Hearing test system and method therefor

Abstract

A hearing test system, comprising: a first sound device; a second sound device; a processing device, which is communicatively connected to the first sound device and the second sound device, wherein on the basis of a first sound production instruction, the processing device makes the first sound device or the second sound device emit a first sound; and an image capturing device, which is communicatively connected to the processing device, wherein the image capturing device captures a first facial image of a first target user so as to generate first facial image data. The processing device generates first eye movement direction data on the basis of the first facial image data. The processing device receives input data, which indicates whether the first target user has heard the first sound. The processing device uses the first eye movement direction data and the input data to train a learning module of the processing device, such that the learning module can generate determination data on the basis of second eye movement direction data, the determination data indicating whether a second target user has heard a second sound emitted by the first sound device or the second sound device.

Description

Hearing testing system and methods

[0001] Related applications

[0002] This application claims priority to U.S. Provisional Application No. 63 / 668,709, filed July 8, 2024, and U.S. Provisional Application No. 63 / 709,011, filed October 18, 2024, the entire contents of which are incorporated herein by reference. Technical Field

[0003] This application relates to a hearing testing system and method that can determine the target user's response (e.g., whether the target user has heard the test sound emitted by the hearing testing device / system) and generate determination data during hearing testing. In particular, this application relates to a hearing testing system and method that can determine the target user's eye movement and / or head movement (e.g., whether the target user has heard the test sound emitted by the hearing testing device / system) and generate determination data during hearing testing. Background Technology

[0004] Current hearing testing devices / systems are inadequate for specific groups, such as infants and young children, who cannot clearly express whether they have heard the test sounds emitted by the device / system. They rely solely on the experience of the testing personnel to determine whether the target user (or the subject of testing) has heard the system, lacking an objective and accurate benchmark to assist the personnel in their judgment. In this situation, the lack of experience among the testing personnel can easily lead to biased assessment results. Therefore, there is a need for a hearing testing system and method that can assess the target user's response during the hearing test (e.g., whether the target user has heard the test sounds emitted by the device / system) and generate assessment data. This would provide more objective assessment results or assist testing personnel in making more accurate judgments. Summary of the Invention

[0005] To address the aforementioned problems, one concept of this application is to provide a hearing testing system and method that can judge the target user's response (e.g., whether the target user has heard the test sound emitted by the hearing testing device / system) and generate judgment data during the hearing test. Another concept of this application is to provide a hearing testing system and method that can judge the target user's eye movement and / or head movement (e.g., whether the target user has heard the test sound emitted by the hearing testing device / system) and generate judgment data during the hearing test.

[0006] Based on the foregoing concept, this application provides a hearing detection system, comprising: a first sound device disposed on a first side of a first target user; a second sound device disposed on a second side of the first target user, wherein the second side direction is different from the first side direction; a processing device communicatively connected to the first sound device and the second sound device, the processing device receiving a first sound output command and causing the first sound device or the second sound device to emit a first sound according to the first sound output command; and an image capture device communicatively connected to the processing device, the image capture device capturing a first facial image of the first target user when the first sound device or the second sound device emits the first sound to generate a first facial image. The first facial image data is transmitted to the processing device; the processing device generates first eye movement direction data based on the first facial image data; the processing device receives input data when the first sound device or the second sound device emits the first sound, the input data indicating whether the first target user has heard the first sound, or indicating a gaze direction of the first target user; the processing device includes a learning module, which is trained with the first eye movement direction data and the input data, so that the learning module can generate judgment data based on a second eye movement direction data, the judgment data indicating whether a second target user has heard a second sound emitted by the first sound device or the second sound device.

[0007] In one embodiment of this application, the processing device generates eye image data and pupil image data based on the first facial image data, and the processing device generates the first eye movement direction data based on the eye image data and the pupil image data.

[0008] In one embodiment of this application, the learning module is a deep learning module, a machine learning module, or a type of neural network learning module.

[0009] In one embodiment of this application, the processing device generates first sound data according to the first sound output instruction, and the first sound data indicates the location of the first sound; wherein the processing device trains the learning module with the first eye movement direction data, the first sound data and the input data, so that the learning module can generate the judgment data according to the second eye movement direction data and the second sound data.

