Sound detection system and information processing device

Abstract

A sound detection system includes a plurality of microphones and an information processing device, wherein the plurality of microphones detect sounds inside a biological body and are capable of outputting sound signals based on the detected sounds. The information processing device includes an acquisition unit for acquiring sound signals from the plurality of microphones, a control unit, and an output unit. The control unit determines a first position as the position of a specified biological body part based on the sound signals acquired by the acquisition unit, estimates a second position that is in a specified relative positional relationship with the first position, controls the directivities of the plurality of microphones to increase sensitivity with respect to the second position, and outputs information based on the sound signals acquired by the acquisition unit when the directivities of the plurality of microphones are controlled to increase sensitivity with respect to the second position.

Description

Technical Field

[0001] The present invention relates to a sound detection system and an information processing device. Background Art

[0002] Conventionally, in order to diagnose the condition of a patient's heart, heart sounds are listened to using a stethoscope or the like.

[0003] Heart sounds include the I sound and the II sound. The I sound is heard when the mitral and tricuspid valves close. The II sound is heard when the pulmonary and aortic valves close.

[0004] For example, Patent Document 1 discloses a technique of detecting heart sounds using a plurality of sensors, selecting a specific sound such as a mitral valve closure sound from the detected heart sounds, and amplifying the selected specific sound.

[0005] Prior art literature

[0006] Patent Literature

[0007] Patent Document 1: Japanese Patent Application Publication No. 2019-10436 Summary of the Invention

[0008] Problems to be solved by the invention

[0009] If there is coronary artery stenosis, a stenotic murmur will occur immediately after the II sound. Detecting a coronary artery stenosis murmur is very useful in detecting signs of coronary artery disease such as angina pectoris and myocardial infarction.

[0010] However, the murmur of coronary artery stenosis is very weak and difficult to detect.

[0011] In view of the above-mentioned problems, an object of the present disclosure is to provide a sound detection system and an information processing device capable of improving detection sensitivity for weak sounds inside a living body.

[0012] Means for solving problems

[0013] A sound detection system in a first embodiment of the present invention includes: a plurality of microphones that detect sounds inside a biological body and can output sound signals based on the detected sounds; and an information processing device, the information processing device including an acquisition unit that acquires sound signals from the plurality of microphones, a control unit, and an output unit, the control unit determining a first position as the position of a specified biological body part based on the sound signal acquired by the acquisition unit, inferring a second position that is in a specified relative position relationship with the first position, controlling the directivity of the plurality of microphones to increase sensitivity with respect to the second position, and the output unit outputting information based on the sound signal acquired by the acquisition unit when the directivity of the plurality of microphones is controlled to increase sensitivity with respect to the second position.

[0014] In the sound detection system according to one embodiment of the present invention, the information processing device further includes a storage unit that stores information on the predetermined relative positional relationship between the first position and the second position.

[0015] In the sound detection system according to one embodiment of the present invention, the control unit determines the first position based on the amplitude and phase of the sound signal acquired from each microphone and the relative positions of the plurality of microphones for the sound originating from the predetermined body part.

[0016] In the sound detection system according to one embodiment of the present invention, the control unit controls the directivity of the plurality of microphones by adjusting and synthesizing the delay amount of the sound signal acquired from each microphone.

[0017] In the sound detection system according to one embodiment of the present invention, the control unit determines the intensity of the sound signal acquired from the second position, and causes the output unit to output an index based on the determination result.

[0018] In the sound detection system according to one embodiment of the present invention, the control unit controls the directivity of at least two microphones among the plurality of microphones so as to increase sensitivity at the second position.

[0019] In the sound detection system according to one embodiment of the present invention, when the first position is separated from the positions of the plurality of microphones by a predetermined distance or more, the control unit causes the output unit to output notification information recommending moving the positions of the plurality of microphones.

[0020] In the sound detection system of one embodiment of the present invention, relative positions of the plurality of microphones are fixed.

