Sound training device

Abstract

The utility model discloses a sound training device. The sound training device comprises an interactive execution unit, a control mainboard unit and a display unit which are connected in sequence, the interactive execution unit is used for collecting sound data and a sound production part image of a user and transmitting the sound data and the sound production part image to the control mainboard unit; the gas injection unit is also used for receiving a control signal of the control mainboard unit and injecting gas at a sounding target part of a user according to the control signal; the control mainboard unit is used for determining a sound production target part of a user according to the sound data and the sound production part image, sending a control signal to the interaction execution unit according to the sound production target part, and sending a display signal to the display unit; and the display unit is used for visually displaying the sounding target part of the user. According to the utility model, people with confusion can find correct sounding parts, and users can learn correct sounding skills through self-training.

Description

Technical Field

[0001] The utility model relates to the technical field of vocal rehabilitation training, in particular to a voice training device. Background Art

[0002] Human vocalization is a complex process controlled by the nervous system, supported by the respiratory system, and executed by the muscular system (the vocal cords and tuning parts including the cavity work together). For people who are born deaf or have non-standard vocalization, scientific and effective vocal guidance tools can be used to improve vocal skills and solve the problems faced by those who are confused about vocalization. People who are born deaf or unable to vocalize can learn to vocalize, and people who overuse their throats or have torn voices can vocalize scientifically. Singers with nearly perfect vocal skills can be helped to better convey their deep emotions and achieve "soul resonance" with the audience. This will improve their mental health, self-confidence and happiness.

[0003] At present, voice guidance usually adopts the method of video recording and manual analysis guidance, allowing users to observe their own voice process. By observing the video, users can more intuitively understand their voice problems and make targeted improvements with manual guidance. However, this method may be limited by the professional level and experience of the analyst. Different analysts may give different suggestions, and there may be some subjective factors, which may make it difficult for users to practice and improve independently. Lack of professional knowledge and feedback may cause users to fall into misunderstandings or fail to effectively improve their voice skills.

[0004] Therefore, there is a need to provide a voice training device that can help people who are confused about voice to find the vocal part and provide users with visual guidance and targeted feedback during autonomous voice training. Utility Model Content

[0005] In view of this, it is necessary to provide a voice training device to solve the technical problem in the prior art that it is difficult for users to practice independently and get guidance feedback when guiding users to perform voice exercises through video recording and manual analysis.

[0006] In order to achieve the above technical purpose, the utility model provides a sound training device, comprising an interactive execution unit, a control mainboard unit and a display unit connected in sequence;

[0007] The interactive execution unit is used to collect the user's voice data and the image of the sound-producing part, and transmit the voice data and the image of the sound-producing part to the control mainboard unit; and is also used to receive the control signal of the control mainboard unit, and spray gas at the user's sound-producing target part according to the control signal;

[0008] The control mainboard unit is used to determine the user's target vocalization part according to the sound data and the vocalization part image, and send a control signal to the interactive execution unit and a display signal to the display unit according to the vocalization target part;

[0009] The display unit is used to visually display the user's vocalization target area.

[0010] Further, the interactive execution unit includes a data transmission module connected to a microphone module, a camera module and a gas transmission module, and a battery module connected to the microphone module, the camera module, the gas transmission module and the data transmission module;

[0011] The microphone module is used to collect the user's voice data;

[0012] The camera module is used to collect images of the user's vocalization area;

[0013] The gas emission module is used to spray gas to the target part of the user's voice;

[0014] The data transmission module is used to wirelessly transmit the sound data and the sound generating part image to the control mainboard unit, and receive the control signal of the control mainboard unit;

[0015] The battery module is used to provide electrical energy to the microphone module, the camera module, the gas emission module and the data transmission module.

[0016] Furthermore, the data transmission module adopts the ESP32 chip.