[0010] In one embodiment of this application, the processing device generates first head-shaking direction data based on the first facial image data, and the first head-shaking direction data indicates the head-shaking direction of the first target user; wherein the processing device trains the learning module with the first eye-tracking direction data, the first head-shaking direction data, the first audio data and the input data, so that the learning module can generate the judgment data based on the second eye-tracking direction data, the second head-shaking direction data and the second audio data.

[0011] In one embodiment of this application, the processing device receives a second sound output instruction and causes the first sound device or the second sound device to emit the second sound according to the second sound output instruction; wherein when the first sound device or the second sound device emits the second sound, the image capture device captures a second facial image of the second target user to generate second facial image data, and transmits the second facial image data to the processing device; wherein the processing device generates second eye movement direction data based on the second facial image data; wherein the learning module of the processing device generates judgment data based on the second eye movement direction data, and the judgment data indicates whether the second target user has heard the second sound emitted by the first sound device or the second sound device.

[0012] In one embodiment of this application, the processing device generates second sound data according to the second sound output instruction, and the second sound data indicates the location of the second sound; wherein the processing device generates the judgment data based on the second eye movement direction data and the second sound data.

[0013] In one embodiment of this application, the processing device generates a second head-shaking direction data based on the second facial image data, the second head-shaking direction data indicating the head-shaking direction of the second target user; wherein the processing device generates the judgment data based on the second eye-tracking direction data, the second head-shaking direction data, and the second audio data.

[0014] This application also provides a hearing detection method applied to a hearing detection system. The hearing detection system includes a first sound device, a second sound device, a processing device, and an image capture device. The processing device includes a learning module and is communicatively connected to the first sound device, the second sound device, and the image capture device. The first sound device is positioned at a first side of a first target user, and the second sound device is positioned at a second side of the first target user, the second side being different from the first side. The hearing detection method includes the following steps: the processing device receives a first sound output command and, according to the first sound output command, causes the first sound device or the second sound device to emit a first sound; the image capture device... When the device emits the first sound, it captures a first facial image of the first target user to generate first facial image data and transmits the first facial image data to the processing device; the processing device generates first eye movement direction data based on the first facial image data; the processing device receives input data when the first sound device or the second sound device emits the first sound, the input data indicating whether the first target user has heard the first sound or indicating a gaze direction of the first target user; and the processing device trains the learning module with the first eye movement direction data and the input data, so that the learning module can generate judgment data based on a second eye movement direction data, the judgment data indicating whether a second target user has heard a second sound emitted by the first sound device or the second sound device.

[0015] In one embodiment of this application, the hearing detection method further includes the following steps: the processing device generates an eye image data and a pupil image data based on the first facial image data; and the processing device generates the first eye movement direction data based on the eye image data and the pupil image data.

[0016] In one embodiment of this application, the learning module is a deep learning module, a machine learning module, or a type of neural network learning module.

[0017] In one embodiment of this application, the hearing detection method further includes the following steps: the processing device generates a first sound data according to the first sound output instruction, the first sound data indicating the location of the first sound; and the processing device trains the learning module with the first eye movement direction data, the first sound data and the input data, so that the learning module can generate the judgment data according to the second eye movement direction data and the second sound data.

[0018] In one embodiment of this application, the hearing detection method further includes the following steps: the processing device generates a first head-shaking direction data based on the first facial image data; and the processing device trains the learning module with the first eye-movement direction data, the first head-shaking direction data, the first sound data, and the input data, so that the learning module can generate the judgment data based on the second eye-movement direction data, the second head-shaking direction data, and the second sound data.

[0019] In one embodiment of this application, the hearing detection method further includes the following steps: the processing device receives a second sound output instruction and causes the first sound device or the second sound device to emit the second sound according to the second sound output instruction; the image capture device captures a second facial image of the second target user when the first sound device or the second sound device emits the second sound to generate second facial image data, and transmits the second facial image data to the processing device; the processing device generates second eye movement direction data based on the second facial image data; and the learning module of the processing device generates judgment data based on the second eye movement direction data, the judgment data indicating whether the second target user has heard the second sound emitted by the first sound device or the second sound device.

