WO2023148796A1

WO2023148796A1 - Information processing device, information processing method, information processing system, and computer-readable medium

Info

Publication number: WO2023148796A1
Application number: PCT/JP2022/003708
Authority: WO
Inventors: 善裕梶木
Original assignee: 日本電気株式会社
Priority date: 2022-02-01
Filing date: 2022-02-01
Publication date: 2023-08-10

Abstract

An information processing device (10) comprises: an acquisition means (11) for acquiring a first signal of a sound collected by a first sound collection device and a second signal of a sound collected by a second sound collection device; and a detection means (2) for detecting an abnormality on the basis of the first and second signals acquired by the acquisition means.

Description

Information processing device, information processing method, information processing system, and computer readable medium

The present disclosure relates to an information processing device, an information processing method, an information processing system, and a non-transitory computer-readable medium storing a program.

In recent years, crimes such as terrorism, assault, and molestation have been increasing in public places such as streets, stations, and trains. there is In order to compensate for this, an anomaly detection method has been devised in which security cameras, microphones, and the like are installed, and the obtained images and sounds are analyzed by a program to detect anomalies (for example, Patent Document 1).

In addition, in Patent Document 2, sound is collected with a plurality of microphones, and the position of the sound source is estimated from the arrival time difference of the sound from the sound source to each microphone, the sound pressure ratio due to the diffusion and attenuation of the sound, etc. (sound source stereotaxic) methods are disclosed.

JP 2013-131153 A Japanese Patent Publication No. 2013-545382

However, the techniques described in Patent Documents 1 and 2 have a problem that, for example, abnormal sounds may not be detected appropriately.

An object of the present disclosure is to provide an information processing device, an information processing method, an information processing system, and a non-temporary computer-readable medium storing a program that can appropriately detect abnormal sounds in view of the above-described problems. .

In a first aspect according to the present disclosure, an acquisition means for acquiring a second signal of sound collected by a first sound collecting device, the first signal and the second signal acquired by the acquisition means There is provided an information processing apparatus having detection means for detecting an abnormality based on the above.

Further, in a second aspect according to the present disclosure, a first signal of sound collected by the first sound collector and a second signal of sound collected by the second sound collector are obtained, An information processing method is provided for detecting an abnormality based on the obtained first signal and the second signal.

Further, a third aspect of the present disclosure includes a first sound collector, a second sound collector, and an information processing device, and the information processing device receives sound collected by the first sound collector. Acquisition means for acquiring a first signal of the sound collected by the second sound collecting device and a second signal of the sound collected by the second sound collecting device; An information processing system having detection means for detecting an abnormality is provided.

Further, in a fourth aspect according to the present disclosure, a first signal of sound collected by the first sound collector and a second signal of sound collected by the second sound collector are obtained, A non-transitory computer-readable medium storing a program for causing a computer to execute a process of detecting an abnormality based on the obtained first signal and the second signal is provided.

According to one aspect, abnormal sounds can be detected appropriately.

It is a figure which shows the structural example of the information processing apparatus which concerns on embodiment. 1 is a diagram illustrating a configuration example of an information processing system according to an embodiment; FIG. It is a figure which shows the hardware structural example of the information processing apparatus which concerns on embodiment. It is a sequence diagram showing an example of processing of the information processing system according to the embodiment. 4 is a flowchart showing an example of processing of the information processing device according to the embodiment;

The principles of the present disclosure will be explained with reference to several exemplary embodiments. It should be understood that these embodiments are described for illustrative purposes only, and do not imply any limitation on the scope of the disclosure, and are intended to assist those skilled in the art in understanding and practicing the present disclosure. The disclosure described herein can be implemented in various ways other than those described below.
In the following description and claims, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. have
Embodiments of the present disclosure will be described below with reference to the drawings.

(Embodiment 1)
<Configuration>
A configuration of an information processing apparatus 10 according to an embodiment will be described with reference to FIG. FIG. 1 is a diagram showing an example of the configuration of an information processing device 10 according to an embodiment. The information processing device 10 has an acquisition unit 11 and a detection unit 12 . Each of these units may be implemented by cooperation of one or more programs installed in the information processing device 10 and hardware such as the processor 101 and the memory 102 of the information processing device 10 .