[0017] Further, the gas emission module includes an angle adjustment device and a gas ejection device;

[0018] The gas ejection device includes an air pump B1, the cathode of the air pump B1 is connected to the collector of the NPN transistor Q1, the base of the NPN transistor Q1 is connected to the data transmission module ESP32 through a resistor R7, and the emitter of the NPN transistor Q1 is grounded; the positive and negative electrodes of the air pump are connected in parallel with the first filter capacitor C12 and the second filter capacitor C13, and are connected in parallel with the diode D3, and the cathode of the diode D3 is connected to the positive electrode of the air pump B1;

[0019] The angle adjustment device is rotatably connected to the air pump B1 and is used to adjust the jet angle of the air pump B1.

[0020] Further, the gas emission module includes an angle adjustment device and a gas ejection device;

[0021] The gas ejection device includes an air pump B1, the cathode of the air pump B1 is connected to the collector of the NPN transistor Q1, the base of the NPN transistor Q1 is connected to the data transmission module ESP32 through a resistor R7, and the emitter of the NPN transistor Q1 is grounded; the positive and negative electrodes of the air pump are connected in parallel with the first filter capacitor C12 and the second filter capacitor C13, and are connected in parallel with the diode D3, and the cathode of the diode D3 is connected to the positive electrode of the air pump B1;

[0022] The angle adjustment device is rotatably connected to the air pump B1 and is used to adjust the jet angle of the air pump B1.

[0023] Furthermore, the model of the CMOS image sensor is OV9734.

[0024] Furthermore, the microphone module includes two microphones of model INMP441 for collecting dual-channel sound data; the SCK pin, SD pin, and WS pin of INMP441 are connected to the data transmission module ESP32 chip, and the L / R pin is grounded.

[0025] Further, the control mainboard unit includes a power management module, and a WIFI module, a processor module, a RAM module, a video data output interface, a power output interface and an external power access port connected to the power management module; the WIFI module, the RAM module, the video data output interface and the common power output interface are all connected to the processor module;

[0026] The external power access port adopts a Type-c interface for obtaining external power supply;

[0027] The power supply output interface is used to provide power to the display unit and transmit touch screen data;

[0028] The power management module is used to convert the voltage of the external power supply and provide power output for the WIFI module, processor module, RAM module, video data output interface and power output interface;

[0029] The processor module is used to determine the user's target vocalization position according to the sound data and the vocalization position image, and determine the control signal and the display signal according to the vocalization target position;

[0030] The WIFI module is used to send a control signal to the interaction execution unit;

[0031] The RAM module is used to store data;

[0032] The video data output interface is used to perform data exchange with the display unit and transmit display signals to the display unit.

[0033] Furthermore, the processor module adopts a processing chip of model Broadcom BCM2711.

[0034] Furthermore, the video data output interface adopts an HDMI interface.

[0035] The beneficial effects of the utility model are: the user's voice data and vocal part image are collected through the interactive execution unit, the sound data and the vocal part image are analyzed through the control mainboard unit, the user's vocal target part is determined, and a control signal is sent to the interactive execution unit to spray gas to the user's correct vocal target part, and the vocal target part is visualized through the display unit. Through this real-time feedback and guidance, the user is helped to correct mistakes and adjust postures in time, thereby improving vocal skills more quickly, and can help users better understand and master correct vocal skills, improve voice clarity, tone accuracy and sound stability. Through systematic training and personalized guidance, users can improve vocal skills more efficiently, reduce learning costs and time costs, and improve the effect of autonomous training. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 A structural schematic diagram of an embodiment of a sound training device provided by the utility model;

[0037] Figure 2 A connection diagram of the data transmission module provided by the utility model;

[0038] Figure 3 A circuit diagram of an embodiment of a gas spraying device provided by the utility model;

[0039] Figure 4 A circuit diagram of an embodiment of a camera power supply module provided by the utility model;

[0040] Figure 5 A circuit diagram of an embodiment of an image sensor provided by the utility model;

[0041] Figure 6 A circuit diagram of an embodiment of a microphone module provided by the utility model;

[0042] Figure 7 This is a structural schematic diagram of another embodiment of the sound training device provided by the utility model. DETAILED DESCRIPTION

[0043] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of the present application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not used to limit the scope of the present invention.