[0021] In a sound detection system according to one embodiment of the present invention, the relative positions of the plurality of microphones are variable. The sound detection system further includes a relative position measuring mechanism, which measures the relative positions of the plurality of microphones. The control unit calculates the relative positions of the plurality of microphones based on the relative positions of the plurality of microphones measured by the relative position measuring mechanism.

[0022] The sound detection system according to one embodiment of the present invention further includes an imaging device. In the sound detection system, relative positions of the plurality of microphones are variable, and the control unit calculates the relative positions of the plurality of microphones based on images of the plurality of microphones captured by the imaging device.

[0023] An information processing device according to a second embodiment of the present invention includes: a plurality of microphones that detect sounds inside a biological body and can output sound signals based on the detected sounds; an acquisition unit that acquires sound signals from the plurality of microphones; a control unit; and an output unit, wherein the control unit determines a first position as the position of a specified biological body part based on the sound signals acquired by the acquisition unit, infers a second position that is in a specified relative positional relationship with the first position, controls the directivities of the plurality of microphones to increase sensitivity with respect to the second position, and outputs information based on the sound signals acquired by the plurality of microphones when the directivities of the plurality of microphones are controlled to increase sensitivity with respect to the second position.

[0024] Effects of the Invention

[0025] According to the sound detection system and information processing device of the present invention, it is possible to improve the detection sensitivity for weak sounds inside a living body. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 This is a functional block diagram of the sound detection system according to the first embodiment of the present invention.

[0027] Figure 2 This diagram shows an example in which a plurality of microphones whose relative positions are fixed are installed near the human heart.

[0028] Figure 3A This is a diagram showing an example of an audio signal.

[0029] Figure 3B This is a diagram showing an example of an audio signal.

[0030] Figure 4 This is a diagram showing an example of estimating a second position based on a first position.

[0031] Figure 5A It is a diagram for explaining the effect of noise cancellation and the effect of directivity control of multiple microphones.

[0032] Figure 5B It is a diagram for explaining the effect of noise cancellation and the effect of directivity control of multiple microphones.

[0033] Figure 5C It is a diagram for explaining the effect of noise cancellation and the effect of directivity control of multiple microphones.

[0034] Figure 6 This is a flowchart showing an example of the operation of the sound detection system according to the first embodiment of the present invention.

[0035] Figure 7 This is a functional block diagram showing a sound detection system according to a second embodiment of the present invention.

[0036] Figure 8 This diagram shows an example in which a plurality of microphones whose relative positions are variable are installed near the human heart. DETAILED DESCRIPTION

[0037] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. In the drawings, common components are denoted by the same reference numerals.

[0038] (First embodiment)

[0039] Figure 1 This is a functional block diagram of the sound detection system 1 according to the first embodiment of the present invention. Figure 1 The configuration and outline of a sound detection system 1 according to a first embodiment of the present invention will be described.

[0040] The sound detection system 1 includes a sound detection device 10 , an information processing device 20 , and an external sound detection microphone 30 .

[0041] The sound detection device 10 is a device that can be attached to a living body, such as a human body, and detects sounds within the body. The sound detection device 10 outputs sound signals based on the detected sounds within the body to the information processing device 20. The sound detection device 10 can be connected to the information processing device 20 via a wired connection or wirelessly.

[0042] The sound detection device 10 includes a plurality of microphones 11-1 to 11-6 and a first coupling member 12. When there is no need to distinguish between the microphones 11-1 to 11-6, they may be simply referred to as the microphone 11 below. Figure 1 Although six microphones 11 - 1 to 11 - 6 are shown in FIG, the number of microphones 11 is not limited to 6. The number of microphones 11 may be any number of two or more.

[0043] The microphone 11 can be attached to the surface of a living body, such as a human body. When attached to the surface of a living body, the microphone 11 can detect sounds within the living body. The microphone 11 can be attached to the living body using, for example, an adhesive sheet. The method for attaching the microphone 11 to the living body is not limited to adhesive attachment. The microphone 11 can be attached to the living body using methods other than adhesive attachment.