[0020] In one embodiment of this application, the hearing detection method further includes the following steps: the processing device generates a second sound data according to the second sound output instruction, the second sound data indicating the location of the second sound; and the processing device generates the judgment data according to the second eye movement direction data and the second sound data.

[0021] In one embodiment of this application, the hearing detection method further includes the following steps: the processing device generates a second head-shaking direction data based on the second facial image data; and the processing device generates the judgment data based on the second eye-movement direction data, the second head-shaking direction data, and the second sound data.

[0022] This application will be described in detail through the following non-limiting specific embodiments and accompanying drawings, so as to more clearly illustrate the above and other aspects. Attached Figure Description

[0023] Figure 1 is a system architecture diagram of a specific embodiment of the hearing detection system of this application.

[0024] Figure 2 is a flowchart of a specific embodiment of the hearing test method of this application.

[0025]

Symbol Explanation

[0026] Please refer to Figure 1, which illustrates a system architecture diagram of a specific embodiment of the hearing detection system according to this application. As shown in Figure 1, the hearing detection system 100 includes a processing unit 110, a first sound device 120, a second sound device 130, and an image capture device 140. The processing unit 110 is communicatively connected to the first sound device 120, the second sound device 130, and the image capture device 140, and includes a learning module 112. During hearing detection of a first target user 900 (or the first target subject to be tested), the first sound device 120 may be disposed on a first side direction 810 of the first target user 900, and the second sound device 130 may be disposed on a second side direction 820 of the first target user 900. The second side direction is different from the first side direction. For example, the first sound device 120 may be disposed on the right front side of the first target user 900 (i.e., the first side direction is the right front side direction of the first target user 900), and the second sound device 130 may be disposed on the left front side of the first target user 900 (i.e., the second side direction is the left front side direction of the first target user 900); or, the first sound device 120 may be disposed on the right rear side of the first target user 900 (i.e., the first side direction is the right rear side direction of the first target user 900), and the second sound device 130 may be disposed on the left rear side of the first target user 900 (i.e., the second side direction is the left rear side direction of the first target user 900), but is not limited thereto.

[0027] The processing device 110 can receive instruction data, image data, text data, etc., but is not limited to these. For example, the processing device 110 can receive instruction data (e.g., selection instructions provided by a mouse), text data (e.g., text / numeric input instructions provided by a keyboard), etc., via the control device or input device (e.g., keyboard, mouse, etc., but not limited to these) of the hearing assessment system 100, or the receiving module 122 can receive image data transmitted by the image capture device 140, but is not limited to these. In one specific embodiment, the processing device 110 may have one or more processors, and implement the functions of the processing device 110 and its various modules in a hardware and software cooperative manner.

[0028] It should be understood that the hearing detection system may not contain only two sound devices, but may contain any number of sound devices as needed. Furthermore, the placement of each sound device varies. Specifically, each sound device may be positioned in different directions from the target user. It should be understood that the processing device 110 may choose to communicate with the first sound device 120 via wired or wireless means as needed, the processing device 110 may choose to communicate with the second sound device 130 via wired or wireless means as needed, and the processing device 110 may choose to communicate with the image capture device 140 via wired or wireless means as needed.

[0029] In the embodiment shown in Figure 1, the processing device 110 can receive a first sound output command, and the processing device 110 can cause the first sound device 120 or the second sound device 130 to emit a first sound according to the first sound output command. The image capture device 140 can capture a facial image (referred to as a first facial image) of the first target user 900 when the first sound device 120 or the second sound device 130 emits the first sound to generate facial image data (referred to as first facial image data), and the image capture device 140 can transmit the first facial image data to the processing device 110. The processing device 110 can generate first eye movement direction data according to the first facial image data, and the processing device 110 can receive input data when the first sound device 120 or the second sound device 130 emits the first sound, wherein the input data indicates whether the first target user 900 has heard the first sound, or indicates a gaze direction of the target user 900. Then, the processing device 110 can train the learning module 112 with the first eye movement direction data and the input data, so that the learning module 112 can generate judgment data based on the second eye movement direction data. The judgment data can indicate whether a second target user using the hearing detection system 100 to perform hearing detection has heard a second sound emitted by the first sound device 120 or the second sound device 130.