The acquisition unit 11 acquires a first signal of sound collected by the first sound collector and a second signal of sound collected by the second sound collector. The detection unit 12 detects an abnormality based on the first signal and the second signal acquired by the acquisition unit 11 .

(Embodiment 2)
Next, the configuration of the information processing system 1 according to the embodiment will be described with reference to FIG.
<System configuration>
FIG. 2 is a diagram showing a configuration example of the information processing system 1 according to the embodiment. In the following, an example of detecting abnormal sounds such as shouts and screams at a station visited by an unspecified number of people and facilities such as commercial facilities will be described, but the technology of the present disclosure is not limited to this. The technology of the present disclosure can be applied to detect abnormal sounds in various places such as robots or factories where products move around.

In the example of FIG. 2, a plurality of microphones 20A to 20H (hereinafter referred to as , and when there is no need to distinguish between them, they are simply referred to as "microphones 20." An example of "sound collectors.") are arranged. Each microphone 20 may have not only a microphone that converts sound into an electrical signal (audio signal), but also a circuit or arithmetic device that analyzes the electrical signal of the sound in the same housing, or may be provided as a separate device. You may have it outside.

In the example of FIG. 2, the information processing device (parent device) 10 that collects sounds detected by the microphones 20 and determines whether or not they are abnormal sounds is also installed on the ceiling 202 . Each microphone 20 and the information processing apparatus 10 may be connected so as to be communicable by, for example, wireless communication. When the information processing apparatus 10 detects an abnormal sound, the information processing apparatus 10 may transmit a notification to that effect to a host system such as a center to notify the security guard and the user at the location (for example, the same floor) where the abnormality was detected. good.

<<Arrangement of each microphone 20>>
In the following, sound pressure will be used as an index representing the loudness of sound. Sound pressure attenuation can be calculated, for example, by the following equation (1). D1 is the distance from the sound source to the first point (m), D2 is the distance from the sound source to the second point, L1 is the noise level at the first point (dB), L2 is the noise level at the second point ( dB).
20×log ₁₀ (D2/D1) = L1-L2 (1)

Assuming that the sound source is point-like, the sound pressure measured at a distance of 5 meters from the sound source is attenuated to 1/25 of the sound pressure measured at a distance of 1 meter from the sound source, and at a distance of 20 meters from the sound source. The sound pressure measured at is attenuated to 1/400. When explained in terms of the sound pressure logarithmized sound level, the sound pressure measured at a distance of 5 meters from the sound source is reduced by 14 dB compared to the sound pressure measured at a distance of 1 meter from the sound source, and the sound pressure at a distance of 20 meters from the sound source is reduced by 14 dB. The sound pressure measured at is reduced by 26 dB.

In the technology of the present disclosure, the interval at which each microphone 20 is arranged (distance between adjacent microphones 20) is determined by the volume of an abnormal sound to be detected (for example, sound pressure) and the volume of background sound, and the microphones 20 can be installed. It may be determined based on conditions such as a position where the sound source can exist and a position where the sound source can exist. In this case, the first microphone 20 detects an abnormal sound that is greater than or equal to a first threshold value (for example, the loudness of a sound that is determined to be an abnormal sound) generated at a position corresponding to the second microphone 20, For example, it may be arranged at a position where the attenuation of the second signal compared with the first signal is less than a predetermined value) where the attenuation does not fall below the loudness of the sound that can be distinguished from the surrounding background sound. Note that the technology of the present disclosure only needs the information processing apparatus 10 to acquire information about the distance between the microphones 20, and thus can be applied to a case where the microphones 20 are installed in a movable robot or the like.

For example, assume that the sound pressure of the background sound at an arbitrary position is 60 to 70 decibels, the height from the floor surface 201 to the mouth of the person 50A is 1.5 meters, and the height from the floor surface 201 to the ceiling 202 is 3 meters. do. In this case, a case will be described in which a scream or scream emitted from the mouth of a person standing at an arbitrary position on the floor surface 201 at 100 decibels is detected as an abnormal sound.

