Silent speech communication system and method thereof using attachable optical sensor

Abstract

To disclose an attachable optical sensor, a silent speech communication system and a silent speed communication method.SOLUTION: A plurality of optical fiber layers may be arranged in layers in a vertical direction relative to each other. A support member may include optical fibers arranged in the vertical direction. The support member may vertically connect the plurality of optical fiber layers arranged in layers in the vertical direction. Light sources may be connected to one side of the optical fibers included in each optical fiber layer and one side of the optical fibers included in the support member, so as to supply light to the optical fibers. Light receivers may be connected to the other side of the optical fibers included in each optical fiber layer and the other side of the optical fibers arranged in the support member, so as to sense light passing through the optical fibers.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The techniques described below relate to silent communication systems. [Background technology]

[0002] Silent-Speech Interface technology is a technology that allows users to communicate virtually silently. Silent-Speech Interface allows users with hearing and speech disabilities, those who have difficulty speaking accurately due to laryngectomy or vocal cord nodules, and military, police, fire, and security personnel who must speak while wearing a mask to communicate without using voice. Among silent-speech interfaces, silent speech recognition technology, which allows communication using only the shape of the mouth without actual voice, is highly resistant to ambient noise and communication security. [Prior art documents] [Patent documents]

[0003] [Non-Patent Document 1] Machine Learning Methods for Automatic Silent Speech Recognition Using a Wearable Graphene Strain Gauge Sensor (Published December 31, 2021) Summary of the Invention [Problem to be solved by the invention]

[0004] Previous silent speech interface technologies included those that capture and use the air coming out of the mouth and those that capture and use the movements of a person's face. However, these existing technologies had problems such as requiring a certain level of sound (ex35db(A)) or that their performance was affected by the shooting angle and the presence or absence of light. This made them particularly difficult to use in everyday life, wartime, and operational situations where recognizable sounds are very limited.

[0005] The technology described below aims to disclose a silent communication system that enables verbal communication using only minute movements of a person's skin without actual voice. [Means for solving the problem]

[0006] The technology described below discloses an adhesive optical sensor, a silent communication system, and a silent communication method.

[0007] In one embodiment of the technology described below, the wearable optical sensor may include an optical fiber layer, a support member, and an optical receiver. The optical fiber layer may include optical fibers arranged horizontally in a lattice structure. The optical fiber layer may include a plurality of optical fiber layers arranged vertically in layers. The support member may include optical fibers arranged vertically. The support member may vertically connect the plurality of optical fiber layers arranged vertically in layers. The light source may be connected to one side of the optical fiber included in the optical fiber layer and one side of the optical fiber included in the support member to supply light to the optical fiber. The optical receiver may be connected to the other side of the optical fiber included in the optical fiber layer and the other side of the optical fiber arranged in the support member to sense light passing through the optical fiber.

[0008] As one embodiment of the technology described below, the silent communication system may include a sensor unit that acquires optical sensing data using an attachable optical sensor, a data processing unit that includes an inference module that generates sound data based on the optical sensing data, and a speaker unit that outputs sound based on the sound data.

[0009] As one embodiment of the technology described below, the silent communication method may include a step of a sensor unit acquiring optical sensing data, a step of an inference module included in a data processing unit generating sound data based on the optical sensing data, and a step of a speaker unit outputting sound corresponding to the sound data. [Effects of the Invention]

[0010] The technology described below can be used to sense the movement of the user's skin.

[0011] Using the technology described below, people can have conversations based on the results of sensing the movements of the user's skin.

[0012] The technology described below enables communication between people without voice during wartime and operational situations, is resistant to loud ambient noise, and solves problems such as communication security.

[0013] The technology described below can be applied not only to silent speech interfaces, but also to measuring muscle and joint movements, which can be useful for diagnosing musculoskeletal disorders and rehabilitation treatments. [Brief explanation of the drawings]