[0044] In the description of the present application, “plurality” means two or more than two, unless otherwise clearly and specifically defined.

[0045] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0046] The utility model provides a sound training device, which is described in detail below.

[0047] See also Figure 1 , Figure 1 A structural diagram of an embodiment of a voice training device 100 provided by the utility model, comprising an interactive execution unit 101, a control mainboard unit 102 and a display unit 103 connected in sequence;

[0048] The interactive execution unit 101 is used to collect the user's voice data and the image of the sound production part, and transmit the voice data and the image of the sound production part to the control mainboard unit 102; it is also used to receive the control signal sent by the control mainboard unit 102, and spray gas at the user's sound production target part according to the control signal;

[0049] The control mainboard unit 102 is used to determine the user's target vocalization part according to the sound data and the vocalization part image, and send a control signal to the interactive execution unit 101 and a display signal to the display unit 103 according to the vocalization target part;

[0050] The display unit 103 is used to visually display the user's vocalization target part.

[0051] The voice training device provided in this embodiment collects the user's voice data and vocal part image through the interactive execution unit, analyzes the voice data and vocal part image through the control mainboard unit, determines the user's vocal target part, and sends a control signal to the interactive execution unit to spray gas to the user's correct vocal target part, and visualizes the vocal target part through the display unit. Through this real-time feedback and guidance, it helps users to correct mistakes and adjust postures in time, so as to improve vocal skills faster, and can help users better understand and master correct vocal skills, improve voice clarity, pitch accuracy and sound stability. Through systematic training and personalized guidance, users can improve vocal skills more efficiently, reduce learning costs and time costs, and improve the effect of autonomous training.

[0052] As a preferred embodiment, the interactive execution unit includes a data transmission module connected to a microphone module, a camera module and a gas transmission module, and a battery module connected to the microphone module, the camera module, the gas transmission module and the data transmission module;

[0053] The microphone module is used to collect the user's voice data;

[0054] The camera module is used to collect images of the user's vocalization area;

[0055] The gas emission module is used to spray gas to the target part of the user's voice;

[0056] The data transmission module is used to wirelessly transmit the sound data and the sound generating part image to the control mainboard unit, and receive the control signal of the control mainboard unit;

[0057] The battery module is used to provide electrical energy to the microphone module, the camera module, the gas emission module and the data transmission module.

[0058] As a specific embodiment, the battery module is powered by a 5V lithium battery. Compared with other types of batteries, lithium batteries of the same size can provide more power, so that the device can have a longer working time at the same volume.

[0059] As a preferred embodiment, the data transmission module adopts the ESP32 chip.

[0060] The ESP32 chip is a highly integrated, low-power system-on-chip (SoC) that is primarily used for Internet of Things (IoT) applications and wireless communications. It integrates Wi-Fi and Bluetooth capabilities, so it can achieve wireless connectivity and communication. The wireless communication capabilities of the ESP32 chip make it widely used in various IoT applications. It can be used as a microcontroller or communicate with other devices to achieve data transmission and control functions.

[0061] In some embodiments, Figure 2 As shown, Figure 2The connection diagram of each pin of the ESP32 chip in the circuit is shown. In the GPIO interface of the chip, the CSI_D0-CSI_D7 signal pins, CSI_VSYNC signal pins, CSI_HSYNC signal pins, CSI_PCLK signal pins, CSI_MCLK signal pins, TWI_SDA signal pins, and TWI_SCK signal pins are used to control and interact with the camera module. The SD1, SD0, and CLK signal pins are used to interact with the microphone module. When working, the ESP32 chip uses WiFi wireless communication. ESP32 sends the data collected by the microphone and camera to the mainboard for processing, and also needs to receive the control signal from the mainboard to control the gas emission module. LED1 is used to intuitively display the power supply status of the module.