When the human 50A stands directly under the microphone 20B (an example of the "second microphone 20"), the distance from the mouth of the human 50A to the microphone 20B is the shortest, and the distance is 1.5 meters. At this time, the distance from the adjacent microphone 20A (an example of the "first microphone 20") to the mouth of the human 50A is approximately 10.1 meters. Therefore, a cry or scream emitted from the human 50A at 100 decibels reaches the microphone 20A only attenuating to about 80 decibels. Therefore, the abnormal sound can be collected by the two

microphones

20B and 20A with a sound pressure higher than that of the background sound.

Similarly, the distance from the mouth of a person standing at an arbitrary position on the floor surface 201 to the second closest microphone 20 among the plurality of microphones 20 is approximately 10.1 meters or less. Therefore, a scream or scream emitted at 100 decibels reaches at least two microphones 20 with a minimum attenuation of about 80 decibels. That is, two or more microphones 20 are arranged in a range where a sound of 100 decibels is attenuated only up to 80 decibels. Therefore, the abnormal sound can be collected by at least two microphones 20 with a sound pressure higher than the sound pressure of the background sound.

<Hardware configuration>
FIG. 3 is a diagram showing a hardware configuration example of the information processing apparatus 10 according to the embodiment. In the example of FIG. 3, the information processing device 10 (computer 100) includes a processor 101, a memory 102, and a communication interface 103. FIG. These units may be connected by a bus or the like. Memory 102 stores at least a portion of program 104 . Communication interface 103 includes interfaces necessary for communication with other network elements.

When the program 104 is executed by cooperation of the processor 101 and the memory 102, etc., the computer 100 performs at least part of the processing of the embodiment of the present disclosure. Memory 102 may be of any type suitable for a local technology network. Memory 102 may be, as a non-limiting example, a non-transitory computer-readable storage medium. Also, memory 102 may be implemented using any suitable data storage technology, such as semiconductor-based memory devices, magnetic memory devices and systems, optical memory devices and systems, fixed and removable memory, and the like. Although only one memory 102 is shown in computer 100, there may be several physically different memory modules in computer 100. FIG. Processor 101 may be of any type. Processor 101 may include one or more of a general purpose computer, a special purpose computer, a microprocessor, a Digital Signal Processor (DSP), and a processor based on a multi-core processor architecture as non-limiting examples. Computer 100 may have multiple processors, such as application specific integrated circuit chips that are temporally dependent on a clock that synchronizes the main processor.

Embodiments of the present disclosure may be implemented in hardware or dedicated circuitry, software, logic, or any combination thereof. Some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software, which may be executed by a controller, microprocessor or other computing device.

The present disclosure also provides at least one computer program product tangibly stored on a non-transitory computer-readable storage medium. A computer program product comprises computer-executable instructions, such as those contained in program modules, to be executed on a device on a target real or virtual processor to perform the processes or methods of the present disclosure. Program modules include routines, programs, libraries, objects, classes, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The functionality of the program modules may be combined or split between program modules as desired in various embodiments. Machine-executable instructions for program modules may be executed within local or distributed devices. In a distributed device, program modules can be located in both local and remote storage media.

Program code for executing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes are provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus. When the program code is executed by the processor or controller, the functions/acts in the flowchart illustrations and/or implementing block diagrams are performed. Program code may run entirely on a machine, partly on a machine, as a stand-alone software package, partly on a machine, partly on a remote machine, or entirely on a remote machine or server. be.

Programs can be stored and supplied to computers using various types of non-transitory computer-readable media. Non-transitory computer-readable media include various types of tangible storage media. Examples of non-transitory computer-readable media include magnetic recording media, magneto-optical recording media, optical disc media, semiconductor memories, and the like. Magnetic recording media include, for example, flexible disks, magnetic tapes, hard disk drives, and the like. Magneto-optical recording media include, for example, magneto-optical disks. Optical disc media include, for example, Blu-ray discs, CD (Compact Disc)-ROM (Read Only Memory), CD-R (Recordable), CD-RW (ReWritable), and the like. The semiconductor memory includes, for example, mask ROM, PROM (Programmable ROM), EPROM (Erasable PROM), flash ROM, RAM (random access memory), and the like. The program may also be delivered to the computer by various types of transitory computer readable media. Examples of transitory computer-readable media include electrical signals, optical signals, and electromagnetic waves. Transitory computer-readable media can deliver the program to the computer via wired channels, such as wires and optical fibers, or wireless channels.