[0030] In one embodiment, the processing device 110 may further include a control device. The first sound output command can be input to the processing device by a testing personnel via the control device. Thus, the testing personnel can determine whether the first sound is emitted by the first sound device 120 or the second sound device 130 via the first sound output command. The control device may be, for example, a user interface display device, but is not limited thereto. In one embodiment, the processing device 110 uses OpenCV (Open Source Computer Vision Library) to generate eye movement direction data based on facial image data. However, it should be understood that the processing device is not limited to using OpenCV to generate eye movement direction data, but may use other methods or other technologies to generate eye movement direction data based on facial image data as needed. In different embodiments, the learning module may be a deep learning module, a machine learning module, or a neural network-like learning module, but is not limited thereto.

[0031] In one specific embodiment, the processing device 100 may further include a control device, through which input data can be input by a testing personnel. Specifically, the testing personnel can determine whether the first target user 900 has heard the first sound, or determine the gaze direction of the first target user 900, based on the first target user 900's response, and can then input the input data to the processing device 110 via the control device. The input data can indicate the testing personnel's judgment result (i.e., the input data can indicate the testing personnel's judgment result regarding whether the first target user 900 has heard the first sound, or regarding the gaze direction of the first target user 900). The control device may be, for example, a user interface display device, but is not limited thereto. In one specific embodiment, eye movement direction data can indicate the target user's current eye movement direction or gaze direction (the gaze direction may be, for example, the gaze direction or gaze point of the target user's eyes). In one specific embodiment, the eye movement direction data can further indicate the trajectory of the target user's eye movement direction or gaze direction change. It should be understood that since the target user may not react immediately when hearing the sound emitted by the first or second sound device (the reaction may be, for example, eye movement or head movement, but not limited to these), training or judging based on the trajectory of changes in the target user's eye movement direction or gaze direction will be more accurate.

[0032] In one specific embodiment, the processing device 110 can generate eye image data and pupil image data based on the first facial image data, and the processing device 110 generates first eye movement direction data based on the eye image data and pupil image data. Both the eye image data and the pupil image data are associated with the first target user 900. In one specific embodiment, the eye image data indicates the eye image and / or eye information of the first target user 900 (e.g., eye contour information, eye length information, eye center point information, etc., but not limited thereto), while the pupil image data indicates the pupil image and / or pupil information of the first target user 900 (e.g., pupil contour information, pupil center point position information, etc., but not limited thereto). In one specific embodiment, the processing device 110 can generate the eye movement direction data in the same way as the eye movement direction data generation method used by OpenCV. However, it should be understood that the processing device 110 is not limited to using this method to generate eye movement direction data.

[0033] In one embodiment, the processing device 110 can generate first sound data according to a first sound output instruction. The first sound data indicates the location where the first sound is emitted. The processing device 110 trains the learning module 112 with first eye-tracking direction data, the first sound data, and input data, so that the learning module 112 can generate judgment data based on second eye-tracking direction data and second sound data. In one embodiment, the sound data can indicate the location of the sound-generating device, thereby representing the location of the sound. For example, if the processing device 110 causes the first sound device 120 to produce the first sound, the first sound data can indicate the location of the first sound device 120. Similarly, if the processing device 110 causes the second sound device 130 to produce the first sound, the first sound data can indicate the location of the second sound device 130, and so on.

[0034] In one embodiment, the processing device 110 can generate a first head-shaking direction data based on the first facial image data. The processing device 110 trains the learning module with the first eye-tracking direction data, the first head-shaking direction data, the first audio data, and the input data, so that the learning module 112 can generate judgment data based on the second eye-tracking direction data, the second head-shaking direction data, and the second audio data. In one embodiment, the first head-shaking direction data is associated with the first target user 900, and the first head-shaking direction data can indicate the current head-shaking direction of the first target user 900. In one embodiment, the first head-shaking direction data can further indicate the trajectory of the head-shaking direction change of the first target user 900. It should be understood that since the target user may not react immediately upon hearing the sound emitted by the first audio device 120 or the second audio device 130 (the reaction may be, for example, eye movement or head movement, but is not limited to these), training or judging based on the trajectory of the target user's head-shaking direction change will be more accurate.

