KR102178414B1 - Wireless sound converting device with multiple microphone units - Google Patents

Abstract

The present invention relates to wireless sound conversion device having a plurality of microphone units, which includes the plurality of microphone units and determines gains of sound signals from the plurality of microphone units according to ambient noise characteristics. According to the present invention, the wireless sound conversion device includes: first and second microphones each obtaining sound to generate and apply first and second electrical signals; a communication unit which performs wireless communication with an electronic device; and a data processor which performs wireless communication with the electronic device through the communication unit, receives first and second electrical signals from the first and second microphones, and receives first and second electrical signals based on the signal-to-noise ratio of the first electrical signal to determine first and second gain ratios for each of the electrical signals, and then processes the first and second electrical signals according to a determined first and second gain ratio, generates an output signal by summing the processed first and second electrical signals, and transmits the generated output signal through the communication unit to the electronic device.

Description

A wireless sound conversion device having a plurality of microphone units TECHNICAL FIELD [0002]

The present invention relates to a wireless acoustic conversion device, and more particularly, to a wireless acoustic conversion device including a plurality of microphone units, which have a plurality of microphone units and determine gains of sound signals from the plurality of microphone units according to ambient noise characteristics. .

The most problematic in signal processing of speech or acoustic data is the removal of noise included in the signal, and the noise can be divided into noise evenly distributed over the entire section of the signal and sporadic noise temporarily present in a specific section.

Among them, sporadic noise is impulse noise, that is, it exists for a short time, and its amplitude is very large and has a simple waveform, and sporadic noise, that is, it exists for a relatively long time compared to impulse noise. It is roughly classified as noise.

Conventionally, a method of removing noise existing over the entire signal has been used, and these methods include a method such as a classical filter or an adaptive filter and a method such as an average noise removal method, and impulse noise, which is one of the sporadic noise, has been used. Methods for removal include using a variable region or a method of using correlation between front and rear signals.

When noise is reduced or removed by using existing noise reduction methods, there is a side effect of distorting or removing necessary signal components. Removing the noise component from the input signal and detecting only the necessary voice signal is very effective in enabling efficient use of the communication bandwidth, improving the system performance and the compression rate of the voice coding in voice signal processing, voice coding and various data communication fields. It's an important issue.

An object of the present invention is to provide a wireless acoustic conversion apparatus including a plurality of microphone units and including a plurality of microphone units for determining gains of sound signals from the plurality of microphone units according to ambient noise characteristics.

The wireless acoustic conversion apparatus of the present invention includes first and second microphones that respectively obtain sound and generate and apply first and second electrical signals, a communication unit for performing wireless communication with an electronic device, and a wireless communication unit through the communication unit. By performing communication, receiving first and second electric signals from the first and second microphones, and receiving first and second electric signals for each of the first and second electric signals based on the signal-to-noise ratio of the first electric signal. A gain ratio is determined, the first and second electrical signals are processed according to the determined first and second gain ratios, the processed first and second electrical signals are summed to generate an output signal, and the generated output signal is A data processor that transmits to the electronic device through the communication unit is provided, and when the wireless acoustic conversion device is worn by the wearer, the first microphone is exposed to the outside of the wearer's hearing organ, and the second microphone is at least partially covered by the wearer's hearing organ. It is preferable to be inserted or blocked from the outside by the case of the wireless sound conversion device.

delete

In addition, the data processor stores at least one gain reference data corresponding to the ambient noise environment, and determines first and second gain ratios according to the signal-to-noise ratio of the first electrical signal from the stored gain reference data, the first and It is preferable that the sum of the second gain ratios is a reference ratio.

In addition, it is preferable that the data processor receives and stores the gain reference data from the electronic device through the communication unit.

Also, it is preferable that the data processor determine gain reference data suitable for the characteristic of the frequency axis signal of the first electrical signal.

Further, in an acoustic communication system comprising a wireless acoustic conversion apparatus according to the present invention, an electronic device performing communication with the wireless acoustic conversion apparatus, and a data server, the wireless acoustic conversion apparatus transmits first and second electrical signals for a predetermined time to the electronic device. And the electronic device receives the first and second electrical signals, transmits the first and second electrical signals to the data server, the data server receives the first and second electrical signals, and the received first Feature data extracted by performing MFCC (Mel Frequency Cepstral Coefficient) on the frequency axis signal of the first electrical signal by performing frequency axis transformation on the electrical signal, and performing artificial neural network processing on the extracted feature data It determines the most suitable gain reference data, transmits the determined gain reference data to the electronic device, the electronic device receives the determined gain reference data, and transmits the determined gain reference data to the wireless acoustic conversion device.