<Processing>
An example of processing of the information processing system 1 according to the embodiment will be described with reference to FIG. 4 . FIG. 4 is a sequence diagram showing an example of processing of the information processing system 1 according to the embodiment.

In step S<b>1 , each of the one or more microphones 20 transmits a signal of the collected sound to the information processing device 10 . Here, for example, the microphone 20 may transmit the signal of the collected sound to the information processing device 10 only when the volume of the collected sound is equal to or greater than a threshold.

Subsequently, the acquisition unit 11 of the information processing device 10 acquires (receives) the signal of the sound collected by each microphone 20 (step S2). Subsequently, the detection unit 12 of the information processing device 10 detects an abnormality based on the sound signals collected by the microphones 20 acquired by the acquisition unit 11 (step S3).

Subsequently, the detection unit 12 (output unit) of the information processing device 10 outputs information based on the detection result (step S4). Here, the detection unit 12, for example, transmits a message indicating that an abnormality has been detected to a host system such as a center, and sends a message from the center or the like to a security guard and a user at the location (for example, the same floor) where the abnormality is detected. etc. may be notified.

In step S3, the detection unit 12 may detect an abnormality by, for example, processing described below. Note that the detection unit 12 may execute the following processing examples in combination as appropriate.
<<Example of judging the same sound based on the arrival time of the sound>>
For example, the detection unit 12 may determine that an abnormality has occurred when a plurality of microphones 20 collect sounds having a volume equal to or larger than a threshold at substantially the same time (substantially at the same time). As a result, for example, it can be determined that an abnormality has occurred when a sound that is considered to be the same sound is collected by a plurality of microphones 20 with a loudness equal to or greater than the threshold.

In this case, for example, the detection unit 12 determines that the difference between the times at which sounds equal to or greater than the threshold are collected by the plurality of microphones 20 (for example, the time at which sound collection is started or the time at which sound collection is finished) is a specific time. If it is within (for example, 50 milliseconds), it may be determined that the sounds were collected substantially simultaneously.

Note that, for example, since the speed of sound in air at a temperature of 20 degrees Celsius is about 344 meters per second, if the distance between the microphones 20 is 10 meters, the maximum speed for the same sound to reach two adjacent microphones 20 is The time difference is approximately 30 milliseconds. Therefore, the specific time may be set to 50 milliseconds in the information processing apparatus 10 in consideration of the measurement error of the arrival time. Further, the detection unit 12 may determine the specific time based on, for example, the room temperature measured by the temperature sensor and the preset distance between the microphones 20 .

(Regarding the loudness of sound)
In the present disclosure, various indicators representing the volume of sound can be used as the volume of sound. The detection unit 12 inputs, for example, sound pressure (volume), power obtained by squaring sound pressure, time differential value of sound pressure, time integral value of sound pressure, and sound into an electric circuit as an index representing the loudness of sound. The strength of the audio signal, the loudness value obtained by correcting the sensitivity characteristic of hearing to the sound pressure, the noise level obtained by correcting the sensitivity characteristic of hearing and logarithmically, and the like may be used.

In addition, the detection unit 12 may use, for example, a physical quantity equivalent to the sound pressure of a specific frequency component after frequency-resolving the sound instead of the sound pressure of the entire sound wave as an index representing the loudness of the sound. In this case, the detection unit 12 may use, for example, the sound pressure of frequency components that are often included in the abnormal sound to be detected as an index representing the loudness of the sound.

In addition, the detection unit 12 may use, for example, a physical quantity that can be converted from sound pressure or the like by some calculation formula as an index representing the loudness of sound. In this case, the detection unit 12 uses, for example, a signal waveform corresponding to a change in sound pressure over time, a spectrum obtained by frequency-resolving the sound, and a spectrogram (also called a soundprint) that is a change in the spectrum over time as an index representing the loudness of the sound. ), pitch which means main frequency components, roughness which expresses the degree of modulation of sound pressure and pitch, cepstrum which is extracted spectrum envelope, and formants contained in human voice may be used.

<<Example of judging the same sound based on sound waveform>>
The detection unit 12 compares waveforms of sounds collected by each of the plurality of microphones 20 to determine whether or not they are signals of the same sound. It may be determined that an abnormality has occurred when the sound is collected at a large size. In this case, the detection unit 12 may determine that an abnormality has occurred when, for example, the waveforms are collated and the same sound is picked up by a plurality of microphones 20 with a loudness equal to or greater than the threshold. As a result, for example, it is possible to reduce erroneous detection that occurs when different sounds are accidentally input to a plurality of microphones 20 at the same time, and to improve the accuracy of abnormality detection.