[0014] [Figure 1] FIG. 1 is a perspective view illustrating an example of an adhesive optical sensor including two optical fiber layers, according to one embodiment. [Figure 2] FIG. 1 illustrates a top view of an example of an adhesive optical sensor including two layers of optical fiber, according to one embodiment. [Figure 3]FIG. 1 illustrates a power communication unit included in an adhesive optical sensor including two layers of optical fiber, according to one embodiment. [Figure 4] FIG. 1 illustrates an embodiment of an adhesive optical sensor attached to a tongue. [Figure 5] 1 is a diagram illustrating an example of a silent communication system according to an embodiment. [Figure 6] FIG. 1 is a diagram illustrating an example of an implementation of a silent communication system according to an embodiment. [Figure 7] 1 illustrates an example of a silent communication system performing a silent communication method, according to one embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0015] The technology described below can be modified in various ways and can have various embodiments. Specific embodiments of the technology described below may be illustrated in the drawings of the specification. However, this is for the purpose of explaining the technology described below and does not limit the technology described below to specific embodiments. Therefore, it should be understood that all modifications, equivalents, or alternatives falling within the spirit and technical scope of the technology described below are included in the technology described below.

[0016] Terms such as "first," "second," "A," and "B" may be used to describe various components. However, these terms are used merely to distinguish one component from another and are not intended to limit the components. For example, a first component could be termed a second component, and similarly, a second component could be termed a first component, without departing from the scope of the technology described below. The term "and / or" includes a combination of two or more related listed items or any of two or more related listed items.

[0017] In the terms used below, the singular expression "a," "an," or "an" should be understood to include the plural expression unless the context clearly indicates otherwise, and the term "comprise" or similar should be understood to mean the presence of a stated feature, number, step, operation, component, part, or combination thereof, but not to exclude the presence or possibility of adding one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0018] Before proceeding to a detailed description of the drawings, it should be made clear that the division of components in this specification is merely a division according to the main function of each component. That is, two or more components described below may be combined into one component, or one component may be divided into two or more components according to more specific functions. Furthermore, each of the components described below may perform some or all of the functions performed by other components in addition to its own main function, and some of the main functions performed by each component may be exclusively performed by other components.

[0019] Furthermore, in performing a method or method of operation, the steps constituting the method may be performed in an order other than that stated, unless the context clearly dictates a particular order, i.e., the steps may be performed in the same order as stated, substantially simultaneously, or in reverse order.

[0020] In one embodiment, the wearable optical sensor may be a sensor used in a silent communication system, or may be a sensor used to measure human muscle movements, etc.

[0021] The wearable optical sensor can be attached to a person's body, for example, the wearable optical sensor can be attached to the top or bottom of the tongue, the roof of the mouth, the lips, the cheeks, the vocal cords in the neck, the arms, the legs, etc.

[0022] The wearable optical sensor can detect minute changes or movements of a person's skin, and can measure minute changes or movements of the skin that occur during silent speech.

[0023] The wearable optical sensor may include an optical fiber. The optical fiber included in the wearable optical sensor may change in response to minute changes or movements of the skin. The optical fiber included in the wearable optical sensor may be stretched or compressed in response to minute changes or movements of the skin. As the optical fiber changes, the path, intensity, or phase of light passing through the optical fiber may change. Based on these changes, changes or movements of the skin may be detected.

[0024] Adhesive optical sensors can include plasmonic strain materials instead of optical fibers, which can enable highly sensitive strain rate sensing by sensing changes in localized surface plasmon resonance (LSPR).

[0025] The adhesive optical sensor may include optical fibers arranged horizontally in a lattice structure. When force is applied to the adhesive optical sensor in the X-axis and Y-axis directions, changes may occur in the optical fibers included in the optical fiber layer. Therefore, the optical fibers included in the optical fiber layer can sense the force applied in the X-axis and Y-axis directions.

[0026] The wearable optical sensor may include an optical fiber arranged in the vertical direction. When a force is applied to the wearable optical sensor in the Z-axis direction, a change may occur in the optical fiber arranged in the vertical direction. For example, when the wearable optical sensor is attached to a tongue, if pressure is generated in the Z-axis direction on the wearable optical sensor by the tongue or teeth, a change may occur in the optical fiber included in the support member. Thus, the wearable optical sensor can measure pressure.

[0027] The wearable optical sensor can measure not only two-dimensional minute changes or movements of the skin but also three-dimensional minute changes or movements of the skin through horizontally arranged optical fibers and vertically arranged optical fibers.

[0028] In one embodiment, the wearable optical sensor may include an optical fiber layer, a light source, an optical receiver, and a support member, and may further include a power supply / communication unit and an adhesive patch unit.

