Voice enhancement intelligent glasses based on ambient light and motion perception

Abstract

The invention discloses voice enhancement intelligent glasses based on ambient light and motion perception, and belongs to the technical field of intelligent glasses. Voice enhancement intelligent glasses based on ambient light and motion perception comprise a glasses frame and a supporting part, the supporting part is connected with the glasses frame through a hinge, and the supporting part comprises a first glasses leg and a second glasses leg; the camera is fixedly connected to the mirror frame; the first sensor is fixedly connected to the mirror frame; the gyroscope is connected to the glasses frame; the main control board is fixedly connected in the second glasses leg; the main control board is electrically connected with the camera and the first sensor through connecting wires; bone conduction loudspeakers are connected in the first glasses leg and the second glasses leg; the voice definition is effectively improved by utilizing the light intensity and color temperature data collected by the ambient light sensor and adjusting the gain and balance of the voice signals, the head movement track is tracked in real time in combination with the gyroscope, the pickup direction of the microphone array is dynamically adjusted in combination with the beam forming algorithm, and the movement artifact noise is effectively reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of smart glasses, and in particular to a pair of voice-enhanced smart glasses based on ambient light and motion perception. Background Art

[0002] With the development of smart technology, smart glasses with various functions have appeared on the market, which not only make people's lives more and more convenient, but also connect people with the Internet more closely, bringing tremendous changes to people's lives and perceptions. Existing smart glasses mostly focus on functions such as shooting and navigation, and lack real-time monitoring of users' health status (such as heart rate and blood pressure) and hearing assistance support; traditional hearing aids are large in size, single in function, and have low integration with smart devices; at the same time, health detection equipment (such as bracelets and watches) are limited by the wearing method and cannot be coordinated with the wearing scenarios of glasses.

[0003] Although there are some integrated smart glasses in the existing technology, there are still certain shortcomings when they are actually worn and used: the microphone array of traditional smart glasses lacks the coordinated perception of ambient light and motion status. In strong light, complex noise or motion scenes, voice pickup is easily interfered with (such as background noise covering the human voice, motion artifacts causing voice distortion), which may lead to a decrease in interaction accuracy; and most smart glasses have not realized the linkage between ambient light sensors, gyroscopes and voice processing modules, and cannot dynamically optimize voice algorithm parameters according to light intensity, color temperature and motion trajectory. Summary of the Invention

[0004] The purpose of the present invention is to solve the problems raised in the above background technology and to propose a voice-enhanced smart glasses based on ambient light and motion perception.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] A voice-enhanced smart glasses based on ambient light and motion perception, comprising:

[0007] A frame and a support portion, wherein the support portion is connected to the frame via a hinge, and the support portion comprises a first temple and a second temple;

[0008] A camera is fixedly connected to the frame;

[0009] A first sensor is fixedly connected to the frame;

[0010] a gyroscope, attached to the frame;

[0011] A main control board is fixedly connected to the second temple;

[0012] The main control board is electrically connected to the camera and the first sensor via a connecting line;

[0013] The first temple and the second temple are both connected to a bone conduction speaker.

[0014] Preferably, an audio power amplifier PCB board is fixedly connected to the first temple, and the audio power amplifier PCB board is electrically connected to the main control board.

[0015] Preferably, a battery is fixedly connected to the first temple.

[0016] Preferably, the first temple comprises a first bracket and a first shell, the first bracket is rotatably connected to the frame, and the first shell is detachably connected to the first bracket.

[0017] Furthermore, the second temple includes a second bracket and a second shell, the second bracket is rotatably connected to the frame, and the second shell is detachably connected to the second bracket.

[0018] Furthermore, MIC modules are fixedly connected to the first bracket and the second bracket, and the two groups of MIC modules are distributed on the top and bottom of the bone conduction speaker.

[0019] Furthermore, both the first shell and the second shell are provided with sound holes, and the MIC module is placed in the sound holes.

[0020] Preferably, a second sensor is connected to the inner wall of the second shell, and the second sensor is electrically connected to the main control board.