[0044] The microphone 11 outputs a sound signal based on the detected sound inside the living body to the information processing device 20. The microphone 11 can be connected to the information processing device 20 by wire. Alternatively, the microphone 11 can have a wireless communication function. If it has a wireless communication function, the microphone 11 can be connected to the information processing device 20 in a manner that enables wireless communication.

[0045] The first coupling member 12 couples the plurality of microphones 11 to fix the relative positions of the plurality of microphones 11. The first coupling member 12 can be made of a material having high rigidity, for example, so as to be able to fix the relative positions of the plurality of microphones 11.

[0046] exist Figure 1 In the example shown, the first coupling component 12 couples the microphone 11-1 to the microphone 11-2. Furthermore, the first coupling component 12 couples the microphone 11-3 to the microphone 11-4. Furthermore, the first coupling component 12 couples the microphone 11-5 to the microphone 11-6. Furthermore, the first coupling component 12 couples the microphone 11-1 to the microphone 11-3. Furthermore, the first coupling component 12 couples the microphone 11-3 to the microphone 11-5. Furthermore, the first coupling component 12 couples the microphone 11-2 to the microphone 11-4. Furthermore, the first coupling component 12 couples the microphone 11-4 to the microphone 11-6.

[0047] The sound detection device 10 is mounted on the surface of a living body near where the target sound is expected to be generated. This embodiment uses the example of a case where the target sound is a stenotic murmur of a coronary artery. In this case, the multiple microphones 11-1 to 11-6 of the sound detection device 10 are mounted near the heart. Figure 2 2 shows an example in which a plurality of microphones 11 - 1 to 11 - 16 are installed near the heart of the human body 100 .

[0048] The information processing device 20 may be a dedicated computer or a general-purpose computer used in the sound detection system 1. In the case of a general-purpose computer, the information processing device 20 may be, for example, a tablet terminal, a smartphone, a notebook PC (Personal Computer), or a desktop PC.

[0049] The information processing device 20 acquires a sound signal based on the sound detected by the sound detection device 10 from the sound detection device 10 . In addition, the information processing device 20 acquires sound information based on the sound detected by the external sound detection microphone 30 from the external sound detection microphone 30 .

[0050] The information processing device 20 processes the sound signal received from the sound detection device 10 to improve the sensitivity to weak sounds to be detected. The configuration of the information processing device 20 is described below, and the details of the operation of the information processing device 20 will be described later.

[0051] The information processing device 20 includes a communication unit 21 , a storage unit 22 , an acquisition unit 23 , an input unit 24 , an output unit 25 , and a control unit 26 .

[0052] The communication unit 21 includes at least one communication interface. Examples of such communication interfaces include a LAN (Local Area Network) interface and a Bluetooth (registered trademark) interface. The communication unit 21 can communicate with various devices via a network or directly. If the sound detection device 10 has wireless communication capabilities, the communication unit 21 can communicate wirelessly with the sound detection device 10. If the external sound detection microphone 30 has wireless communication capabilities, the communication unit 21 can communicate wirelessly with the external sound detection microphone 30.

[0053] The storage unit 22 is, for example, a semiconductor memory, a magnetic memory, or an optical memory, but is not limited thereto. The storage unit 22 may also function as, for example, a main storage device, an auxiliary storage device, or a flash memory. The storage unit 22 stores any information used in the operation of the information processing device 20. For example, the storage unit 22 may also store system programs, application software programs, and various information received through the communication unit 21. The information stored in the storage unit 22 can also be updated by information received via, for example, the communication unit 21. A portion of the storage unit 22 may also be provided outside the information processing device 20. In this case, the portion of the storage unit 22 provided outside may also be connected to the information processing device 20 via any interface.