[0029] The optical fiber layer can include optical fibers. The optical fiber layer can include horizontally arranged optical fibers. The optical fiber layer can include optical fibers in a lattice structure. The optical fiber layer can include horizontally arranged optical fibers in a lattice structure.

[0030] There may be multiple optical fiber layers, which may be arranged vertically one above the other, and which may have the same or different shapes, configurations, and structures.

[0031] The support member may include an optical fiber. The support member may include a vertically disposed optical fiber.

[0032] The support member can connect multiple optical fiber layers. The support member can connect multiple optical fiber layers in a vertical direction. The support member can connect multiple optical fiber layers arranged in layers in a vertical direction.

[0033] The light source may be coupled to one side of the optical fiber. The light source may be coupled to one side of the optical fiber included in the optical fiber layer. The light source may be coupled to one side of the optical fiber included in the support member. The light source may supply light to the optical fiber. The light source may be coupled to one side of the optical fiber included in the optical fiber layer and one side of the optical fiber included in the support member to supply light to the optical fibers.

[0034] The optical receiver may be coupled to the other side of the optical fiber. The optical receiver may be coupled to the other side of the optical fiber included in the optical fiber layer. The optical receiver may be coupled to the other side of the optical fiber included in the support member. The optical receiver may sense light passing through the optical fiber. The optical receiver may be coupled to the other side of the optical fiber included in the optical fiber layer and the other side of the optical fiber included in the support member, and may sense light passing through the optical fiber. The optical receiver may sense at least one of the path, intensity, and phase of light passing through the optical fiber.

[0035] The optical fiber layers may have the same or different shapes, configurations, or structures. For example, the optical fiber layers may have the same rectangular shape. Alternatively, the optical fiber layers may have a circular shape in some portions and a rectangular shape in the other portions.

[0036] A light source and an optical receiver can be provided for each of the multiple optical fiber layers. For example, if the adhesive optical sensor has three optical fiber layers, a light source and an optical receiver can be provided for each layer, resulting in a total of three light sources and three optical receivers in the adhesive optical sensor.

[0037] A portion of the optical fiber included in the support member may be coupled to a light source included in the upper optical fiber layer and an optical receiver included in the lower optical fiber layer, and the remainder of the optical fiber may be coupled to a light source included in the lower optical fiber layer and an optical receiver included in the upper optical fiber layer.

[0038] The power communication unit can supply power to the light source and the light receiver.

[0039] The power communication unit can transmit and receive optical sensing data. To this end, the power communication unit can use near-field magnetic induction (NFMI) technology. The use of NFMI technology enables power-efficient short-range wireless charging and data transmission / reception to a near-field power source and wireless receiver. In addition, the NFMI technology can be fabricated into a flexible and very small micro-strain chip, allowing it to be attached to the skin in a patch-type configuration. In addition, the use of the NFMI strain chip enables operation with very low power and resistance to radio frequency (RF) interference, enabling short-range communication that is safe from eavesdropping.

[0040] The adhesive patch can allow the adhesive optical sensor to adhere to the skin, can be non-toxic to the human body, can remain attached for several hours, and can be resistant to body waste such as saliva and sweat.

[0041] The adhesive patch may include an adhesive substance that reacts with saliva to generate adhesive strength. The adhesive patch may include an adhesive substance that dissolves over time after application. For example, the adhesive substance may include materials such as ethyl cellulose, PVP, glycerin, or silicone.

[0042] 1 to 3 show an example of an adhesive optical sensor 100 according to one embodiment, which includes two optical fiber layers, which will be referred to as a first optical fiber layer 110, a first light source 111, a first optical receiver 112, a second optical fiber layer 120, a second light source 121, and a second optical receiver 122, respectively, for ease of explanation.

[0043] Fig. 1 is a perspective view of the wearable optical sensor 100 according to the embodiment. Fig. 2 is a top view of the wearable optical sensor 100 according to the embodiment. Fig. 3 is a diagram illustrating a power supply communication unit 140 included in the wearable optical sensor 100 according to the embodiment.

[0044] The wearable optical sensor 100 may include a first optical fiber layer 110, a first light source 111, a first optical receiver 112, a second optical fiber layer 120, a second light source 121, a second optical receiver 122, and a support member 130. The wearable optical sensor 100 may further include a power communication unit 140 and an adhesive patch unit 150.