[0021] Furthermore, a third sensor is fixedly connected to the first bracket, and the third sensor is electrically connected to the main control board.

[0022] Preferably, an LED indicator light is fixedly connected to the mirror frame, and the LED indicator light is electrically connected to the main control board.

[0023] Compared with the existing technology, the present invention provides a voice-enhanced smart glasses based on ambient light and motion perception, which has the following beneficial effects:

[0024] 1. The present invention automatically adjusts the gain and balance of the voice signal by utilizing the light intensity and color temperature data collected in real time by the ambient light sensor, effectively improving the voice clarity. At the same time, it combines the gyroscope to track the head movement trajectory in real time, and combines the beamforming algorithm to dynamically adjust the pickup direction of the microphone array, effectively reducing motion artifact noise.

[0025] 2. The present invention adopts bone conduction speakers to avoid ear canal blockage during use. Combined with the distributed design of double temples, it achieves stereo effect while reducing the user's wearing discomfort. At the same time, the heart rate data collected by the third sensor can assist in the judgment of voice interaction scenarios and improve the interaction reliability in special scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 This is a schematic diagram of the structure of the voice-enhanced smart glasses based on ambient light and motion perception proposed by the present invention;

[0027] Figure 2 The invention proposes a speech-enhanced smart glasses based on ambient light and motion perception. Figure 1 ;

[0028] Figure 3 The invention proposes a speech-enhanced smart glasses based on ambient light and motion perception. Figure 2 ;

[0029] Figure 4 This is a process system diagram of the voice-enhanced smart glasses based on ambient light and motion perception proposed by the present invention.

[0030] In the figure: 1. Frame; 101. LED indicator light; 102. Camera; 103. First sensor; 104. Gyroscope; 2. Support part; 201. First temple; 2011. Push button switch; 2012. First bracket; 2013. First shell; 2014. Third sensor; 2015. Battery; 2016. Audio amplifier PCB board; 202. Second temple; 2021. Second bracket; 2022. Main control board; 2023. Second shell; 3. Bone conduction speaker; 4. Hinge; 5. Sound outlet; 6. Second sensor; 7. MIC module. DETAILED DESCRIPTION

[0031] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0032] Example 1:

[0033] Reference Figure 1-Figure 3 , a voice-enhanced smart glasses based on ambient light and motion perception, including a frame 1 and a support part 2, wherein a camera 102, a first sensor 103, a gyroscope 104 and an LED indicator light 101 are fixedly connected to the frame 1.

[0034] The first sensor 103 is an ambient light sensor for collecting ambient light parameters, including light intensity, color temperature, etc. The gyroscope 104 is used to detect the motion state of the smart glasses, including the rotation angle and angular velocity of the head. The LED indicator 101 is used to indicate the working status of the smart glasses.

[0035] The support part 2 is connected to the frame 1 through a hinge 4. The support part 2 includes a first temple 201 and a second temple 202, wherein the first temple 201 includes a first bracket 2012 and a first shell 2013, the first bracket 2012 is rotatably connected to the frame 1, and the first shell 2013 is detachably connected to the first bracket 2012; a battery 2015, an audio amplifier PCB board 2016 and a bone conduction speaker 3 are fixedly connected to the first temple 201.

[0036] It should be noted that the battery 2015 provides power for the smart glasses.

[0037] Reference Figure 1 The first temple 201 is connected to a button switch 2011 .

[0038] The audio amplifier PCB board 2016 is electrically connected to the main control board 2022 for amplifying the audio signal; the bone conduction speaker 3 is used to transmit the audio signal to the user through bone conduction, avoiding the blockage of the ear canal by traditional speakers and improving the wearing comfort and safety.

[0039] The second temple 202 includes a second bracket 2021 and a second housing 2023. The second bracket 2021 is rotatably connected to the frame 1, and the second housing 2023 is detachably connected to the second bracket 2021. A main control board 2022 and a bone conduction speaker 3 are fixedly connected to the second temple 202. The main control board 2022 is the core control unit of the smart glasses, responsible for processing various sensor data, executing the voice enhancement algorithm, and controlling the operation of other hardware modules.