[0035] In one specific embodiment, after the learning module 112 of the processing device 110 has completed its training, the processing device 110 can receive a second sound output instruction during the hearing test for a second target user, and cause the first sound device 120 or the second sound device 130 to emit a second sound according to the second sound output instruction. The image capture device 140 can capture a facial image (which may be referred to as a second facial image) of the second target user when the first sound device 120 or the second sound device 130 emits the second sound to generate second facial image data. The image capture device 140 can also transmit the second facial image data to the processing device 110. Then, the processing device 110 can generate second eye movement direction data based on the second facial image data. Subsequently, the learning module 112 of the processing device 110 can generate judgment data based on the second eye movement direction data, which indicates whether the second target user has heard the second sound emitted by the first sound device 120 or the second sound device 130.

[0036] In one embodiment, the processing device 110 may further include a control device. A second sound output command can be input to the processing device by an inspector via the control device. Thus, the inspector can determine whether the second sound is emitted by the first sound device 120 or the second sound device 130 via the second sound output command. The control device may be, for example, a user interface display device, but is not limited thereto. In one embodiment, the processing device 110 may further include a display device on which the processing device 110 can display judgment data to assist the inspector in making a judgment. The display device may be, for example, a user interface display device, but is not limited thereto.

[0037] In one specific embodiment, the processing device 110 can generate second sound data according to a second sound output instruction, the second sound data indicating the location where the second sound is emitted. The processing device 110 generates judgment data based on second eye movement direction data and the second sound data.

[0038] In one specific embodiment, the processing device 110 can generate a second head-shaking direction data based on the second facial image data. The processing device 110 generates judgment data based on the second eye-tracking direction data, the second head-shaking direction data, and the second audio data. In one specific embodiment, the second head-shaking direction data is associated with the second target user, and the second head-shaking direction data can indicate the current head-shaking direction of the second target user. In one specific embodiment, the second head-shaking direction data can further indicate the trajectory of the second target user's head-shaking direction change. It should be understood that since the target user may not immediately react when hearing the sound emitted by the first audio device 120 or the second audio device 130 (the reaction may be, for example, eye movement or head movement, but is not limited to these), training or judging based on the trajectory of the target user's head-shaking direction change will be more accurate.

[0039] Please refer to Figure 2, which illustrates a flowchart of a specific embodiment of the hearing detection method according to this application. As shown in Figure 2, the hearing detection method 200 can be applied to a hearing detection system. The hearing detection system includes a first sound device, a second sound device, a processing device, and an image capture device, and the processing device includes a learning module. The processing device of the hearing detection system is communicatively connected to the first sound device, the second sound device, and the image capture device. The first sound device is disposed on a first side of a first target user, and the second sound device is disposed on a second side of the first target user, and the second side direction is different from the first side direction.

[0040] The hearing detection method 200 begins at step 210, where the processing unit of the hearing detection system receives a first sound output command and, according to the command, causes a first sound device or a second sound device to emit a first sound. Next, step 220 is executed, where the image capture device of the hearing detection system captures a first facial image of a first target user when the first sound device or the second sound device emits the first sound, generating first facial image data, and transmits this data to the processing unit. Next, step 230 is executed, where the processing unit generates first eye movement direction data based on the first facial image data. Next, step 240 is executed, where the processing unit receives input data when the first sound device or the second sound device emits the first sound. This input data indicates whether the first target user has heard the first sound or indicates the first target user's gaze direction. Next, step 250 is executed, where the processing unit trains a learning module using the first eye movement direction data and the input data, enabling the learning module to generate judgment data based on second eye movement direction data. The judgment data indicates whether the second target user hears a second sound emitted by the first sound device or the second sound device.

[0041] In different specific embodiments, the learning module of the hearing detection system is a deep learning module, a machine learning module, or a neural network-like learning module, but is not limited thereto. In one specific embodiment, the hearing detection method 200 may further include the following steps: generating eye image data and pupil image data by a processing device based on first facial image data; and generating first eye movement direction data by the processing device based on the eye image data and pupil image data.