[0045] The first optical fiber layer 110 and the second optical fiber layer 120 may include optical fibers arranged horizontally in a lattice structure. The support member 130 may include optical fibers arranged vertically. The first optical fiber layer 110 and the second optical fiber layer 120 may be arranged in layers vertically. The first optical fiber layer 110 may be located on the upper side, and the second optical fiber layer 120 may be located on the lower side. The support member 130 may vertically connect the first optical fiber layer 110 and the second optical fiber layer 120 arranged in layers vertically.

[0046] The light sources 111, 121 and light receivers 112, 122 may be present in the first optical fiber layer 110 and the second optical fiber layer 120, respectively.

[0047] The first light source 111 can be located on two adjacent sides of the first optical fiber layer 110. The first optical receiver 112 can be located on two adjacent sides of the first optical fiber layer 110. The first optical receiver 112 can be located on two adjacent sides of the first optical fiber layer 110 opposite to the first light source 111.

[0048] The first light source 111 may be connected to one side of the optical fiber included in the first optical fiber layer 110. The first light source 111 may supply light to the inside of the optical fiber included in the first optical fiber layer 110. The first optical receiver 112 may be connected to the other side of the optical fiber included in the first optical fiber layer 110. The first optical receiver 112 may sense light passing through the optical fiber included in the first optical fiber layer 110.

[0049] The second light source 121 can be located on two adjacent sides of the second optical fiber layer 120. The second optical receiver 122 can be located on two adjacent sides of the second optical fiber layer 120. The second optical receiver 122 can be located on two adjacent sides of the second optical fiber layer 120 opposite to the second light source 121.

[0050] The second light source 121 may be connected to one side of the optical fiber included in the second optical fiber layer 120. The second light source 121 may supply light to the inside of the optical fiber included in the second optical fiber layer 120. The second optical receiver 122 may be connected to the other side of the optical fiber included in the second optical fiber layer 120. The second optical receiver 122 may sense light passing through the optical fiber included in the second optical fiber layer 120.

[0051] A portion of the optical fiber included in the support member 130 may be connected between the first light source 111 and the second optical receiver 122. The first light source 111 may be connected to one side of the portion of the optical fiber included in the support member 130. The second optical receiver 122 may be connected to the other side of the portion of the optical fiber included in the support member 130.

[0052] The remainder of the optical fiber included in the support member 130 may be coupled between the second light source 121 and the first optical receiver 112. The second light source 121 may be coupled to one side of the remainder of the optical fiber included in the support member 130. The first optical receiver 112 may be coupled to the other side of the remainder of the optical fiber included in the support member 130.

[0053] The power communication unit 140 may be located between the first optical fiber layer 110 and the second optical fiber layer 120 .

[0054] The power communication unit 140 may include a battery 141 that supplies power, a data collector 142 that collects optical sensing data from an optical receiver, a power receiver 143 that receives power to the NFMI microchip via near field communication, and a data transmitter 144 consisting of an NFMI antenna that transmits the optical sensing data. In this case, the NFMI microchip has a unique ID and can transmit data together with the NFMI ID when transmitting data. The power communication unit 140 can be supplied with power using NFMI technology.

[0055] The adhesive patch part 150 may be located below the second optical fiber layer 120. The adhesive patch part 150 allows the wearable optical sensor 100 to adhere to human skin.

[0056] FIG. 4 illustrates an embodiment of a wearable optical sensor 100 attached to a tongue. As shown in FIG. 4, the wearable optical sensor 100 may be positioned at the top of the tongue. As such, the wearable optical sensor 100 can detect tongue movement and acquire optical sensing data. This is merely an example, and the wearable optical sensor 100 does not necessarily have to be attached to the tongue. The wearable optical sensor 100 can be attached anywhere that can be attached to human skin. In addition to silent speech interfaces, the wearable optical sensor 100 can also be used to measure muscle and joint movements, thereby enabling diagnosis or rehabilitation of musculoskeletal disorders.

[0057] FIG. 5 illustrates an example of a silent communication system 200 according to one embodiment.

