JP7384397B2 - Audio leak prevention device and audio leak prevention program - Google Patents

Description

The present invention relates to an audio leakage prevention device and an audio leakage prevention program that generate disturbing sounds that prevent conversations in a room surrounded by partition walls such as partitions and walls from leaking outside from the partition walls.

2. Description of the Related Art There is a known technology that prevents the conversation from being heard by people around you by covering the conversation with an interfering sound called masking sound.
For example, Non-Patent Document 1 describes a basic explanation of masking sound and an explanation of generation of masking sound.

Further, Patent Document 1 describes a masking sound generation system. This masking sound generation system includes a masking sound data generation device that generates sound data indicating masking sounds (hereinafter referred to as "masking sound data"), and a masking sound data generation device that generates sound data indicating masking sounds (hereinafter referred to as "speaker sound data"), and a masking sound data generation device that collects the speaker's voice and generates sound data (hereinafter referred to as "speaker sound data"). A microphone is a sound collection device that generates sound data (hereinafter referred to as "source sound data"); a storage device that stores sound data (hereinafter referred to as "source sound data") representing sound used as a material to generate masking sound data; A speaker that is a sound emitting device that emits the sound indicated by the masking sound data generated by the masking sound data generation device as a masking sound into a space where there is a person (the person whose communication of the content of the speaker's voice is to be inhibited) is present. It is equipped with the following.

In addition, Patent Document 1 describes a modification of the masking sound generation system that includes a microphone that picks up the speaker's voice, as well as a microphone that picks up background noise in the space where the speaker is (or the space where the listener is). It is described that the technology includes a microphone that generates data (hereinafter referred to as "background noise data"), and adjusts the level of masking sound data for each frequency band according to the level of background noise for each frequency band.

“Ono Sokki - What is sound quality evaluation (page2)”, [online], May 8, 2018, Ono Sokki Co., Ltd., [searched on June 26, 2019], Internet <URL: https: //www.onosokki.co.jp/HP-WK/c_support/newreport/soundquality/soundquality_2.htm＞

Japanese Patent Application Publication No. 2015-187714

However, in the masking sound generation system described in Patent Document 1, if the microphone picks up not only the voice of the speaker to be masked but also the voices of surrounding speakers, the masking sound data generation device generates the masking sound. may not be effectively masked.
This is because the masking sound generation system described in Patent Document 1 is assumed to be installed in a place where a speaker and a listener are located in the same place.

For example, a large room in a company may be divided into several small rooms using partitions or other partition walls to form conference rooms, and others may be used as offices.
In such cases, thin partition walls may allow conversations in the conference room to leak into the office. At this time, if the masking sound generation system described in Patent Document 1 is installed in an office, the masking sound is generated mainly from the environmental sounds in the office, so the sound leaking from the conference room can be heard in the office as it is. There is a possibility that it will be stored away.

SUMMARY OF THE INVENTION Accordingly, an object of the present invention is to provide an audio leakage prevention device and an audio leakage prevention program that can generate disturbing sounds that accurately prevent conversations in a room surrounded by partition walls from leaking from the partition walls to the outside. shall be.

The audio leakage prevention device of the present invention uses indoor sound data collected by a first microphone installed in a first room and a second microphone installed in a second room adjacent to the first room by a partition wall. Based on the collected environmental sound data, generate interference sound data that prevents the conversation in the first room from leaking from the partition wall to the second room; Interfering sound is emitted from a speaker directed toward the second room, and based on the environmental sound data, characteristics of the environmental sound collected in the second room are extracted to generate an environmental sound profile. a profile generating means; a conversational sound extracting means for extracting a speaker's sound component representing a conversation in the first room by removing an environmental sound component from the indoor sound data based on the environmental sound profile; The present invention is characterized by comprising an interfering sound generating means for generating interfering sound data based on a speaker's voice component.

Furthermore, the audio leakage prevention program of the present invention collects indoor sound data collected by a first microphone installed in a first room, and a second microphone installed in a second room adjacent to the first room by a partition wall. Generate interfering sound data that prevents the conversation in the first room from leaking from the partition wall to the second room based on the environmental sound data collected by the microphone, and based on the interfering sound data The computer is operated to emit an interfering sound from a speaker directed toward the second room, and the computer is operated to emit environmental sound collected in the second room based on the environmental sound data. profile generating means for extracting the characteristics of and generating an environmental sound profile, and removing an environmental sound component from the indoor sound data based on the environmental sound profile, thereby generating the speaker's voice of the conversation in the first room. The present invention is characterized in that it functions as a conversational sound extracting means for extracting components, and as an interfering sound generating means for generating interfering sound data based on the speaker's audio components.