Since the positions of the microphones 20 are far apart, the conditions such as reflection from the wall surface are greatly different, and it may be difficult to collate the voice signals as they are. Therefore, the detection unit 12 may, for example, frequency-decompose the sound signal from each microphone 20 and compare the time change of the frequency component. The detection unit 12 may perform verification using, for example, a correlation coefficient between one waveform and the other waveform, or a mean square error. In addition, for example, the detection unit 12 determines that the difference between the times at which sounds equal to or greater than the threshold are collected by the plurality of microphones 20 is within a specific time (for example, 50 milliseconds), and that each waveform is collated to obtain a plurality of If the same sound is picked up by the microphone 20 with a loudness equal to or greater than the threshold, it may be determined that an abnormality has occurred.　

<<Example of detecting anomalies by estimating the loudness of the sound source>>
The detection unit 12 may estimate the loudness of the sound from the sound source, and determine that an abnormality has occurred when the estimated loudness of the sound is equal to or greater than a threshold. As a result, for example, even in an environment where non-abnormal sounds close to the sound pressure of abnormal sounds are generated, the accuracy of abnormality detection can be improved.

An example of the processing of the information processing device 10 when an abnormality is detected by estimating the sound volume of the sound source in step S3 of FIG. 4 will be described with reference to FIG. FIG. 5 is a flowchart showing an example of processing of the information processing device 10 according to the embodiment.

In step S101, the detection unit 12 detects the difference between the time of sound collected by each microphone 20 and the loudness ratio of the sound collected by each microphone 20, based on at least one of them. Estimate distance.

Here, the detection unit 12 may select two or more microphones 20 in descending order of the volume of the collected sound. Then, the detection unit 12 may compare each waveform of the sound collected by each microphone 20 and calculate the difference between the times when the sound was collected by each microphone 20 . Then, the detection unit 12 may calculate the distance from the sound source to each microphone 20 based on the difference in time when the sound is collected by each microphone 20 .

Further, the detection unit 12 may calculate the distance from the sound source to each microphone 20 based on the volume of the sound collected by each microphone 20 using Equation (1) described above. In this case, theoretically, the sound source exists on a hyperboloid of revolution obtained by rotating the hyperbola with each position of the two microphones 20 as the focal point about the straight line connecting the microphones 20 as an axis. When the same sound is collected by three or more microphones 20, the detection unit 12 calculates a plurality of rotational hyperboloids for each combination of the two microphones 20, and determines the line of intersection of the calculated plurality of rotational hyperboloids. It may be assumed that there is a sound source above. Also, for example, if the abnormal sound is a shout or scream, it can be assumed that the sound source is located within a plane at a distance of about 1.5 meters from the floor, which is the height of the mouth. Therefore, the detection unit 12 may estimate the position of the sound source from the intersection of the intersection line and the plane. Also, when the same sound is collected only by two microphones 20, the position of the sound source becomes indefinite on the hyperboloid of revolution in principle. Therefore, the detection unit 12 may estimate the shortest possible position as the position of the sound source by using the constraint conditions of the sound source position in the actual site.

Subsequently, the detection unit 12 estimates the loudness of the sound source (step S102). Here, based on the distance from the sound source to the microphone 20 and the volume of the sound collected by the microphone 20, the detection unit 12 calculates the volume of the sound at the sound source using the above equation (1). can be estimated.

For example, if the distance from the sound source to the microphone 20 is 20 meters and the sound reaches the microphone 20 at 96 decibels, using the above equation (1), the sound pressure at a position of 1 meter from the sound source is 120 decibels. can be calculated backwards. From this, it can be estimated that the sound is not a sneeze or the like but an abnormal sound accompanying a burst or an explosion.

Subsequently, the detection unit 12 determines whether or not the volume of the sound from the estimated sound source is equal to or greater than the threshold (step S103). If the volume of the sound from the estimated sound source is greater than or equal to the threshold (YES in step S103), the detection unit 12 detects an abnormality (determines that the sound is abnormal) (step S104), and terminates the process. On the other hand, if the volume of the sound from the estimated sound source is equal to or greater than the threshold (NO in step S103), the detection unit 12 determines that the sound is not abnormal (step S105), and terminates the process.