[0040] Microphone modules 7 are fixedly connected to both the first bracket 2012 and the second bracket 2021. Two sets of these modules are located at the top and bottom of the bone conduction speaker 3. Sound holes 5 are provided on both the first and second housings 2013 and 2023. The microphone modules 7 are placed in these sound holes and are used to pick up ambient sound and user voice signals. A second pressure sensor 6 is connected to the inner wall of the second housing 2023. The second pressure sensor is used to detect the wearer's state of the smart glasses. A third pressure sensor 2014 is fixedly connected to the first bracket 2012. The third pressure sensor is used to detect physiological parameters such as the user's heart rate.

[0041] It should be noted that the MIC module 7 is a microphone available on the market.

[0042] Reference Figure 4 , in the specific implementation, the process steps are as follows:

[0043] Initialization phase:

[0044] The smart glasses are powered on, and the main control board 2022 performs system initialization and checks whether each hardware module is working properly. The first sensor 103 begins to collect ambient light parameters, including light intensity, color temperature, etc., and transmits the collected data to the main control board 2022.

[0045] The gyroscope 104 starts to detect the motion state of the smart glasses, including the rotation angle and angular velocity of the head, and transmits the collected data to the main control board 2022;

[0046] The MIC module 7 starts to pick up the ambient sound and user voice signals, and transmits the picked-up signals to the main control board 2022;

[0047] The main control board 2022 initializes the parameters of the voice enhancement algorithm according to the ambient light parameters and the motion status data.

[0048] Voice interaction stage:

[0049] When the user issues a voice command, the MIC module 7 picks up the voice signal and transmits it to the main control board 2022. The main control board 2022 enhances the voice signal by combining the ambient light parameters and motion status data. The specific processing steps are as follows:

[0050] Ambient light perception processing: Adjusts the gain and balance of voice signals based on ambient light intensity and color temperature. For example, in strong light environments, it automatically boosts the high-frequency components of the voice signal to enhance voice clarity. In low light environments, it appropriately reduces the intensity of noise suppression to avoid over-suppression of the voice signal.

[0051] Motion state perception processing: Based on the motion data detected by the gyroscope 104, it is determined whether the user is in a motion state; if the user is in a motion state, an adaptive noise suppression algorithm is activated to suppress the noise generated by the motion; at the same time, the direction of the beamforming is adjusted according to the direction and speed of the motion to ensure that the pickup direction of the voice signal is consistent with the user's voice direction.

[0052] Speech enhancement algorithm processing: Combined with the processing results of ambient light and motion status, the speech signal is filtered, denoised, enhanced, and other processing is performed to improve the quality of the speech signal.

[0053] The main control board 2022 transmits the enhanced voice signal to the audio power amplifier PCB board 2016. The audio power amplifier PCB board 2016 amplifies the voice signal and then transmits it to the bone conduction speaker 3. The bone conduction speaker 3 transmits the voice signal to the user through bone conduction.

[0054] If the voice command needs to trigger the camera 102 to shoot, the main control board 2022 controls the camera 102 to shoot, and stores the captured image or video data in the storage unit of the main control board 2022, or transmits it to an external device through the wireless communication module.

[0055] Dynamic adjustment stage:

[0056] During the voice interaction process, the first sensor 103 and the gyroscope 104 continuously collect ambient light parameters and motion status data, and transmit them to the main control board 2022; the main control board 2022 analyzes the changes in ambient light parameters and motion status data in real time, and dynamically adjusts the parameters of the voice enhancement algorithm; for example, when the ambient light intensity suddenly changes, the main control board 2022 immediately adjusts the gain and balance of the voice signal to adapt to the new ambient light conditions; when the user's motion state changes, the main control board 2022 adjusts the noise suppression algorithm and the direction of beamforming to ensure the stability of the voice enhancement effect.

[0057] If the second sensor 6 detects that the smart glasses are taken off, the main control board 2022 controls the smart glasses to enter a standby state to reduce power consumption; when it is detected that the smart glasses are put on again, the main control board 2022 controls the smart glasses to resume normal working state.