[0054] The acquisition unit 23 acquires, from the sound detection device 10, a sound signal based on the sound detected by the sound detection device 10. The acquisition unit 23 may acquire the sound signal from the sound detection device 10 via the communication unit 21.

[0055] The acquisition unit 23 acquires, from the external sound detection microphone 30 , sound information based on the sound detected by the external sound detection microphone 30 . The acquisition unit 23 may acquire a sound signal from the external sound detection microphone 30 via the communication unit 21 .

[0056] The input unit 24 includes one or more input interfaces for detecting user input and acquiring input information based on user operations. For example, the input unit 24 may be a physical key, a capacitance key, a touch screen integrated with the display of the output unit 25, or a microphone for receiving voice input, but is not limited thereto.

[0057] The output unit 25 includes one or more output interfaces for outputting information to inform the user. For example, the output unit 25 includes a display that outputs information in the form of images or a speaker that outputs information in the form of sounds, but is not limited thereto. The output unit 25 can output information in a variety of ways.

[0058] The control unit 26 includes at least one processor, at least one dedicated circuit, or a combination thereof. The processor can be a general-purpose processor such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit), or a dedicated processor dedicated to specific processing. Dedicated circuits can be, for example, FPGAs (Field-Programmable Gate Arrays) or ASICs (Application-Specific Integrated Circuits). The control unit 26 controls various components of the information processing device 20 and executes processing related to the operation of the information processing device 20.

[0059] The external sound detection microphone 30 is a microphone capable of detecting external sounds. Here, "external sounds" refer to sounds such as ambient sounds surrounding the sound detection system 1 that constitute noise relative to the sound detected by the sound detection device 10. The external sound detection microphone 30 outputs a sound signal based on the detected external sound to the information processing device 20. The external sound detection microphone 30 can be connected to the information processing device 20 either by wire or wirelessly.

[0060] <Operation of the sound detection system>

[0061] Next, explain Figure 1 The operation of the sound detection system 1 is shown.

[0062] The sound detection system 1 can improve the detection sensitivity for weak sounds in a living body. In the following description, the case of detecting a coronary artery stenosis murmur as a weak sound in a living body is given as a specific example.

[0063] The user of the sound detection system 1 places the sound detection device 10 near a location where the weak sound to be detected is expected to be generated. For example, if a coronary artery stenosis murmur is the target of detection, the user places the sound detection device 10 near the heart. Figure 2 This diagram shows a state where microphones 11 - 1 to 11 - 6 included in the sound detection device 10 are attached near the heart of the human body 100 .

[0064] The microphones 11 - 1 to 11 - 6 each output a sound signal based on the detected sound inside the human body to the information processing device 20 .

[0065] The acquisition unit 23 of the information processing device 20 acquires sound signals based on sounds detected by the plurality of microphones 11 - 1 to 11 - 6 from the plurality of microphones 11 - 1 to 11 - 6 .

[0066] The acquisition unit 23 acquires, from the external sound detection microphone 30 , a sound signal based on the external sound detected by the external sound detection microphone 30 .

[0067] The control unit 26 of the information processing device 20 performs noise cancellation by subtracting the sound signal acquired from the external sound detection microphone 30 from the sound signals acquired from the microphones 11-1 to 11-6. This allows the sound detection system 1 to reduce noise components caused by external sounds contained in the sound signals acquired from the microphones 11-1 to 11-6.

[0068] It should be noted that the sound detection system 1 does not necessarily need to perform noise cancellation and may not perform noise cancellation. In the case of a configuration in which noise cancellation is not performed, the sound detection system 1 may not include the external sound detection microphone 30.

[0069] Based on the sound signal acquired by the acquisition unit 23, the control unit 26 determines a first position, which is the position of a predetermined living body part. The sound signal acquired by the acquisition unit 23 may or may not be subjected to noise cancellation. Here, the "first position" refers to the position of a living body part that is in a predetermined relative positional relationship with the position where the faint sound, the target of detection, is assumed to be generated. In the case of a coronary artery stenosis murmur, the position where the faint sound is assumed to be generated is the position of the coronary artery. Hereinafter, the position where the faint sound is assumed to be generated is also referred to as the "second position."