[0058] The silent communication system 200 may include a sensor unit 210, a speaker unit 220, a microphone unit 230, a relay unit 240, a data processing unit 250, and a communication unit 260. The sensor unit 210, the speaker unit 220, the microphone unit 230, the relay unit 240, the data processing unit 250, and the communication unit 260 included in the silent communication system 200 may be implemented as separate devices, or may be implemented as a single device or multiple devices. For example, a speaker, a microphone, and a relay may be included in a single earphone. Alternatively, the sensor unit 210, the microphone unit 230, and the relay unit 240 may be included in a single sensor.

[0059] The sensor unit 210 can acquire optical sensing data using an adhesive optical sensor such as the one shown in FIG.

[0060] The speaker unit 220 can output sound. The speaker unit 220 can output sound to a user. The speaker unit 220 can be physically realized in various ways. For example, the speaker unit 220 can be realized in the form of earphones, earbuds, a headset, etc.

[0061] The speaker unit 220 can output sound corresponding to the sound data received from the relay unit 240. The sound data received by the speaker unit 220 can be data related to sound inferred from the light sensing data.

[0062] The microphone unit 230 can acquire sound. The microphone unit 230 can acquire sound corresponding to the user's voice. The microphone unit 230 can be physically realized in various ways.

[0063] The microphone unit 230 can acquire sound data corresponding to the voice spoken by the user wearing the sensor unit 210. The sound data acquired by the microphone unit 230 can become learning data necessary for building an analysis model.

[0064] The relay unit 40 can transmit and receive data to and from the sensor unit 210, the speaker unit 220, the microphone unit 230, and the data processing unit 250. The relay unit 240 can communicate with the sensor unit 210, the speaker unit 220, the microphone unit 230, and the data processing unit 250 wirelessly and / or via wire. For example, the relay unit 240 can receive optical sensing data from the sensor unit 210. The relay unit 240 can transmit sound data to the speaker unit 220. The relay unit 240 can receive sound data from the microphone unit 230. The relay unit 240 can transmit and receive optical sensing data and sound data to and from the data processing unit 250.

[0065] The relay unit 240 may include a chip for wireless communication and / or wireless power transmission. As an example, the relay unit 240 may include an NFMI microchip.

[0066] The relay unit 240 may be located close to the sensor unit 210. Because the relay unit 240 is located close to the sensor unit 210, the relay unit 240 can perform wireless communication and / or wireless power transmission with the sensor unit 210. For example, because the relay unit 240 is located close to the sensor unit 210, the relay unit 240 can perform NFMI-based wireless communication and wireless power transmission with the sensor unit 210. Wireless power supply or data transmission can be performed between the relay unit 240 and the power communication unit 140 via an NFMI chip attached to each other. The NFMI chip allows for efficient power supply and wireless transmission without complex wiring. Power can be wirelessly supplied from the relay unit 240 to the optical sensor via the NFMI chip. The power communication unit 140 can wirelessly transmit optical sensing data to the relay unit via the NFMI chip.

[0067] The data processing unit 250 can perform data processing, calculations, etc. required for the operation of the silent communication system 200. The data processing unit 250 can perform calculations required for the silent communication method. The data processing unit may be a device including a processor, an AP (Application Processor), or a chip with an embedded program that processes certain calculations. For example, the calculation device 930 may include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or an NPU (Neural Processing Unit), etc.

[0068] The data processing unit 250 can be physically realized in various forms, such as a PC, a notebook computer, a smart device, a server, or a chipset dedicated to data processing.

[0069] The data processing unit 250 may include an inference module 252 and a learning module 251 .

[0070] The inference module 252 can generate sound data based on the light sensing data. The inference module 252 can generate sound data corresponding to the light sensing data based on the light sensing data.

[0071] The inference module 252 can generate sound data based on the light sensing data using an analytical model. The inference module 252 can input the light sensing data to the trained analytical model and then generate sound data based on the output value of the analytical model. The analytical model used by the inference module 252 can be a model trained by the learning module 251.

[0072] The sound data generated by the inference module 252 may be transmitted to the speaker unit 220. The sound data generated by the inference module 252 may be transmitted to the speaker unit 220 via the relay unit 240. The speaker unit 220 may output sound to the user based on the transmitted sound data.

[0073] The learning module 251 can train an analytical model based on the training data.

[0074] The learning module 251 can construct learning data for training an analysis model based on the optical sensing data acquired by the sensor unit 210 and the sound data acquired by the microphone unit 230. As an example, the learning module 251 can construct learning data for training an analysis model by pairing the optical sensing data acquired by the sensor unit 210 and the sound data of the user acquired by the microphone unit 230.