<Others>
In general, when a failure occurs in an industrial machine, abnormal noise that is clearly different from normal noise is often generated. Using this principle, for the purpose of automatic detection of failures in industrial machinery operating in an unmanned environment, a method of collecting sound with a microphone and detecting anomalies from characteristics such as sound pressure and frequency of the collected sound. can be considered.

In addition to detecting the occurrence of anomalies, it is also possible to install multiple microphones around the monitored object and estimate the location of the anomaly. The sound pressure of sound emitted from a point-like sound source is attenuated in inverse proportion to the square of the distance from the sound source. It reaches the distant microphone with a low sound pressure attenuated. Therefore, it can be estimated that an abnormality has occurred in the vicinity of the microphone that detected the abnormal sound with the highest sound pressure.

In addition, when people encounter danger, they often emit abnormal sounds that are clearly different from normal times, such as screams, screams, gunshots, and explosions. security) purposes.

However, if the position of the sound source is indeterminate due to the movement of people or objects to be monitored, for example, in stations, commercial facilities, etc., the distance from the pre-arranged microphone to the sound source will be indeterminate. Since the sound pressure attenuates in inverse proportion to the square of the distance from the sound source, it is difficult to determine whether the sound is abnormal from the sound pressure of the sound collected by the microphone. For example, if we compare the case where something explodes far from the microphone and the case where someone sneezes near the microphone, in both cases, relatively high (e.g., similar) sound pressure is picked up. Therefore, in the method of detecting abnormality based on sound pressure, it becomes impossible to determine whether the sound is abnormal.

Specifically, plosive sounds generally have a sound pressure of about 120 decibels near the sound source, but attenuate to about 100 decibels when the distance is 10 meters. On the other hand, since a sneeze emitted near the microphone may have a sound pressure of about 100 decibels, it is impossible to distinguish between a plosive sound and a sneeze from the sound pressure reaching the microphone.

In addition, background sounds of about 60 to 80 decibels are always generated in stations and commercial facilities. There is a restriction that the abnormal sound cannot be distinguished from the background sound unless the microphone is placed at a distance where the sound reaches a level of about 90 to 100 decibels, which is sufficiently higher than the background sound.

With the technology of the present disclosure, multiple microphones are arranged, and abnormal sound is detected based on the volume of sound reaching the multiple microphones. As a result, for example, even when the distance from the microphone to the sound source is indefinite, it is possible to distinguish normal sounds and abnormal sounds emitted in the vicinity of the microphone. Therefore, an abnormal sound can be appropriately detected.

<Modification>
The information processing device 10 may be implemented by cloud computing, which is configured by one or more computers, for example. Further, the information processing device 10 and the microphone 20 may be configured as an integrated device. Further, at least part of the processing of the microphone 20 may be configured to be executed by the information processing device 10 . Further, at least part of the processing of the information processing device 10 may be configured to be executed by the microphone 20 .

It should be noted that the present invention is not limited to the above embodiments, and can be modified as appropriate without departing from the scope of the invention.