[0070] When the second position is the position of the coronary artery, the predetermined body part located at the first position, which is in a predetermined relative positional relationship with the second position, is, for example, the mitral valve, tricuspid valve, pulmonary valve, and aortic valve. The body part located at the first position is a body part that produces a sound louder than the weak sound to be detected. Therefore, microphone 11 can more easily detect the sound produced at the first position than the sound produced at the second position.

[0071] The storage unit 22 stores information on the relative positional relationship between the first position and the second position. The storage unit 22 stores information on the relative positional relationship between the first position and the second position for at least one first position. When the second position is the position of the coronary artery, the first position is, for example, the position of the mitral valve, the position of the tricuspid valve, the position of the pulmonary valve, and the position of the aortic valve. In this case, the storage unit 22 stores at least one relative positional relationship among the relative positional relationship between the position of the mitral valve and the position of the coronary artery, the relative positional relationship between the position of the tricuspid valve and the position of the coronary artery, the relative positional relationship between the position of the pulmonary valve and the position of the coronary artery, and the relative positional relationship between the position of the aortic valve and the position of the coronary artery.

[0072] As explained in the Background Art section, heart sounds include sounds called I and II. I sounds are heard when the mitral and tricuspid valves close. II sounds are heard when the pulmonary and aortic valves close.

[0073] The I sound is the overlap of the sound of the mitral valve closing and the sound of the tricuspid valve closing. The II sound is the overlap of the sound of the pulmonary valve closing and the sound of the aortic valve closing.

[0074] The storage unit 22 stores feature values of the mitral valve closure sound extracted based on the sound samples emitted when the mitral valve closes. The feature values may include, for example, spectral feature values obtained by frequency analysis such as FFT (Fast Fourier Transform).

[0075] The sound sample emitted when the mitral valve closes may be a sample obtained by measuring the subject himself or herself, or a sample obtained by measuring another person.

[0076] The storage unit 22 similarly stores feature values for the sound of tricuspid valve closure, feature values for the sound of pulmonary valve closure, and feature values for the sound of aortic valve closure. It should be noted that the storage unit 22 storing the feature values for the sound of mitral valve closure, tricuspid valve closure, pulmonary valve closure, and aortic valve closure is merely an example, and the storage unit 22 stores feature values for any sound assumed to be emitted at the first position.

[0077] The control unit 26 performs frequency analysis, such as FFT, on the sound signal acquired by the acquisition unit 23 from the sound detection device 10, and extracts the characteristic values contained in the sound signal. The control unit 26 compares the extracted characteristic values with the characteristic values of various samples stored in the storage unit 22 to determine the type of sound contained in the sound signal acquired by the acquisition unit 23.

[0078] For example, the control unit 26 determines that the sound signal acquired by the acquisition unit 23 includes the sound of mitral valve closure and the sound of tricuspid valve closure at the timing of the occurrence of sound I. For example, the control unit 26 determines that the sound signal acquired by the acquisition unit 23 includes the sound of pulmonary valve closure and the sound of aortic valve closure at the timing of the occurrence of sound II.

[0079] When the control unit 26 identifies the sound type, it also identifies the location where the sound is generated, i.e., the first location. For example, when the control unit 26 determines that the sound signal acquired by the acquisition unit 23 includes the sound of mitral valve closure, it identifies the location where the sound of mitral valve closure is generated, i.e., the location of the mitral valve.

[0080] Reference Figure 3A and Figure 3B , explaining the first position determination performed by the control unit 26. Figure 3A and Figure 3B The waveform shown in exemplarily shows the sound signal generated at the first position.