The present invention includes a plurality of microphone units, determines the gain of each of the sound signals from the plurality of microphone units according to the ambient noise characteristics, performs gain processing, so that the wearer's voice (sound) is well transmitted. There is an effect of enabling attenuation processing (noise removal processing) for ambient noise by determining gain reference data having a gain ratio suitable for noise characteristics.

1 is a control configuration diagram of an acoustic communication system including a wireless acoustic conversion device and an electronic device according to the present invention.
2 is an example of gain reference data.

In the following, the present invention will be described in detail through examples and drawings. However, this is not intended to limit the present invention to a specific embodiment, it should be understood to include various modifications, equivalents, and/or alternatives of the embodiments of the present invention. In connection with the description of the drawings, similar reference numerals may be used for similar elements.

In this document, expressions such as "have", "may have", "include", or "may contain" are the presence of corresponding features (eg, elements such as numbers, functions, actions, or parts). And does not exclude the presence of additional features.

In this document, expressions such as "A or B", "at least one of A or/and B", or "one or more of A or/and B" may include all possible combinations of items listed together. . For example, “A or B”, “at least one of A and B”, or “at least one of A or B” includes (1) at least one A, (2) at least one B, Or (3) it may refer to all cases including both at least one A and at least one B.

Expressions such as “first”, “second”, “first”, or “second” used in this document can modify various elements regardless of their order and/or importance, and It is used to distinguish it from the component, but does not limit the component. For example, a first user device and a second user device may represent different user devices regardless of order or importance. For example, without departing from the scope of the rights described in this document, a first component may be referred to as a second component, and similarly, a second component may be renamed to a first component.

Some component (eg, a first component) is "(functionally or communicatively) coupled with/to)" to another component (eg, a second component) or " When referred to as "connected to", it should be understood that the certain component may be directly connected to the other component or may be connected through another component (eg, a third component). On the other hand, when a component (eg, a first component) is referred to as being “directly connected” or “directly connected” to another component (eg, a second component), the component and the It may be understood that no other component (eg, a third component) exists between the different components.

The expression "configured to" used in this document is, for example, "suitable for", "having the capacity to" depending on the situation. It can be used interchangeably with ", "designed to", "adapted to", "made to", or "capable of". The term "configured to (or set) to" may not necessarily mean only "specifically designed to" in hardware. Instead, in some situations, the expression "a device configured to" may mean that the device "can" along with other devices or parts. For example, the phrase “a processor configured (or configured) to perform A, B, and C” means a dedicated processor (eg, an embedded processor) for performing the operation, or executing one or more software programs stored in a memory device. By doing so, it may mean a generic-purpose processor (eg, a CPU or an application processor) capable of performing corresponding operations.

Terms used in this document are only used to describe a specific embodiment, and may not be intended to limit the scope of other embodiments. Singular expressions may include plural expressions unless the context clearly indicates otherwise. Terms used herein, including technical or scientific terms, may have the same meaning as commonly understood by one of ordinary skill in the technical field described in this document. Among the terms used in this document, terms defined in a general dictionary may be interpreted as having the same or similar meaning as the meaning in the context of the related technology, and unless explicitly defined in this document, they may be interpreted in an ideal or excessively formal meaning. It is not interpreted. In some cases, even terms defined in this document cannot be interpreted to exclude embodiments of this document.

1 is a control configuration diagram of an acoustic communication system including a wireless acoustic conversion apparatus and an electronic device according to the present invention, and FIG. 2 is an example of gain reference data.

The wireless sound conversion devices 10 and 20 perform wireless communication with the electronic device 30 (for example, Bluetooth communication, etc.), and the wireless sound conversion device 10 (for example, for the right auditory organ) and wireless sound The conversion device 20 (for example, for a left auditory organ) also performs wireless communication with each other.