[0042] In one specific embodiment, the hearing detection method 200 may further include the following steps: a processing device generates first sound data according to a first sound production instruction; and the processing device trains a learning module with first eye movement direction data, the first sound data, and input data, so that the learning module can generate judgment data based on second eye movement direction data and second sound data. The first sound data indicates the location of the first sound.

[0043] In one specific embodiment, the hearing detection method 200 may further include the following steps: a processing device generates a first head-shaking direction data based on first facial image data; and the processing device trains a learning module with the first eye-movement direction data, the first head-shaking direction data, the first sound data, and input data, so that the learning module can generate the judgment data based on the second eye-movement direction data, the second head-shaking direction data, and the second sound data.

[0044] In one specific embodiment, the hearing detection method 200 may further include the following steps: a processing device receives a second sound output instruction and causes a first sound device or a second sound device to emit a second sound according to the second sound output instruction; an image capture device captures a second facial image of a second target user when the first sound device or the second sound device emits the second sound to generate second facial image data, and transmits the second facial image data to the processing device; the processing device generates second eye movement direction data based on the second facial image data; and the learning module of the processing device generates judgment data based on the second eye movement direction data. The judgment data indicates whether the second target user has heard the second sound emitted by the first sound device or the second sound device.

[0045] In one specific embodiment, the hearing detection method 200 may further include the following steps: a processing device generates a second sound data according to a second sound production instruction, the second sound data indicating the location of the second sound; and the processing device generates judgment data according to second eye movement direction data and the second sound data.

[0046] In one specific embodiment, the hearing detection method 200 may further include the following steps: generating a second head-shaking direction data by a processing device based on the second facial image data; and generating judgment data by the processing device based on the second eye-movement direction data, the second head-shaking direction data, and the second sound data.

[0047] Thus, the hearing detection system and method of this application have been described in the foregoing description and figures. However, it should be understood that the technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments have been described. However, as long as the combination of these technical features does not contradict each other, it should be considered to be within the scope of this specification.

[0048] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A hearing detection system, comprising: A first sound device is disposed at a first side of a first target user; A second sound device is disposed on a second side of the first target user, and the second side direction is different from the first side direction; A processing device communicatively connected to the first sound device and the second sound device, the processing device receiving a first sound output command, and causing the first sound device or the second sound device to emit a first sound according to the first sound output command; and An image capture device is communicatively connected to the processing device. When the first sound device or the second sound device emits the first sound, the image capture device captures a first facial image of the first target user to generate first facial image data and transmits the first facial image data to the processing device. The processing device generates a first eye movement direction data based on the first facial image data; When the first sound device or the second sound device emits the first sound, the processing device receives input data indicating whether the first target user has heard the first sound or indicating a gaze direction of the first target user. The processing device includes a learning module, which is trained with the first eye movement direction data and the input data, so that the learning module can generate judgment data based on a second eye movement direction data, and the judgment data indicates whether a second target user has heard a second sound device or a second sound emitted by the second sound device.

2. The hearing detection system as claimed in claim 1, wherein the processing device generates an eye image data and a pupil image data based on the first facial image data, and the processing device generates the first eye movement direction data based on the eye image data and the pupil image data.

3. The hearing detection system as described in claim 1, wherein the learning module is a deep learning module, a machine learning module, or a type of neural network learning module.

4. The hearing detection system as claimed in claim 1, wherein the processing device generates first sound data according to the first sound output instruction, the first sound data indicating the location of the first sound; The processing device trains the learning module with the first eye movement direction data, the first sound data, and the input data, so that the learning module can generate the judgment data based on the second eye movement direction data and a second sound data.

5. The hearing detection system as claimed in claim 4, wherein the processing device generates a first head-shaking direction data based on the first facial image data, the first head-shaking direction data indicating the head-shaking direction of the first target user; The processing device trains the learning module with the first eye movement direction data, the first head sway direction data, the first sound data, and the input data, so that the learning module can generate the judgment data based on the second eye movement direction data, the second head sway direction data, and the second sound data.