[0058] Data storage and transmission stage:

[0059] The main control board 2022 stores the collected ambient light parameters, motion status data, voice signal processing data, and user's physiological parameters in a storage unit.

[0060] The main control board 2022 transmits the stored data to the external device through the wireless communication module for users to view and manage; users can customize the voice enhancement parameters of the smart glasses through the APP of the external device, such as adjusting the intensity of noise suppression and the direction of beamforming.

[0061] The present invention automatically adjusts the gain and balance of the voice signal by utilizing the light intensity and color temperature data collected in real time by the ambient light sensor, thereby effectively improving the voice clarity. At the same time, it combines the gyroscope 104 to track the head movement trajectory in real time, and combines the beamforming algorithm to dynamically adjust the pickup direction of the microphone array, thereby effectively reducing motion artifact noise. At the same time, by adopting the bone conduction speaker 3, it avoids ear canal blockage during use, and cooperates with the distributed design of the double temples to achieve a stereo effect while reducing the user's wearing discomfort. At the same time, the heart rate data collected by the third sensor 2014 can assist in the judgment of voice interaction scenarios and improve the interaction reliability in special scenarios.

[0062] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solution and inventive concept of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. A voice-enhanced smart glasses based on ambient light and motion perception, characterized in that: include: A mirror frame (1) and a support portion (2), wherein the support portion (2) is connected to the mirror frame (1) via a hinge (4), and the support portion (2) comprises a first mirror leg (201) and a second mirror leg (202); A camera (102) is fixedly connected to the mirror frame (1); A first sensor (103) is fixedly connected to the mirror frame (1); A gyroscope (104) connected to the mirror frame (1); A main control board (2022) is fixedly connected to the second temple (202); The main control board (2022) is electrically connected to the camera (102) and the first sensor (103) via connecting wires; The first temple (201) and the second temple (202) are both connected to a bone conduction speaker (3).

2. The voice-enhanced smart glasses based on ambient light and motion perception according to claim 1, characterized in that: An audio power amplifier PCB board (2016) is fixedly connected to the first temple (201), and the audio power amplifier PCB board (2016) is electrically connected to the main control board (2022).

3. The voice-enhanced smart glasses based on ambient light and motion perception according to claim 1, characterized in that: A battery (2015) is fixedly connected to the first temple (201).

4. The voice-enhanced smart glasses based on ambient light and motion perception according to claim 1, characterized in that: The first temple (201) comprises a first bracket (2012) and a first shell (2013); the first bracket (2012) is rotatably connected to the frame (1), and the first shell (2013) is detachably connected to the first bracket (2012).

5. The voice-enhanced smart glasses based on ambient light and motion perception according to claim 4, characterized in that: The second temple (202) comprises a second bracket (2021) and a second shell (2023); the second bracket (2021) is rotatably connected to the mirror frame (1), and the second shell (2023) is detachably connected to the second bracket (2021).

6. The voice-enhanced smart glasses based on ambient light and motion perception according to claim 5, characterized in that: The first bracket (2012) and the second bracket (2021) are both fixedly connected with a MIC module (7), and the two groups of MIC modules (7) are distributed at the top and bottom of the bone conduction speaker (3).

7. The voice-enhanced smart glasses based on ambient light and motion perception according to claim 6, characterized in that: The first shell (2013) and the second shell (2023) are both provided with a sound outlet hole (5), and the MIC module (7) is placed in the sound outlet hole (5).

8. The voice-enhanced smart glasses based on ambient light and motion perception according to claim 1, characterized in that: A second sensor (6) is connected to the inner wall of the second shell (2023), and the second sensor (6) is electrically connected to the main control board (2022).

9. The voice-enhanced smart glasses based on ambient light and motion perception according to claim 5, characterized in that: A third sensor (2014) is fixedly connected to the first bracket (2021), and the third sensor (2014) is electrically connected to the main control board (2022).

10. The voice-enhanced smart glasses based on ambient light and motion perception according to claim 1, characterized in that: An LED indicator light (101) is fixedly connected to the mirror frame (1), and the LED indicator light (101) is electrically connected to the main control board (2022).

Images