The wireless acoustic conversion device 10 includes an input unit 11 that obtains an input (for example, power on/off, selection of a playback song, selection of gain reference data, etc.) from a wearer and applies it to the data processor 19, A display unit 12 that displays power status (eg, charging, degree of charge, etc.), a communication unit 13 that performs wireless communication with the electronic device 30 and/or the wireless sound conversion device 20, The first and second microphones 14a, 14b, and the electronic device 30 respectively generate first and second electrical signals of each of the acquired sound by obtaining sound and apply it to the data processor 19, respectively. A speaker 15 that emits sound by receiving an electrical signal from the data processor 19 and the above-described components are controlled to sound such as a sound reproduction function and a phone call function through wireless communication with the electronic device 30 While performing the conversion function, each of the first and second electric signals is applied from each of the first and second microphones 14a and 14b, and processed according to the gain processing data, and the processed first and second electric signals are It consists of a data processor 19 that adds up to generate an output signal. However, the power supply unit (not shown), the input unit 11, the display unit 12, the communication unit 13, and the speaker 15 that supply power are naturally recognized by those with ordinary knowledge in the technical field to which the present invention belongs. It corresponds to a technique only to the extent that it becomes, and a detailed description thereof is omitted.

The first and second microphones 14a and 14b are the same as the microphone, but the wireless sound conversion device 10 is mounted or inserted into the wearer's hearing organ, so that sound conversion by the wearer (for example, sound reproduction When used for a function, a phone call function, etc.), the characteristics of the sound obtained by the installation position or the wearing position are different.

The first microphone 14a is exposed to the outside (outside of the wearer's hearing organ) and is mounted at a position capable of acquiring both sound from the wearer's pronunciation organ (ie, mouth, etc.) and ambient noise. On the other hand, the second microphone 14b is at least partially inserted into the wearer's hearing organ and is blocked from the outside, or is mounted at a location that is blocked from the outside by the case of the wireless acoustic conversion device 10, so that the surrounding noise is significantly reduced. While mainly acquiring sound from the wearer's pronunciation organ. Due to this positional difference, the frequency of the sound signal obtained from the first microphone 14a includes the entire frequency band, but the frequency of the sound signal obtained from the second microphone 14b is within the frequency band (for example, For example, a frequency within 2 kHz), or a frequency band exceeding the voice frequency band to a certain extent. That is, the frequency band of the sound signal obtained from the first microphone 14a is larger than the frequency band of the sound signal obtained from the second microphone 14b.

As described above, since the first electrical signal from the first microphone 14a can better acquire the ambient noise than the second electrical signal from the second microphone 14b, the data processor 19 The signal is used to determine the ambient noise or ambient noise environment.

The data processor 19 controls the communication unit 13, the first and second microphones 14a and 14b, and the speaker 15 to perform a sound reproduction function, a phone call function, etc. , MICROPROCESSOR, etc.), and a storage space (eg, memory, etc.) for storing gain processing data including at least one gain reference data corresponding to the ambient noise environment.

The data processor 9 processes the first electrical signal in units of a reference frame having a preset size, and performs at least Fast Fourier Transform (FFT) to convert the first electrical signal, which is a signal in the time domain, into a signal in the frequency domain. Convert to In addition, the data processor 9 calculates the frequency axis energy of the first electric signal from the signal in the frequency domain of the first electric signal, and calculates the signal-to-noise ratio (SNR) reflecting the surrounding noise environment using the calculated frequency axis energy. Calculate. The process of calculating the frequency axis energy from the signal in the frequency domain and the process of calculating the signal-to-noise ratio (SNR) using the frequency axis energy are techniques that are well known to those of ordinary skill in the art to which the present invention belongs. Corresponds to, and its description is omitted. In addition, the data processor 9 converts the first electrical signal, which is a signal in the frequency domain, into a first electrical signal, which is a signal in the time domain, by performing an Inverse Fast Fourier Transform (IFFT).

In addition, the data processor 9 calculates the frequency axis energy of the first electrical signal every frame or at predetermined time intervals (e.g., 5 seconds, 10 seconds), and uses the calculated frequency axis energy. Calculate the noise-to-noise ratio (SNR).

The gain reference data stored by the data processor 9 will be described. The gain reference data is data for determining each of a first gain ratio and a second gain ratio for each of the first and second electric signals based on the signal-to-noise ratio (SNR) of the first electric signal. Here, the first gain ratio and the second gain ratio fall in the range of 0 to 1, and the sum of the first and second gain ratios is 1 (reference ratio), which is always the same value. For example, if the first gain ratio is 0, the second gain ratio is 1, and if the first gain ratio is 0.3, the second gain ratio is 0.7.