[0075] The learning module 251 can store the constructed learning data in a database. The database may record the user's light sensing data and the user's sound data. The database may also record the characteristics of the user's individual speech voice and light sensing data.

[0076] The learning module 251 can preprocess the training data and then train the analytical model. For example, the learning module 251 can convert the training data into a form suitable for training the analytical model by performing preprocessing such as noise removal, normalization, and dimensionality reduction (PCA, t-SNE) on the training data.

[0077] The analytical model may be a model that generates, from the light sensing data, sound data corresponding to the light sensing data.

[0078] The analytical model may be a machine learning (ML)-based model. A machine learning-based model may learn through data to understand a specific object or condition, or may find and classify patterns in data. Machine learning-based models may be of various types. For example, machine learning-based models may include decision trees, random forests (RF), k-nearest neighbors (KNN), naive Bayes, support vector machines (SVM), and artificial neural networks (ANN). The ANN may be a deep neural network (DNN), which may include convolutional neural networks (CNN), recurrent neural networks (RNN), restricted Boltzmann machines (RBM), deep belief networks (DBN), generative adversarial networks (GAN), and relation networks (RL).

[0079] The analysis model may be a model that performs an attention mechanism. The analysis model may generate sound data by focusing more on data necessary for generating sound data from optical sensing data. For example, the analysis model may generate sound data by focusing more on data affected by movements of the tongue, lips, vocal cords, etc. in the optical sensing data.

[0080] The analytical model can include an encoder-decoder structure. The encoder can compress the optical sensing data and extract only the parts necessary to generate sound data. The decoder can generate sound data based on the information extracted by the encoder.

[0081] The communication unit 260 can transmit or receive data via wired or wireless communication. The communication unit 260 can transmit or receive light sensing data. The inference module 252 can generate sound data based on the light sensing data received by the communication unit 260. The communication unit 260 can also transmit or receive sound data. When the communication unit 260 receives light sensing data and sound data from a third party other than the user, the user and the third party can communicate silently.

[0082] FIG. 6 illustrates an example implementation of a silent communication system according to one embodiment.

[0083] The sensor unit 210 may include at least one wearable optical sensor. The wearable optical sensor may be attached to a person's nasal groove, lower jaw, and neck area near the vocal cords. The earphone may include a relay unit 240 and a speaker unit 220. The relay unit 240 may receive optical sensing data from at least one wearable optical sensor. The relay unit 240 may collect the optical sensing data received from the at least one wearable optical sensor and transmit the collected data to the data processing unit 250. The data processing unit 250 may generate sound data based on the received optical sensing data. The data processing unit 250 may be implemented in the form of a smartphone. The communication unit 260 may transmit the optical sensing data and the sound data to another data processing unit or receive the optical sensing data and the sound data from another data processing unit. The speaker unit 220 may output sound based on the sound data. This allows a person to hear sound through the movement of the skin even without direct sound. Furthermore, a person may communicate with a third party by listening to sound based on the third party's optical sensing data.

[0084] FIG. 7 illustrates an example 300 of a silent communication system performing a silent communication method, according to one embodiment.

[0085] The sensor unit may acquire optical sensing data (310). For example, when a speaker begins silent speech, the sensor unit may acquire optical sensing data corresponding to minute changes or movements of the skin via an adhesive optical sensor attached around the vocal cords of the neck. The sensor unit may transmit the acquired optical sensing data to a relay unit (320). The relay unit may be implemented in the form of earphones or as part of the earphones. The relay unit may transmit the received optical sensing data to a data processing unit (330). The data processing unit may be a smartphone. The data processing unit may generate sound data based on the received optical sensing data (340). The data processing unit may transmit the generated sound data to the relay unit (350). The relay unit may transmit the sound data to a speaker unit (360). The speaker unit may be implemented in the form of earphones or as part of the earphones. The speaker unit may output sound corresponding to the sound data (370).