[0062] As a preferred embodiment, the gas emission module includes an angle adjustment device and a gas ejection device;

[0063] like Figure 3 As shown, the gas spraying device includes an air pump B1, the cathode of the air pump B1 is connected to the collector of the NPN transistor Q1, the base of the NPN transistor Q1 is connected to the data transmission module ESP32 through a resistor R7, and the emitter of the NPN transistor Q1 is grounded; the positive and negative electrodes of the air pump are connected in parallel with the first filter capacitor C12 and the second filter capacitor C13, and are connected in parallel with the diode D3, and the cathode of the diode D3 is connected to the positive electrode of the air pump B1.

[0064] Among them, the first filter capacitor C12 uses a 100uF capacitor to filter out high-frequency noise in the circuit, and the second filter capacitor C13 is mainly used to filter out low-frequency noise in the circuit. Diode D3 is used as reverse voltage protection in the circuit. When the air pump needs to be turned on, the control motherboard will send an opening command to the ESP32 chip through wireless communication to turn on the air pump.

[0065] The angle adjustment device is rotatably connected to the air pump B1 and is used to adjust the jet angle of the air pump B1. The angle adjustment device uses a common electric device such as a motor or a steering gear to adjust the air outlet angle of the air pump by controlling the rotation of the motor or the position of the steering gear, and sprays the gas to the user's target position, so that the user knows the correct vocalization position, and can scientifically and correctly vocalize or improve the vocalization through practice.

[0066] As a preferred embodiment, the camera module includes a camera power supply module and a CMOS image sensor;

[0067] The camera power supply module includes a first voltage stabilizer U3, and a second voltage stabilizer U1 and a third voltage stabilizer U2 connected to the output end of the first voltage stabilizer U3; the first voltage stabilizer U3 is used to convert the first voltage provided by the battery module into a second voltage; the second voltage stabilizer U1 is used to convert the second voltage into a third voltage; the third voltage stabilizer U2 is used to convert the second voltage into a fourth voltage;

[0068] The CMOS image sensor is used to capture the image of the user's vocalization site.

[0069] As a specific example, Figure 4 As shown, Figure 4 The specific circuit diagram of the camera power supply module is shown. Figure 4 In the example, the first voltage regulator U3 uses AMS1117, and the second voltage regulator U1 and the third voltage regulator U2 use XC6206. The first voltage provided by the battery module is 5V, which is converted to 3.3V by AMS1117 and provided to the CMOS image sensor. Then, the 3.3V voltage is converted to 2.8V and 1.2V respectively by XC6206 to meet the voltage level required by the image sensor. Figure 4 In the embodiment, capacitors C2, C3, C4, C5, C8, C9, and C10 are filter capacitors, Q2 is a PMOS tube, the drain of Q2 is connected to the input end of XC6206, and the source is connected to the output end of AMS1117. The output voltage of the circuit is adjusted by controlling the PMOS tube Q2. In the voltage regulator circuit of this embodiment, accurate adjustment of the output voltage can be achieved.

[0070] As a preferred embodiment, the model of the CMOS image sensor is OV9734. OV9734 is a high-resolution CMOS sensor that can provide high-quality images and has the advantages of low power consumption and low cost. OV9734 can be used as the core component of the camera module to provide video input and image capture functions. The optical fiber and lens combination are used to complete the transmission of light and images. The whole system consists of an objective lens system, an optical image transmission system, and an observation eyepiece system. All optical fiber fibers are arranged neatly, with the ends corresponding to each other, and all light spots from one end to the other. The closer each fiber is arranged and the neater the ends are, the greater the brightness of the transmitted image, the higher the resolution, and the clearer the image.