According to the present invention, first, features are extracted based on the environmental sound from the second microphone to generate an environmental sound profile. Next, the conversational sound extracting means extracts the speaker's sound component from the room sound data from the first microphone by removing the environmental sound component based on the environmental sound profile. Then, the interfering sound generation means generates interfering sound based on the speaker's voice component. Therefore, it is possible to eliminate or reduce the presence of environmental sounds in the speaker's voice component.

The disturbing sound generating means identifies the speaker in the first room by associating the speaker voice component with identification information of a terminal device carried by the speaker located in the first room, and generates the identification information. It is possible to generate interfering sound data according to the By associating the speaker's voice component with the identification information of the terminal device, the speaker in the first room can be specified, and therefore it is possible to associate the interfering sound according to the speaker (identification information). Therefore, it is possible to generate an interfering sound suitable for each speaker, and it is possible to generate more effective interfering sound data.

Consisting of one or more first devices to which the first microphone, the second microphone, and the speaker are connected, and a second device communicably connected to the first device via a telecommunications line,
The first device includes a first audio processing unit that converts indoor sound from the first microphone into the indoor sound data, and a second audio processing unit that converts the environmental sound from the first microphone into the environmental sound data. and an audio output control means for emitting an interfering sound from the speaker based on the interfering sound data, the second device comprising: the profile generating means, the conversation sound extracting means, and the interfering sound generating means. and means.

By configuring the audio leakage prevention device of the present invention by a first device and a second device connected to the first device by a telecommunications line, one second device can receive information from a plurality of first devices. It can process audio data.

The information processing apparatus may include a concealing means for thinning out the indoor sound data and the environmental sound data transmitted from the first device and transmitting the same to the second device.
The anonymization means thins out the room sound data and the environmental sound data and sends it to the second device, so even if the conversation in the first room or the conversation in the second room is sent to the telecommunications line, there is no possibility that malicious information will be detected. This prevents eavesdropping on voice data flowing through telecommunications lines and restoring conversations.

According to the audio leakage prevention device of the present invention, since it is possible to prevent a small amount of environmental sound from being mixed with the speaker's voice component or from being mixed, it is possible to emit an interfering sound that can interfere with the speaker's conversation with high accuracy. Therefore, it is possible to prevent the conversation in the first room from being overheard in the second room.

FIG. 1 is a diagram for explaining the configuration of an audio leakage prevention device according to the present embodiment. FIG. 2 is a block diagram for explaining the configuration of a control device that functions as a first device of the audio leakage prevention device shown in FIG. 1. FIG. FIG. 2 is a block diagram for explaining the configuration of a processing device that functions as a second device of the audio leakage prevention device shown in FIG. 1. FIG. 2 is a diagram for explaining the operation and usage state of the audio leakage prevention device shown in FIG. 1. FIG.

An audio leak prevention device according to an embodiment of the present invention will be described based on the drawings. First, the overall configuration will be explained based on FIG. 1.
As shown in FIG. 1, the audio leakage prevention device includes a control device 10, which is a first device, and a processing device 20, which is a second device.
The control device 10 is a computer that functions as a local device installed at company C.
The processing device 20 is a computer functioning as a cloud device that is communicably connected to the control device 10 via the Internet N, which is an example of a telecommunications line.

In this embodiment, one control device 10 is connected to the processing device 20, but the processing device 20 may be connected to respective control devices 10 installed in a plurality of companies. In this case, when the control device 10 transmits data to the processing device 20, the processing device 20 can identify the company C (control device 10) by also transmitting identification information that identifies the company. It is possible.

Company C has a first room and a second room, which are adjacent to each other by a partition wall between the first and second rooms. In this embodiment, a conference room C1, which is a first room, is formed by surrounding a part of a large room of a company C with a partition wall W such as a partition or a wall. By making a part of the large room of company C a small meeting room C1, the room other than the meeting room C1 becomes an office C2, which is a second room where employees work.

In this embodiment, the control device 10 is installed in the office C2, which is the second room, but may be installed in the conference room C1, which is the first room.

A first microphone M1, a second microphone M2, and a speaker S are connected to the control device 10.
The first microphone M1 is installed in the conference room C1. The first microphone M1 collects the speaker's voice. The second microphone M2 is installed inside the office C2 outside the conference room C1. The second microphone M2 collects environmental sounds that are sounds inside the office C2. Furthermore, the speaker S is installed facing the office C2. The speaker S generates and emits an interfering sound.