2A and 2B are examples showing characteristics of gain-based data. The upper side of the gain reference curves S1 and S2 is the area of the first gain ratio T1, and the lower side of the gain reference curves S1 and S2 is the area of the second gain ratio T2. The gain reference curve (S1) is linear with a characteristic that increases in direct proportion to the first gain ratio (T1) as the signal-to-noise ratio (SNR) increases, and the gain reference curve (S2) increases the signal-to-noise ratio (SNR). The first gain ratio T1 is nonlinear with an increasing characteristic.

In Fig. 2A, when the signal-to-noise ratio (SNR) is E1, the first gain ratio (T1) is the ratio (T1-1) and the second gain ratio (T2) is determined as the ratio (T2-1). When the signal-to-noise ratio (SNR) is E2, the first gain ratio T1 is the ratio T1-2 and the second gain ratio T2 is the ratio T2-2. As the signal-to-noise ratio (SNR) increases, the first gain ratio (T1) increases and the second gain ratio (T2) decreases. As the signal-to-noise ratio (SNR) decreases, the first gain ratio (T1) decreases. And the second gain ratio T2 increases. That is, the data processor 9 determines the first and second gain ratios from one gain reference data included in the gain-processed data using the signal-to-noise ratio (SNR) of the first electrical signal.

Further, the data processor 9 calculates a gain-processed first electrical signal by multiplying the determined first gain ratio and the first electrical signal, and multiplies the determined second gain ratio by the second electrical signal to obtain a gain-processed second electrical signal. After calculating, the gain-processed first electric signal and the gain-processed second electric signal are summed to generate an output signal. The data processor 9 transmits an output signal to the electronic device 30 through the communication unit 13.

(A) and (b) shown by way of example in FIG. 2 are gain ratios between the first and second electrical signals according to the signal-to-noise ratio (SNR), which is the characteristic of the gain-based data, It was determined depending on the ambient noise environment. That is, the gain reference data includes gain ratios between the first and second electrical signals according to the signal-to-noise ratio (SNR) so that the wearer's voice is more clearly transmitted or transmitted to the other party of the call in a specific ambient noise environment. Is composed. The ambient noise environment may be defined as various characteristics of the frequency axis energy of the first electric signal, such as that 80% or more of the frequency axis energy of the first electric signal is formed at 2 kHz or less. The data processor 9 stores a plurality of gain reference data corresponding to each of the ambient noise environments having different frequency axis energy characteristics.

Next, the wireless sound conversion device 20 has the same configuration as the wireless sound conversion device 10, and the input unit 21, the display unit 22, the communication unit 23, the first and second microphones 24a, 24b ), the speaker 25 and the data processor 29, respectively, the input unit 11, the display unit 12, the communication unit 13, the first and second microphones 14a, 14b, the speaker 15, and the data processor 19 ) It performs the same function as each.

However, only one of the wireless sound conversion device 10 and the wireless sound conversion device 20 may generate an output signal and apply it to the communication unit 13.

In addition, the wireless sound conversion device 10 and the wireless sound conversion device 20 may operate as a master device and a slave device in a communication relationship with each other.

Next, the electronic device 30 corresponds to an information communication device such as, for example, a smart phone or a tablet PC, and inputs from the wearer (eg, power on/off, selection of playback songs, An input unit 31 that acquires a selection, etc.) and applies it to the data processor 39, a display unit 32 that displays gain processing data, power status (e.g., charging, degree of charge, etc.), and wireless sound A communication unit 33 that performs wireless communication with the conversion device 10 and/or the wireless sound conversion device 20, and a microphone that applies an electrical signal of sound obtained by obtaining external sound to the data processor 39 ( 34), a speaker 35 for receiving an electrical signal from the data processor 39 to emit sound, and a wireless sound conversion device 10 and/or 20 by controlling the above-described components. While performing a sound reproduction function, a phone call function, etc. through wireless communication, an update process of the gain reference data and the gain processing data stored in the wireless acoustic conversion devices 10 and 20, and the gain reference data according to the surrounding noise environment It includes a data processor 39 that performs the determination process of. However, the power supply unit (not shown), the input unit 31, the display unit 32, the communication unit 33, the microphone 34, the speaker 35, and the like that supply power are generally knowledgeable in the technical field to which the present invention belongs. It corresponds to a skill that is only recognized by those who have it, and a detailed description thereof is omitted.

The data processor 39 controls the above-described components to perform a sound reproduction function, a phone call function, etc. through wireless communication with the wireless sound conversion device 10 and/or 20 (e.g., MCU, CPU, MICROPROCESSOR, etc.), and a storage space (eg, memory) for storing gain processing data including at least one gain reference data corresponding to the ambient noise environment.

