspension method for command acceptance.
As long as the instruction is correctly received, the results will be fulfilled and returned. If the measurement and control computer does not receive the returned results within the limited time, it indicates an error, and the measurement and control computer needs to be sent from the beginning.
This article uses a smart voice chip to plan a teaching and playback system that imitates an exerciser. The system does not require the support of the prevailing virtual reality skills, and can be operated only under the control of the MCU. The system can also be completed on small portable devices and has an excellent vision for use.
5050 Rgb Color Strip ,Color Changing Strip Lights,Colored Led Light Strips,Multi Color Led Strip Lights
NINGBO SENTU ART AND CRAFT CO.,LTD. , https://www.lightworld-sentu.com