An employee (operator) located in the office C2 can have a smartphone P (terminal device) for adjusting the volume of sound emitted from the speaker S.
Further, a wireless router device R that transmits and receives wireless signals to and from the smartphone P is connected to the control device 10.
Furthermore, the wireless router device R has a function as a hub, and is connected to the Internet N via a relay device (not shown).

Next, the configuration of the control device 10 will be described based on FIG. 2.
As shown in FIG. 2, the control device 10 includes a communication means 11, a first audio processing means 12, a second audio processing means 13, an anonymization means 14, an audio output control means 15, and a storage means 16. It is equipped with

The communication means 11 receives information from the Internet N via the wireless router device R or via a wireless communication network provided by a mobile phone company, and outputs the information to each means of the control device 10 or receives information from each means. Information is input and transmitted to the wireless router device R or the wireless communication network.
When the communication means 11 connects to the Internet N via the wireless router device R, a LAN such as 1000Base-T can be used. Furthermore, when the communication means 11 communicates with a wireless communication network, it can be 3G to 5G, LTE, etc.
The communication means 11 can have BLUETOOTH (registered trademark) or other short-range wireless communication function, and can directly communicate with the smartphone P by this function.
At this time, this wireless communication function can also have directivity toward the conference room C1 side. The communication means 11 is a smartphone P carried by an employee who is in close range (in a conference room), acquires communication log information with the smartphone P that is uniquely identified by identification information, and stores it in the storage means 16. be able to.
The first audio processing means 12 collects the voices of speakers in the conference room C1 shown in FIG. A certain sound collection signal is AD converted into room sound data which is a digital signal and stored in the storage means 16.
The second audio processing means 13 converts an environmental sound signal, which is an analog signal, into which the second microphone M2 collects the voice of the speaker in the office C2, noise from the office C2, and external noise, into environmental sound data, which is a digital signal. The data is AD converted and stored in the storage means 16.

The concealing means 14 reads the room sound data and the environmental sound data from the storage means 16 , performs a concealing process to thin out these audio data, and transmits the data to the processing device 20 via the communication means 11 .
The audio output control means 15 generates a disturbance sound which is an analog signal from the disturbance sound data from the processing device 20 and emits the sound from the speaker S. The audio output control means 15 also adjusts the volume from the speaker S based on a volume instruction from the smartphone P.
The storage unit 16 includes an OS (operating system), application software, various settings, audio data (indoor sound data, environmental sound data, interference sound data), and identification information for identifying the speaker who owns the smartphone P. Communication log information etc. are stored. The storage means 16 can be a hard disk drive or an SSD (solid state drive) using flash memory.

Next, the configuration of the processing device 20 will be described based on FIG. 3.
The processing device 20 includes a communication means 21 , a profile generation means 22 , a conversational sound extraction means 23 , an interfering sound generation means 24 , and a storage means 25 .
The communication means 21 receives information from the Internet N and outputs it to each means of the processing device 20, or inputs information from each means and transmits it to the Internet N. The communication means 21 can be a LAN.

The profile generation means 22 extracts features of the environmental sound based on the environmental sound data from the control device 10, generates an environmental sound profile, and stores it in the storage means 25.
Further, the profile generating means 22 can update and store an environmental sound profile by machine learning, using the frequency component of the environmental sound as frequency element data and the sound collection time as time element data, using machine learning for environmental sounds that change over time.
Furthermore, when the profile generation means 22 updates and stores the environmental sound profile by machine learning, the machine learns the recording time of the environmental sound data and the identification information included in the communication log information with the smartphone P at the same time. This can be used to identify employee voices included in environmental sounds.

The conversational sound extraction means 23 extracts the speaker's sound component from the indoor sound data from the control device 10 based on the environmental sound profile and stores it in the storage means 25 by removing the environmental sound component.
The interfering sound generating means 24 generates interfering sound data to be an interfering sound (masking sound) based on the speaker's voice component, and transmits it to the control device 10 via the communication means 21.
Similar to the storage unit 16 of the control device 10, the storage unit 25 stores the OS, application software, various settings, audio data (indoor sound data, environmental sound data, disturbance sound data), and communication between the smartphone P and the control device 10. Log information etc. are stored.

The smartphone P runs application software that communicates with the control device 10 and adjusts the volume of the interfering sound.
The smartphone P can directly communicate with the control device 10 via the wireless router device R using WiFi (registered trademark), or by BLUETOOTH or other short-range wireless communication. Furthermore, as shown in FIG. 1, the smartphone P can communicate with the control device 10 through the Internet N via a communication base T such as a base station or relay station of a mobile phone company.