Some or all of the above-described embodiments can also be described in the following supplementary remarks, but are not limited to the following.
(Appendix 1)
Acquisition means for acquiring a first signal of sound collected by the first sound collector and a second signal of sound collected by the second sound collector;
detection means for detecting an abnormality based on the first signal and the second signal acquired by the acquisition means;
Information processing device having
(Appendix 2)
The first sound collecting device is arranged at a position where the attenuation of the second signal is less than a predetermined value.
The information processing device according to appendix 1.
(Appendix 3)
The detection means determines that an abnormality has been detected when the first signal and the second signal are equal to or greater than a threshold;
The information processing device according to appendix 1 or 2.
(Appendix 4)
The detection means determines whether the sound signals are emitted from the same sound source based on the first signal and the second signal, and determines that the sound signals are emitted from the same sound source. If so, it is determined that an abnormality is detected.
The information processing device according to appendix 3.
(Appendix 5)
When the second signal is collected within a specific time after the first signal is collected, the detection means detects that the first signal and the second signal are sound emitted from the same sound source. determine that it is a signal,
The information processing device according to appendix 4.
(Appendix 6)
When the waveform of the first signal and the waveform of the second signal have a predetermined relationship, the detection means detects that the first signal and the second signal are sound signals emitted from the same sound source. The information processing apparatus according to appendix 4 or 5, which determines that
(Appendix 7)
The detection means detects the difference between the time of sound collected by the first sound collector and the time of sound collected by the second sound collector, and the magnitude of sound collected by the first sound collector and the 2 Estimate the sound volume at the sound source based on at least one of the ratio of the sound volume to the sound collected by the sound collector, and when the estimated sound volume at the sound source is equal to or greater than a threshold , determine that an abnormality has occurred,
7. The information processing device according to any one of appendices 1 to 6.
(Appendix 8)
Acquiring a first signal of sound collected by the first sound collector and a second signal of sound collected by the second sound collector;
Detecting an abnormality based on the acquired first signal and the second signal;
Information processing methods.
(Appendix 9)
The first sound collecting device is arranged at a position where the attenuation of the second signal is less than a predetermined value.
The information processing method according to appendix 8.
(Appendix 10)
In the detecting process, when the first signal and the second signal are equal to or greater than a threshold value, it is determined that an abnormality is detected;
The information processing method according to appendix 8 or 9.
(Appendix 11)
In the detecting process, based on the first signal and the second signal, it is determined whether the sound signals are emitted from the same sound source, and the sound signals are detected as being emitted from the same sound source. If it is determined, it is determined that an abnormality has been detected,
The information processing method according to appendix 10.
(Appendix 12)
In the detecting process, when the second signal is collected within a specific time after the first signal is collected, the first signal and the second signal are sounds emitted from the same sound source. determined to be the signal of
The information processing method according to appendix 11.
(Appendix 13)
In the detecting process, when the waveform of the first signal and the waveform of the second signal have a predetermined relationship, the first signal and the second signal are sound signals emitted from the same sound source. 13. The information processing method according to

appendix

11 or 12, in which it is determined that there is
(Appendix 14)
In the detection process, the difference between the time collected by the first sound collecting device and the time collected by the second sound collecting device, and the magnitude of sound collected by the first sound collecting device and the When the loudness of the sound at the sound source is estimated based on at least one of the ratio to the loudness of the sound collected by the second sound collector, and the estimated loudness of the sound at the sound source is equal to or greater than a threshold to determine that an abnormality has occurred,
14. The information processing method according to any one of Appendices 8 to 13.
(Appendix 15)
Having a first sound collecting device, a second sound collecting device, and an information processing device,
The information processing device is
Acquisition means for acquiring a first signal of sound collected by the first sound collector and a second signal of sound collected by the second sound collector;
detection means for detecting an abnormality based on the first signal and the second signal acquired by the acquisition means;
An information processing system having
(Appendix 16)
The first sound collecting device is arranged at a position where the attenuation of the second signal is less than a predetermined value.
The information processing system according to appendix 15.
(Appendix 17)
The detection means determines that an abnormality has been detected when the first signal and the second signal are equal to or greater than a threshold;
The information processing system according to appendix 15 or 16.
(Appendix 18)
The detection means determines whether the sound signals are emitted from the same sound source based on the first signal and the second signal, and determines that the sound signals are emitted from the same sound source. If so, it is determined that an abnormality is detected.
17. The information processing system according to appendix 17.
(Appendix 19)
When the second signal is collected within a specific time after the first signal is collected, the detection means detects that the first signal and the second signal are sound emitted from the same sound source. determine that it is a signal,
18. The information processing system according to appendix 18.
(Appendix 20)
When the waveform of the first signal and the waveform of the second signal have a predetermined relationship, the detection means detects that the first signal and the second signal are sound signals emitted from the same sound source. The information processing system according to appendix 18 or 19, which determines that
(Appendix 21)
The detection means detects the difference between the time of sound collected by the first sound collector and the time of sound collected by the second sound collector, and the magnitude of sound collected by the first sound collector and the 2 Estimate the sound volume at the sound source based on at least one of the ratio of the sound volume to the sound collected by the sound collector, and when the estimated sound volume at the sound source is equal to or greater than a threshold , determine that an abnormality has occurred,
21. The information processing system according to any one of appendices 15 to 20.
(Appendix 22)
Acquiring a first signal of sound collected by the first sound collector and a second signal of sound collected by the second sound collector;
Detecting an abnormality based on the acquired first signal and the second signal;
A non-transitory computer-readable medium storing a program that causes a computer to execute a process.
(Appendix 23)
The first sound collecting device is arranged at a position where the attenuation of the second signal is less than a predetermined value.
23. The computer-readable medium of clause 22.
(Appendix 24)
In the detecting process, when the first signal and the second signal are equal to or greater than a threshold value, it is determined that an abnormality is detected;
24. The computer readable medium of clause 22 or 23.
(Appendix 25)
In the detecting process, based on the first signal and the second signal, it is determined whether the sound signals are emitted from the same sound source, and the sound signals are detected as being emitted from the same sound source. If it is determined, it is determined that an abnormality has been detected,
25. The computer-readable medium of clause 24.
(Appendix 26)
In the detecting process, when the second signal is collected within a specific time after the first signal is collected, the first signal and the second signal are sounds emitted from the same sound source. determined to be the signal of
26. The computer-readable medium of clause 25.
(Appendix 27)
In the detecting process, when the waveform of the first signal and the waveform of the second signal have a predetermined relationship, the first signal and the second signal are sound signals emitted from the same sound source. 27. The computer readable medium of Clause 25 or 26.
(Appendix 28)
In the detection process, the difference between the time collected by the first sound collector and the time collected by the second sound collector, and the magnitude of the sound collected by the first sound collector and the When the loudness of the sound at the sound source is estimated based on at least one of the ratio to the loudness of the sound collected by the second sound collector, and the estimated loudness of the sound at the sound source is equal to or greater than a threshold to determine that an abnormality has occurred,
28. The computer-readable medium of any one of clauses 22-27.