[0071] like Figure 5 As shown, Figure 5The connection diagram of each pin of the OV9734 image sensor is shown. The DVDD pin is connected to the 1.2V voltage output by the camera power supply module, the AVDD pin is connected to the 2.8V voltage output by the camera power supply module, and the DOVDD pin is connected to the 3.3V voltage. Connect the CSI_D0-CSI_D7 signal pins, CSI_VSYNC signal pins, CSI_HSYNC signal pins, CSI_PCLK signal pins, CSI_MCLK signal pins, TWI_SDA signal pins, and TWI_SCK signal pins to the GPIO pins of the ESP32 chip.

[0072] The ESP32 microcontroller sends the image data collected by the OV9734 camera module to the control motherboard unit through WiFi communication. The control motherboard unit compares the image data with the collected image to determine whether the part used for sound generation is correct.

[0073] As a preferred embodiment, the microphone module includes two microphones of model INMP441 to collect dual-channel sound data; the SCK pin, SD pin, and WS pin of INMP441 are connected to the data transmission module ESP32 chip, and the L / R pin is grounded.

[0074] The microphone INMP441 is a high performance, low power, digital output, omnidirectional MEMS microphone with bottom port, consisting of a MEMS sensor, signal conditioning analog-to-digital converter, anti-aliasing filter, power management and industry standard 24-bit 12S interface. The INMP441 has a high signal-to-noise ratio and is an excellent choice for near-field applications. The INMP441 has a flat broadband frequency response, resulting in natural sound with high clarity.

[0075] As a specific example, Figure 6 The schematic diagram of the complete microphone module solution is shown in Figure 6, the SCK pin, SD pin and WS pin of INMP441 constitute the I2S bus. The I2S interface allows INMP441 to be directly connected to a digital processor without the use of an audio codec. Among them, SCK is the clock line, which is used to control the transmission timing of each bit of data; SD is the I2S data line, through which the sound sampling value is sent to ESP32; WS is the I2S channel selection line. The I2S protocol can transmit data of the left and right channels. The WS signal is sent from the control motherboard to the microphone module. The microphone module determines whether the current data frame sends left or right channel data according to the level of WS. When WS is low, the left channel data is sent, and when it is high, the right channel is sent. The SCK, SD, and WS of INMP441 are connected to ESP32, and the collected sound data is sent to the control motherboard unit through WiFi wireless communication. The control motherboard unit extracts audio features and analyzes the sound data of the left and right channels, thereby determining the air flow (volume), the standard of pronunciation, and the location of the sound.

[0076] As a preferred embodiment, the control mainboard unit includes a power management module, and a WIFI module, a processor module, a RAM module, a video data output interface, a power output interface and an external power access port connected to the power management module; the WIFI module, the RAM module, the video data output interface and the common power output interface are all connected to the processor module;

[0077] The external power access port adopts a Type-c interface for obtaining external power supply;

[0078] The power supply output interface is used to provide power to the display unit and transmit touch screen data;

[0079] The power management module is used to convert the voltage of the external power supply and provide power output for the WIFI module, processor module, RAM module, video data output interface and power output interface;

[0080] The processor module is used to determine the user's target vocalization position according to the sound data and the vocalization position image, and determine the control signal and the display signal according to the vocalization target position;

[0081] The WIFI module is used to send a control signal to the interaction execution unit;

[0082] The RAM module is used to store data;

[0083] The video data output interface is used to perform data exchange with the display unit and transmit display signals to the display unit.

[0084] As a preferred embodiment, the processor module adopts a processing chip of Broadcom BCM2711. Broadcom BCM2711 is a SoC chip, and the CPU core of BCM2711 is a 64-bit quad-core Cortex-A72 ARM processor based on Armv8 architecture, with a main frequency of 1.5GHz. Built-in GPU (500MHZ VideoCore VI).

[0085] In some embodiments, the external power access port uses a Type-c interface with a power supply voltage of 5V, which increases the versatility and compatibility of the interface.

[0086] The RAM module (8GB) is an SDRAM based on LPDDR4, which is packaged in Micron FBGA. It is equivalent to the DDR4 memory used in mobile devices. Compared with DDR4, it has lower power consumption, but the bandwidth is also reduced. The RAM module is used to temporarily store data and provide temporary storage space for high-speed access for the processor module and other modules. This helps to improve the operating efficiency and response speed of the system.