The operation and usage state of the audio leak prevention device (control device 10, processing device 20) according to the embodiment of the present invention configured as described above will be explained based on the drawings.
First, the second microphone M2 shown in FIG. 4 collects the voice of the speaker in the office C2 and the noise in the office C2 as environmental sounds (see S10). In the control device 10 shown in FIG. 2, the second audio processing means 13 converts environmental sound into environmental sound data and stores it in the storage means 16.
Next, the concealing means 14 reads out the environmental sound data from the storage means 16, thins it out at predetermined time intervals, and transmits it to the processing device 20 (see S20). For example, by repeating the process of extracting a few seconds worth of environmental sound data, leaving a few seconds in between, extracting another few seconds worth of data, and concatenating them, it is possible to obtain concealed environmental sound data.

In the processing device 20, when the profile generation means 22 receives the environmental sound data from the control device 10 via the communication means 21, it extracts the characteristics of frequency components in the environmental sound by frequency-analyzing the environmental sound data. Generate as an environmental sound profile. This feature can be a frequency distribution, volume, occurrence pattern, etc.

The environmental sound profile manages various noises such as mechanical sounds, conversations, external sounds, etc. that occur in the office C2 and change over time as environmental sounds.
The second audio processing means 13 of the control device 10 continuously transmits the environmental sound data to the processing device 20, so that the profile generation means 22 of the processing device 20 stores the environmental sound profile in the storage device 25. (See S30).

Once the environmental sound profile is in place, it can be put into operation.
When a conference is held in the conference room C1 shown in FIG. The sound is collected as room sound (see S40).

In the control device 10 shown in FIG. 2, the first audio processing means 12 converts indoor sound into room sound data and stores it in the storage means 16.
Next, the concealing means 14 reads the room sound data from the storage means 16, thins it out at predetermined intervals, and transmits it to the processing device 20 (see S50). For example, just like with environmental sound data, you can extract a few seconds of room sound data from the room sound data, leave a few seconds in between, and then repeat the process of extracting a few seconds of data and concatenating it. It can be data.
At this time, the anonymizing means 14 also transmits the identification information of the smartphone P stored in the storage means 16 to the processing device 20 via the communication means 11.

The room sound data is a synthesis of speaker voice components by participants in the conference and environmental sound components from the office C2 leaking into the conference room C1. Therefore, in the processing device 20, the conversation sound extraction means 23 performs frequency analysis based on the indoor sound data, extracts environmental sound components from the indoor sound data based on the characteristics of the frequency components in the environmental sound profile, and extracts environmental sound components from the indoor sound data. By removing the environmental sound component from the sound data, the speaker's voice component is extracted and stored in the storage means 25 (see S60).

Next, the interfering sound generation means 24 reads out the speaker's voice component from the storage means 16, and generates interfering sound data to be an interfering sound based on the speaker's voice component. The interfering sound can be generated, for example, according to the theory described in Non-Patent Document 1. At this time, as reference data when generating the disturbance sound data, the disturbance sound generation means 24 refers to the identification information of the smartphone P carried by the speaker located in the conference room C1. By doing so, it is possible to identify the speaker in the conference room C1 by associating the speaker's voice component with the identification information, and therefore it is possible to associate the interfering sound according to the speaker (identification information). Therefore, it is possible to generate an interfering sound suitable for each speaker, and it is possible to generate more effective interfering sound data.
The interfering sound generation means 24 transmits interfering sound data to the control device 10 (see S70).

In the control device 10, the audio output control means 15 generates a disturbance sound from the disturbance sound data from the processing device 20, and emits the sound from the speaker S (see S80).
At this time, if the employee carrying the smartphone P starts the volume adjustment application software running on the smartphone P and adjusts the volume, the specified volume will be controlled via the wireless router device R. transmitted to the device 10.
In the control device 10, based on the volume received via the communication means 11, the audio output control means 15 adjusts the interfering sound to the instructed volume.

As described above, according to the audio leakage prevention device using the control device 10 and the processing device 20 according to the embodiment of the present invention, first, features are extracted based on the environmental sound from the second microphone M2, and the environmental sound profile is generate. Next, the conversational sound extraction means 23 extracts the speaker's voice component from the room sound data from the first microphone M1 by removing the environmental sound component based on the environmental sound profile. Then, the interfering sound generation means 24 generates an interfering sound based on the speaker's voice component. Therefore, since there is little or no environmental sound mixed in the speaker's voice component, the audio leakage prevention device according to the present embodiment can emit an interfering sound that can interfere with the speaker's conversation with high accuracy. Therefore, it is possible to prevent the conversation in the conference room C1 from being overheard in the office C2.