1 information processing system 10 information processing device 11 acquisition unit 12 detection unit 20 microphone

Claims

Acquisition means for acquiring a first signal of sound collected by the first sound collector and a second signal of sound collected by the second sound collector;
detection means for detecting an abnormality based on the first signal and the second signal acquired by the acquisition means;
Information processing device having
The first sound collecting device is arranged at a position where the attenuation of the second signal is less than a predetermined value.
The information processing device according to claim 1 .
The detection means determines that an abnormality has been detected when the first signal and the second signal are equal to or greater than a threshold;
The information processing apparatus according to claim 1 or 2.
The detection means determines whether the sound signals are emitted from the same sound source based on the first signal and the second signal, and determines that the sound signals are emitted from the same sound source. If so, it is determined that an abnormality is detected.
The information processing apparatus according to claim 3.
When the second signal is collected within a specific time after the first signal is collected, the detection means detects that the first signal and the second signal are sound emitted from the same sound source. determine that it is a signal,
The information processing apparatus according to claim 4.
When the waveform of the first signal and the waveform of the second signal have a predetermined relationship, the detection means detects that the first signal and the second signal are sound signals emitted from the same sound source. 6. The information processing apparatus according to claim 4 or 5, which determines that
The detection means detects the difference between the time of sound collected by the first sound collector and the time of sound collected by the second sound collector, and the magnitude of sound collected by the first sound collector and the 2 Estimate the sound volume at the sound source based on at least one of the ratio of the sound volume to the sound collected by the sound collector, and when the estimated sound volume at the sound source is equal to or greater than a threshold , determine that an abnormality has occurred,
The information processing apparatus according to any one of claims 1 to 6.
Acquiring a first signal of sound collected by the first sound collector and a second signal of sound collected by the second sound collector;
Detecting an abnormality based on the acquired first signal and the second signal;
Information processing methods.
Having a first sound collecting device, a second sound collecting device, and an information processing device,
The information processing device is
Acquisition means for acquiring a first signal of sound collected by the first sound collector and a second signal of sound collected by the second sound collector;
detection means for detecting an abnormality based on the first signal and the second signal acquired by the acquisition means;
An information processing system having
Acquiring a first signal of sound collected by the first sound collector and a second signal of sound collected by the second sound collector;
Detecting an abnormality based on the acquired first signal and the second signal;
A non-transitory computer-readable medium storing a program that causes a computer to execute a process.