[0081] Figure 3A It is a sound signal detected by the microphone 11 installed at a position close to the first position. Figure 3B is the sound signal detected by the microphone 11 installed at a position far from the first position. Figure 3B The sound signal, and Figure 3A Compared to the sound signal detected by each microphone 11, the amplitude is smaller and the phase is delayed. Thus, the amplitude and phase of the sound signal depend on the distance from the first position. Therefore, if the relative positions of the multiple microphones 11-1 to 11-6 are known, the first position can be determined based on the amplitude and phase of the sound signal based on the sound detected by each microphone 11 and the relative positions of the multiple microphones 11-1 to 11-6.

[0082] The relative positions of the plurality of microphones 11 - 1 to 11 - 6 are fixed, and information on the relative positions of the plurality of microphones 11 - 1 to 11 - 6 is stored in the storage unit 22 .

[0083] The control unit 26 determines the first position of a sound having a predetermined body part as a sound source based on the amplitude and phase of the sound signal acquired from each microphone 11 and the relative positions of the plurality of microphones 11-1 to 11-6. For example, if the predetermined body part is the mitral valve, the control unit 26 determines the position of the mitral valve based on the amplitude and phase of the sound signal acquired from each microphone 11 by the acquisition unit 23 and the relative positions of the plurality of microphones 11-1 to 11-6.

[0084] The control unit 26 similarly specifies the position of the tricuspid valve, the position of the pulmonary valve, and the position of the aortic valve.

[0085] It should be noted that the control unit 26 does not need to determine the positions of all the mitral valve, tricuspid valve, pulmonary valve, and aortic valve as the first position. The control unit 26 only needs to determine at least one of the positions of the mitral valve, tricuspid valve, pulmonary valve, and aortic valve as the first position.

[0086] If the determined first position is separated from the positions of the plurality of microphones 11-1 to 11-6 by a predetermined distance or more, the control unit 26 may cause the output unit 25 to output notification information recommending that the positions of the plurality of microphones 11-1 to 11-6 be moved. Alternatively, the control unit 26 may cause the output unit 25 to output information guiding the installation locations of the plurality of microphones 11-1 to 11-6 so that a position near the center surrounded by the plurality of microphones 11-1 to 11-6 is located near the first position.

[0087] Once the first position is determined, the control unit 26 estimates the second position based on the information on the relative positional relationship between the first and second positions stored in the storage unit 22. When a coronary artery stenosis murmur is the detection target, the control unit 26 estimates the position of the coronary artery as the second position.

[0088] Figure 4 FIG2 is a schematic diagram showing how the control unit 26 estimates the position of the coronary artery based on the position of the aortic valve and the position of the pulmonary valve. Figure 4 In FIG, P1 is the position of the aortic valve determined by the control unit 26 based on the sound signal acquired by the acquisition unit 23. P2 is the position of the pulmonary valve determined by the control unit 26 based on the sound signal acquired by the acquisition unit 23. P3 is the position of the coronary artery estimated by the control unit 26 based on P1 and P2.

[0089] Once the second position is estimated, control unit 26 controls the directivity of multiple microphones 11-1 to 11-6 to increase sensitivity at the second position. For example, control unit 26 controls the directivity of multiple microphones 11-1 to 11-6 by adjusting and combining the delay of the sound signals acquired from each microphone 11-1 to 11-6. By controlling the directivity of multiple microphones 11-1 to 11-6 to increase sensitivity at the second position, control unit 26 can acquire the sound signal generated at the second position with high sensitivity.

[0090] When controlling the directivity of the plurality of microphones 11-1 to 11-6, the control unit 26 may not use the audio signals of all the microphones 11-1 to 11-6. The control unit 26 may control the directivity of the microphone 11 using the audio signals of at least two of the plurality of microphones 11-1 to 11-6.

[0091] The output unit 25 controls the directivity of the plurality of microphones 11-1 to 11-6 to increase sensitivity at the second position and outputs information based on the sound signal acquired by the acquisition unit 23. The output unit 25 can output information based on the sound signal acquired by the acquisition unit 23 in various ways.