In addition, the audio leakage prevention device is configured by a control device 10 installed in company C, and a processing device 20 connected to the control device 10 via the Internet N, so that one processing device 20 can control multiple devices. Audio data from device 10 can be processed.

In the processing device 20, the profile generation means 22 handles environmental sound data, and the conversation sound extraction means 23 handles indoor sound data, but the content of the conversation is not necessary, only a part of the conversation is required, and the frequency components can be analyzed. I wish I could.
Therefore, since the anonymization means 14 of the control device 10 thins out the audio data and sends it to the processing device 20, even if the conversation in the conference room C1 or the conversation in the office C2 is sent to the Internet N, the audio data can be It is possible to prevent eavesdropping and recovery of conversations.

Note that in this embodiment, the audio leakage prevention device is composed of two devices, the control device 10 and the processing device 20.
However, the first audio processing means 12, the second audio processing means 13, the anonymization means 14, the audio output control means 15, and the storage means 16 included in the control device 10 and the profile generation means 22 included in the processing device 20 , the conversational sound extraction means 23, the interfering sound generation means 24, and the storage means 25 are housed in the same device, so that the control device 10 and the processing device 20 can be configured into one device.

The audio leakage prevention device and audio leakage prevention program of the present invention are suitable for companies and various facilities where a room (first room) is surrounded by partition walls such as partitions and walls.

10 Control device 11 Communication means 12 First audio processing means 13 Second audio processing means 14 Anonymization means 15 Audio output control means 16 Storage means 20 Processing device 21 Communication means 22 Profile generation means 23 Conversation sound extraction means 24 Disturbing sound generation means 25 Storage means C Company C1 Conference room C2 Office M1 First microphone M2 Second microphone S Speaker W Partition wall P Smartphone R Wireless router device N Internet T Communication base

Claims (4)

Indoor sound data collected by a first microphone installed in the first room, and environmental sound data collected by a second microphone installed in a second room adjacent to the first room by a partition wall. based on the interference sound data that prevents the conversation in the first room from leaking from the partition wall to the second room, and generates interference from a speaker directed toward the second room based on the interference sound data. It emits sound,
Profile generation means for extracting characteristics of environmental sounds collected in the second room based on the environmental sound data and generating an environmental sound profile;
Conversation sound extraction means for extracting a speaker voice component representing a conversation in the first room by removing an environmental sound component from the room sound data based on the environmental sound profile;
and disturbing sound generation means for generating disturbing sound data based on the speaker's voice component ,
The disturbing sound generating means identifies the speaker in the first room by associating the speaker voice component with identification information of a terminal device carried by the speaker located in the first room, and generates the identification information. An audio leakage prevention device that generates interfering sound data according to the Consisting of one or more first devices to which the first microphone, the second microphone, and the speaker are connected, and a second device communicably connected to the first device via a telecommunications line,
The first device includes a first audio processing unit that converts indoor sound from the first microphone into the indoor sound data, and a second audio processing unit that converts the environmental sound from the first microphone into the environmental sound data. and an audio output control means for emitting interfering sound from the speaker based on the interfering sound data,
2. The audio leakage prevention device according to claim 1 , wherein the second device includes the profile generating means, the conversational sound extracting means, and the interfering sound generating means. 3. The audio leakage prevention device according to claim 2 , further comprising a concealing means for thinning out the indoor sound data and the environmental sound data transmitted from the first device and transmitting the thinned data to the second device. Indoor sound data collected by a first microphone installed in the first room, and environmental sound data collected by a second microphone installed in a second room adjacent to the first room by a partition wall. based on the interference sound data that prevents the conversation in the first room from leaking from the partition wall to the second room, and generates interference from a speaker directed toward the second room based on the interference sound data. It is an audio leak prevention program that makes the computer function to emit sound.
The computer,
profile generating means for extracting characteristics of the environmental sound collected in the second room based on the environmental sound data and generating an environmental sound profile;
Conversation sound extraction means for extracting a speaker voice component representing a conversation in the first room by removing an environmental sound component from the room sound data based on the environmental sound profile;
Interfering sound generation means for generating interfering sound data based on the speaker's voice component, and associating the speaker's voice component with identification information of a terminal device carried by the speaker located in the first room; An audio leakage prevention program that functions as an interfering sound generation means that identifies a speaker in a first room and generates interfering sound data according to the identification information.

Images