First, an update process for the gain processing data will be described. The data processor 39 receives new gain-processed data including gain reference data according to a signal-to-noise ratio (SNR) from an external server (not shown) through the communication unit 33, and stores the received new gain-processed data. Save it. In addition, the data processor 39 transmits the new gain processing data stored in the communication connection state with the communication units 13 and 23 to the wireless acoustic conversion devices 10 and 20. Each of the data processors 19 and 29 receives and stores the new gain processing data through the communication units 13 and 23, respectively, and uses the stored gain processing data instead of the previously stored gain processing data.

Next, a process of determining the gain reference data according to the surrounding noise environment will be described. As described in FIG. 2, the data processor 39 stores gain reference data corresponding to the gain reference curve S of various types, and among the stored gain reference data, the frequency axis signal characteristic of the first electric signal is more Determine the gain reference data that is suitable, that is, more suitable for the ambient noise environment. For this determination, while the wireless acoustic conversion apparatuses 10 and 20 and the electronic device 30 can communicate with each other, the data processor 39 performs an application for determining the gain reference data, and the data processor 19 ) And (29) respectively perform a request for transmission of the first and second electrical signals. Accordingly, each of the data processors 19 and 29 transmits the first and second electrical signals including sound for a predetermined time (eg, 5 seconds) through the communication units 13 and 23 respectively. And, during a preset time, gain processing is performed according to the previously determined gain reference data, and the output signal is transmitted to the electronic device 30 through the communication units 13 and 23, respectively. The data processor 39 receives the first and second electrical signals through the communication unit 33, and determines gain reference data suitable for the frequency axis signal characteristic of the received first electrical signal. The data processor 39 transmits the determined gain reference data to the wireless acoustic conversion devices 10 and 20 through the communication unit 33. Each of the data processors 19 and 29 receives and stores the gain reference data through the communication units 13 and 23, and performs gain processing based on the most recently stored gain reference data.

In addition, in a state in which the wireless acoustic conversion apparatuses 10 and 20 and the electronic device 30 can communicate with each other, when the data processor 39 does not perform an application for determining the gain reference data, the data processor 19 ) And (29) each perform gain processing based on the most recently stored gain reference data.

Further, the data processor 39 may display gain reference data corresponding to the previously stored gain reference curve S on the display unit 32 and allow the wearer to select one of the displayed gain reference data. The data processor 39 transmits the selected gain reference data or identification data capable of distinguishing the selected gain reference data (eg, a unique number of the gain reference data) through the communication unit 33 to the wireless acoustic conversion device 10, Transfer to (20). Accordingly, each of the data processors 19 and 29 receives gain reference data or identification data through the communication units 13 and 23, and a pre-stored gain reference corresponding to the received gain reference data or the identification data. Performs gain processing according to data.

In particular, the data processor 39 may transmit the first electrical signal to a data server (not shown) to select or determine the learned gain reference data using artificial intelligence. The data server receives the first electrical signal, performs a fast Fourier transform (FFT) on the first electrical signal in units of a reference frame, and converts the first electrical signal, which is a time domain signal, into a frequency domain signal. Perform. Next, the data server extracts sound feature data by performing MFCC (Mel Frequency Cepstral Coefficient) on the signal in the frequency domain. Next, the data server has an artificial neural network composed of an input layer that receives the extracted feature data, a hidden layer that receives feature data from the input layer and extracts a feature, and an output layer that outputs the feature extracted from the hidden layer. Has hidden layers corresponding to the number of gain reference data. In addition, the data server calculates a hypothesis, which is the output of the Sigmoid function, which takes as input the sum of the product of features and weights extracted from each hidden layer and the bias, and inputs the hypothesis. It calculates the cost, which is the output of the cost function, and calculates the optimizer, which is the output of the gradient function that takes the calculated cost as an input. The data server determines an optimizer that is the closest or closest to the extracted feature data among the calculated optimizers, and determines a hidden layer corresponding to the determined optimizer and gain reference data corresponding to the corresponding hidden layer. The data server determines gain reference data most suitable for the feature data through the above process and transmits the determined gain reference data to the electronic device 30.

The electronic device 30 receives the gain reference data and transmits the received gain reference data to each of the wireless acoustic conversion devices 10 and 20 through the communication unit 33. Accordingly, the wireless acoustic conversion apparatuses 10 and 20 receive and store the gain reference data, process the first and second electrical signals according to the stored gain reference data, generate an output signal, and transmit it to the electronic device 30. .