6. The hearing detection system of claim 1, wherein the processing device receives a second sound output instruction and causes the first sound device or the second sound device to emit the second sound according to the second sound output instruction; When the first sound device or the second sound device emits the second sound, the image capture device captures a second facial image of the second target user to generate second facial image data, and transmits the second facial image data to the processing device. The processing device generates a second eye movement direction data based on the second facial image data; The learning module of the processing device generates the judgment data based on the second eye movement direction data. The judgment data indicates whether the second target user has heard the second sound emitted by the first sound device or the second sound device.

7. The hearing detection system of claim 6, wherein the processing device generates second sound data according to the second sound output instruction, the second sound data indicating the location of the second sound; The processing device generates the judgment data based on the second eye movement direction data and the second sound data.

8. The hearing detection system of claim 7, wherein the processing device generates a second head-shaking direction data based on the second facial image data, the second head-shaking direction data indicating the head-shaking direction of the second target user; The processing device generates the judgment data based on the second eye movement direction data, the second head sway direction data, and the second sound data.

9. A hearing detection method applied to a hearing detection system, the hearing detection system comprising a first sound device, a second sound device, a processing device, and an image capture device, the processing device comprising a learning module, the processing device being communicatively connected to the first sound device, the second sound device, and the image capture device, the first sound device being disposed at a first side of a first target user, the second sound device being disposed at a second side of the first target user, the second side being different from the first side; the hearing detection method comprising the following steps: The processing device receives a first sound output instruction and causes the first sound device or the second sound device to emit a first sound according to the first sound output instruction. When the first sound is emitted by the first sound device or the second sound device, the image capture device captures a first facial image of the first target user to generate first facial image data, and transmits the first facial image data to the processing device. The processing device generates first eye movement direction data based on the first facial image data; When the first sound is emitted by the first sound device or the second sound device, the processing device receives input data indicating whether the first target user has heard the first sound, or indicating a gaze direction of the first target user; and The processing device trains the learning module with the first eye movement direction data and the input data, so that the learning module can generate a judgment data based on a second eye movement direction data, the judgment data indicating whether a second target user hears a second sound emitted by the first sound device or the second sound device.

10. The hearing testing method as described in claim 9, further comprising the following steps: The processing device generates eye image data and pupil image data based on the first facial image data; and The processing device generates the first eye movement direction data based on the eye image data and the pupil image data.

11. The hearing detection method as described in claim 9, wherein the learning module is a deep learning module, a machine learning module, or a neural network learning module.

12. The hearing test method as described in claim 9, further comprising the following steps: The processing device generates first sound data according to the first sound output command, the first sound data indicating the location of the first sound; and The processing device trains the learning module with the first eye movement direction data, the first sound data, and the input data, so that the learning module can generate the judgment data based on the second eye movement direction data and a second sound data.

13. The hearing testing method as described in claim 12, further comprising the following steps: The processing device generates a first head-turning direction data based on the first facial image data; and The processing device trains the learning module with the first eye movement direction data, the first head sway direction data, the first sound data, and the input data, so that the learning module can generate the judgment data based on the second eye movement direction data, the second head sway direction data, and the second sound data.

14. The hearing testing method as described in claim 9, further comprising the following steps: The processing device receives a second sound output command and causes the first sound device or the second sound device to emit the second sound according to the second sound output command; When the first sound device or the second sound device emits the second sound, the image capture device captures a second facial image of the second target user to generate second facial image data, and transmits the second facial image data to the processing device. The processing device generates second eye movement direction data based on the second facial image data; and The learning module of the processing device generates the judgment data based on the second eye movement direction data. The judgment data indicates whether the second target user has heard the second sound emitted by the first sound device or the second sound device.

15. The hearing testing method as described in claim 14, further comprising the following steps: The processing device generates second sound data according to the second sound output command, and the second sound data indicates the location of the second sound; and The processing device generates the judgment data based on the second eye movement direction data and the second sound data.

16. The hearing testing method as described in claim 15, further comprising the following steps: The processing device generates a second head-turning direction data based on the second facial image data; and The processing device generates the judgment data based on the second eye movement direction data, the second head sway direction data, and the second sound data.

Images