[0087] The power management module uses the MaxLinear MxL7704 power management chip (PMIC) for MxL7704. The MxL7704 is equipped with 100mALD0 to provide a stable 1.5V to 3.6V power supply for the onboard subsystems. Four synchronous LD0s provide the required power for the system, memory, I / O and core power. It also has ADC, I2C configuration and state machine. The power management module is responsible for voltage conversion of external power supply and provides stable power output for each module. This helps to ensure the stable operation of the system and extend the service life of the equipment.

[0088] The WIFI module uses Cypress CYW43455 to provide dual-band 2.4GHz and 5GHZ wireless networks as well as Bluetooth 5.0 and low-power Bluetooth BLE functions. By integrating the WIFI module, users can easily achieve wireless network connection and enjoy network services and resources. This wireless connection method provides greater flexibility and convenience for the device.

[0089] The power output interface uses VL805, a USB 3.0 controller that supports PCI Express and USB super-speed (5Gbps), high-speed (480Mbps), full-speed (12Mbps) and low-speed (1.5Mbps) devices. There are two groups of USB2.0 / USB3.0. The power output interface using the VL805 USB 3.0 controller has the advantages of high-speed transmission, strong compatibility, multiple groups of interfaces, flexibility and stability, and is suitable for connecting various USB devices and achieving efficient data transmission.

[0090] In some embodiments, the control motherboard unit also includes a Gigabit Ethernet module, using BCM54213PE, which is a Gigabit Ethernet (GbE) transceiver. It is highly integrated in Ethernet reception and includes an adaptive equalizer, ADC, phase-locked loop, line driver, encoder, decoder, echo canceller, crosstalk canceller, and all Ethernet necessary functions. In some cases, data can be uploaded to a host computer through Ethernet for further storage or analysis.

[0091] It should be noted that the processor module determines the user's target vocalization position based on the sound data and the vocalization position image, and determines the control signal and the display signal based on the vocalization target position; this analysis process adopts conventional signal analysis methods and image processing methods, such as the currently commonly used laryngeal language analysis method, or the commonly used vocal cord movement correction control method, to analyze the sound signal and vocal cord video, etc., to determine whether it is a correct vocalization, and to find the target vocalization position, such as the analysis method described in "A Vocal Cord Movement Correction System and Control Method" with application number CN202211609239.X.

[0092] As a preferred embodiment, the video data output interface adopts an HDMI interface.

[0093] The HDMI interface supports high-definition video transmission and can provide high-quality image and audio effects. This means that users can enjoy a clearer and more realistic audio-visual experience. At the same time, since the HDMI interface has become one of the most popular video interface standards, it is widely used in various TVs, monitors, projectors and other devices. Therefore, the use of the HDMI interface can ensure the compatibility and versatility of the equipment.

[0094] Combine the following Figure 7 The structure of the sound training device is explained more intuitively, such as Figure 7 As shown, Figure 7 The specific device models and connection diagrams used in each unit in actual applications are shown. The sound data and the image of the vocal part are captured by the interactive execution unit, and the sound data and the image of the vocal part are analyzed by the control motherboard unit to determine the user's vocal target part, and a control signal is sent to the interactive execution unit to spray gas to the user's correct vocal target part. At the same time, the vocal target part is visualized through the display unit. The control motherboard unit can also wirelessly upload data to the cloud platform for further analysis and processing. Through this real-time feedback and guidance, users can correct mistakes and adjust postures in time, thereby improving vocal skills faster, which can help users better understand and master correct vocal skills.

[0095] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by any technician familiar with the technical field within the technical scope disclosed in the present invention should be included in the protection scope of the present invention.