In the process of determining the gain reference data described above, the process of determining by the electronic device 30 is described, but each of the data processors 19 and 29 selects gain reference data suitable for the surrounding noise environment from among a plurality of gain reference data. You can decide. That is, the data processors 19 and 29 calculate the frequency axis energy of the first electric signal and determine gain reference data suitable for the characteristics of the calculated frequency axis energy. In particular, the data processors 19 and 29 may select or determine the learned gain reference data using the aforementioned artificial intelligence. In addition, the data processors 19 and 29 may obtain selection inputs for gain reference data by the wearer from the input units 11 and 21, respectively, and perform gain processing according to the selected gain reference data.

At least a part of a device (eg, a processor or its functions) or a method (eg, operations) according to various embodiments is, for example, in a computer-readable storage media in the form of a program module. It can be implemented with stored instructions. When the command is executed by a processor, the one or more processors may perform a function corresponding to the command. The computer-readable storage medium may be, for example, a memory.

Computer-readable recording media include hard disks, floppy disks, magnetic media (e.g. magnetic tape), optical media (e.g. CD-ROM, DVD (Digital Versatile Disc), magnetic- It may include optical media (eg floptical disk), hardware devices (eg ROM, RAM, flash memory, etc.), etc. In addition, program instructions, such as those made by a compiler, may be included. It may include not only machine code but also high-level language code that can be executed by a computer using an interpreter, etc. The above-described hardware device may be configured to operate as one or more software modules to perform operations of various embodiments. The same goes for vice versa.

A processor or functions performed by the processor according to various embodiments of the present disclosure may include at least one or more of the above-described components, some of the above-described components may be omitted, or additional other components may be further included. Operations performed by a module, a program module, or other components according to various embodiments may be executed sequentially, in parallel, repeatedly, or in a heuristic manner. Also, some operations may be executed in a different order, omitted, or other operations may be added.

As described above, the present invention is not limited to the specific preferred embodiment described above, and anyone with ordinary knowledge in the technical field to which the present invention belongs without departing from the gist of the present invention claimed in the claims It goes without saying that modifications can be made, and such changes are within the scope of the claims.

10, 20: wireless sound conversion device 30: electronic device

Claims (6)

First and second microphones respectively obtaining sound and generating and applying first and second electrical signals;
A communication unit for performing wireless communication with an electronic device;
By performing wireless communication with the electronic device through the communication unit, the first and second electric signals are applied from the first and second microphones, and each of the first and second electric signals based on the signal-to-noise ratio of the first electric signal Determining the first and second gain ratios for, processing the first and second electrical signals according to the determined first and second gain ratios, and summing the processed first and second electrical signals to generate an output signal And a data processor for transmitting the generated output signal to the electronic device through the communication unit,
When the wireless acoustic conversion device is worn by the wearer, the first microphone is exposed to the outside of the wearer's hearing organ, and the second microphone is at least partially inserted into the wearer's hearing organ or blocked from the outside by the case of the wireless acoustic conversion device. Wireless sound conversion device, characterized in that mounted in the position. delete The method of claim 1,
The data processor stores at least one gain reference data corresponding to the ambient noise environment, and determines first and second gain ratios according to the signal-to-noise ratio of the first electrical signal from the stored gain reference data, the first and second gain reference data. The wireless sound conversion device, characterized in that the sum of the gain ratio is a reference ratio. The method of claim 3,
The data processor receives and stores the gain reference data from the electronic device through the communication unit. The method of claim 3,
The data processor determines gain reference data suitable for characteristics of a frequency axis signal of the first electric signal. A wireless sound conversion device according to claim 4;
In the acoustic communication system consisting of an electronic device and a data server for performing communication with a wireless acoustic conversion device,
The wireless sound conversion apparatus transmits the first and second electrical signals for a preset time to the electronic device,
The electronic device receives the first and second electrical signals, transmits the first and second electrical signals to the data server, the data server receives the first and second electrical signals, and frequency the received first electrical signals. The most suitable gain for the extracted feature data by performing axial transformation and extracting feature data by performing MFCC (Mel Frequency Cepstral Coefficient) on the frequency axis signal of the first electrical signal, and performing artificial neural network processing on the extracted feature data. Determine reference data, transmit the determined gain reference data to the electronic device,
The electronic device receives the determined gain reference data, and transmits the determined gain reference data to the wireless acoustic conversion device.

Images