Claims

1. 1. An adhesive optical sensor comprising an optical fiber layer, a support member, a light source, and an optical receiver, the optical fiber layer includes optical fibers arranged horizontally in a lattice structure; The optical fiber layers are a plurality of layers arranged vertically relative to one another, the support member includes an optical fiber arranged in the vertical direction, the support member vertically connects the plurality of optical fiber layers arranged in layers in the vertical direction, the light source is connected to one side of the optical fiber included in the optical fiber layer and one side of the optical fiber included in the support member to supply light to the optical fibers; The optical receiver is connected to the other side of the optical fiber included in the optical fiber layer and the other side of the optical fiber disposed on the support member, and detects light passing through the optical fiber.

2. The adhesive optical sensor according to claim 1 , wherein the light source and the optical receiver are provided for each of the plurality of optical fiber layers.

3. 3. The adhesive optical sensor of claim 2, wherein a portion of the optical fiber included in the support member is connected to a light source included in the upper optical fiber layer and an optical receiver included in the lower optical fiber layer, and the remainder of the optical fiber is connected to a light source included in the lower optical fiber layer and an optical receiver included in the upper optical fiber layer.

4. The adhesive optical sensor according to claim 1 , wherein the optical receiver senses at least one of a path, intensity, and phase of light passing through an interior of the optical fiber.

5. The adhesive optical sensor of claim 1 , wherein the plurality of optical fiber layers have the same or different shapes, configurations, and structures.

6. The adhesive optical sensor further includes a power supply communication unit, 2. The wearable optical sensor of claim 1, wherein the power communication unit includes a battery that supplies power to the wearable optical sensor, a data collector that collects optical sensing data from the optical receiver, and a data transmitter that transmits the optical sensing data.

7. the adhesive optical sensor further includes an adhesive patch portion; The adhesive optical sensor of claim 1 , wherein the adhesive patch portion comprises an adhesive material that allows the adhesive optical sensor to adhere to human skin.

8. a sensor unit that acquires optical sensing data using an adhesive optical sensor; a data processing unit including an inference module that generates sound data based on the optical sensing data; a speaker unit that outputs sound based on the sound data, The silent communication system, wherein the adhesive optical sensor is the adhesive optical sensor of claim 1 .

9. The silent communication system according to claim 8 , further comprising a relay unit capable of transmitting and receiving data to and from the sensor unit, the data processing unit, and the speaker unit.

10. the inference module generates sound data based on the light sensing data using an analytical model; The silent communication system according to claim 8 , wherein the analytical model is a trained model that is trained based on training data.

11. 11. The silent communication system of claim 10, wherein the analytical model comprises an artificial neural network (ANN)-based model capable of performing an attention mechanism to further focus data necessary to generate sound data from the optical sensing data.

12. The silent communication system of claim 10, wherein the analytical model includes an encoder-decoder structure.

13. The silent communication system according to claim 8 , further comprising a communication unit capable of transmitting or receiving at least one of optical sensing data and sound data.

14. The silent communication system further includes a microphone unit for capturing a sound corresponding to a user's voice; the data processing unit further includes a learning module; The silent communication system of claim 8, wherein the learning module constructs learning data necessary to train an analytical model used by the inference module based on the optical sensing data acquired by the sensor unit and the sound corresponding to the user's voice acquired by the microphone unit.

15. 9. A method for performing a silent communication method in a silent communication system according to claim 8, comprising: A step in which a sensor unit acquires light sensing data; generating sound data based on the optical sensing data by an inference module included in the data processing unit; and a step of outputting a sound corresponding to the sound data by the speaker unit.

16. The silent communication system further includes a relay unit; The silent communication method according to claim 15 , further comprising the step of transmitting or receiving data from the relay unit to or from the sensor unit, the data processing unit, and the speaker unit.

17. the inference module generates sound data based on the light sensing data using an analytical model; The silent communication method according to claim 15, wherein the analytical model is a training model trained based on training data.

18. The silent communication system further includes a communication unit; The silent communication method according to claim 15, further comprising the step of transmitting or receiving at least one of optical sensing data and sound data by the communication unit.

19. The silent communication system further includes a microphone unit, the data processing unit further includes a learning module; The silent communication method includes: a step of acquiring a sound corresponding to a user's voice by the microphone unit; The silent communication method of claim 15, further comprising a step in which a learning module included in the data processing unit constructs learning data necessary for training an analytical model used by the inference module based on the optical sensing data acquired by the sensor unit and the sound corresponding to the user's voice acquired by the microphone unit.

Images