Claims

1. A voice training device, characterized in that: It includes an interactive execution unit, a control mainboard unit and a display unit connected in sequence; The interactive execution unit is used to collect the user's voice data and the image of the sound-producing part, and transmit the voice data and the image of the sound-producing part to the control mainboard unit; and is also used to receive the control signal of the control mainboard unit, and spray gas at the user's sound-producing target part according to the control signal; The control mainboard unit is used to determine the user's target vocalization part according to the sound data and the vocalization part image, and send a control signal to the interactive execution unit and a display signal to the display unit according to the vocalization target part; The display unit is used to visually display the user's vocalization target area.

2. The voice training device according to claim 1, characterized in that: The interactive execution unit includes a data transmission module connected to a microphone module, a camera module and a gas transmission module, and a battery module connected to the microphone module, the camera module, the gas transmission module and the data transmission module; The microphone module is used to collect the user's voice data; The camera module is used to collect images of the user's vocalization area; The gas emission module is used to spray gas to the target part of the user's voice; The data transmission module is used to wirelessly transmit the sound data and the sound generating part image to the control mainboard unit, and receive the control signal of the control mainboard unit; The battery module is used to provide electrical energy to the microphone module, the camera module, the gas emission module and the data transmission module.

3. The voice training device according to claim 2, characterized in that: The data transmission module adopts ESP32 chip.

4. The voice training device according to claim 3, characterized in that: The gas emission module includes an angle adjustment device and a gas ejection device; The gas ejection device includes an air pump B1, the cathode of the air pump B1 is connected to the collector of the NPN transistor Q1, the base of the NPN transistor Q1 is connected to the data transmission module ESP32 through a resistor R7, and the emitter of the NPN transistor Q1 is grounded; the positive and negative electrodes of the air pump are connected in parallel with the first filter capacitor C12 and the second filter capacitor C13, and are connected in parallel with the diode D3, and the cathode of the diode D3 is connected to the positive electrode of the air pump B1; The angle adjustment device is rotatably connected to the air pump B1 and is used to adjust the jet angle of the air pump B1.

5. The voice training device according to claim 2, characterized in that: The camera module includes a camera power supply module and a CMOS image sensor; The camera power supply module includes a first voltage stabilizer U3, and a second voltage stabilizer U1 and a third voltage stabilizer U2 connected to the output end of the first voltage stabilizer U3; the first voltage stabilizer U3 is used to convert the first voltage provided by the battery module into a second voltage; the second voltage stabilizer U1 is used to convert the second voltage into a third voltage; the third voltage stabilizer U2 is used to convert the second voltage into a fourth voltage; The CMOS image sensor is used to capture the image of the user's vocalization site.

6. The voice training device according to claim 5, characterized in that: The model of the CMOS image sensor is OV9734.

7. The voice training device according to claim 2, characterized in that: The microphone module includes two microphones of model INMP441 for collecting dual-channel sound data; the SCK pin, SD pin, and WS pin of INMP441 are connected to the data transmission module ESP32 chip, and the L / R pin is grounded.

8. The voice training device according to claim 2, characterized in that: The control mainboard unit includes a power management module, and a WIFI module, a processor module, a RAM module, a video data output interface, a power output interface and an external power access port connected to the power management module; the WIFI module, the RAM module, the video data output interface and the common power output interface are all connected to the processor module; The external power access port adopts a Type-c interface for obtaining external power supply; The power supply output interface is used to provide power to the display unit and transmit touch screen data; The power management module is used to convert the voltage of the external power supply and provide power output for the WIFI module, processor module, RAM module, video data output interface and power output interface; The processor module is used to determine the user's target vocalization position according to the sound data and the vocalization position image, and determine the control signal and the display signal according to the vocalization target position; The WIFI module is used to send a control signal to the interaction execution unit; The RAM module is used to store data; The video data output interface is used to perform data exchange with the display unit and transmit display signals to the display unit.

9. The voice training device according to claim 8, characterized in that: The processor module adopts a processing chip of Broadcom BCM2711.

10. The voice training device according to claim 8, characterized in that: The video data output interface adopts an HDMI interface.

Images