[0092] The output unit 25 can, for example, display the audio signal in a graph with the horizontal axis being the time axis and the vertical axis being the amplitude on a display, or can output the audio signal in the form of sound from a speaker.

[0093] The control unit 26 determines the intensity of the sound signal acquired from the second position and causes the output unit 25 to output an index based on the determination result. For example, the control unit 26 may determine whether the intensity of the sound signal acquired from the second position is greater than a predetermined threshold value. For example, if the intensity of the sound signal acquired from the second position is greater than a predetermined threshold value, the control unit 26 may cause the output unit 25 to display a message such as "Stenosis murmur in the coronary artery." For example, the control unit 26 may compare the intensity of the sound signal acquired from the second position with multiple thresholds and make a determination in multiple stages. For example, the control unit 26 may calculate an index (referred to as "stenosis degree") indicating the degree of stenosis assumed to be present based on the intensity of the stenosis murmur in the coronary artery and cause the output unit 25 to display a message such as "Stenosis degree: 0.8."

[0094] The control unit 26 may also use a learning model learned through machine learning to perform determination processing on the sound signal generated at the second position. The learning model may be, for example, a learning model learned based on actual coronary artery stenosis murmurs. The learning model may be stored in the storage unit 22.

[0095] Figures 5A to 5CA schematic diagram showing a situation in which a coronary artery stenosis murmur is acquired as a weak sound signal with high sensitivity. Figure 5A Schematic diagram showing a sound signal before noise cancellation and directivity control of the microphone 11 . Figure 5B Schematic diagram showing an audio signal at a stage after noise cancellation. Figure 5C This is a schematic diagram of an audio signal at a stage after the directivity of the microphone 11 is controlled in addition to noise cancellation.

[0096] exist Figures 5A to 5C In FIG, the region indicated by R1 indicates the region where sound I is detected. The region indicated by R2 indicates the region where sound II is detected. R3 indicates the region where a stenotic murmur of a coronary artery is detected.

[0097] Reference Figure 5A , it is difficult to determine whether R3 produces a coronary artery stenosis murmur. Figure 5B By performing noise elimination, some coronary artery stenosis murmurs were observed at R3, but they were still very small. Figure 5C By controlling the directivity of the microphone 11, the stenosis murmur of the coronary artery detected at R3 is made prominent.

[0098] Reference Figure 6 The flowchart shown explains the operation of the sound detection system 1 . Figure 6 The illustrated operation is performed in a state where the plurality of microphones 11 - 1 to 11 - 6 of the sound detection device 10 are attached to a living body.

[0099] The acquisition unit 23 of the information processing device 20 acquires audio signals from the plurality of microphones 11 - 1 to 11 - 6 (step S101 ).

[0100] The control unit 26 of the information processing device 20 determines the first position based on the sound signal acquired by the acquisition unit 23 in step S101 (step S102). When determining the first position, the control unit 26 may use the sound signal after noise cancellation.

[0101] The control unit 26 estimates the second position based on the first position specified in step S102 (step S103 ).

[0102] The control unit 26 controls the directivity of the plurality of microphones 11-1 to 11-6 so as to increase sensitivity at the second position estimated in step S103 (step S104). The control unit 26 may cause the output unit 25 to output information based on the sound signal acquired by the acquisition unit 23 while controlling the directivity of the plurality of microphones 11-1 to 11-6 so as to increase sensitivity at the second position.

[0103] As described above, according to the sound detection system 1 of this embodiment, the acquisition unit 23 acquires sound signals based on sounds within a living body from the multiple microphones 11-1 to 11-6. Based on the sound signals acquired by the acquisition unit 23, the control unit 26 determines a first position, which is the position of a predetermined living body part, and estimates a second position that is in a predetermined relative positional relationship with the first position. The control unit 26 then controls the directivity of the multiple microphones 11-1 to 11-6 to increase sensitivity at the second position. The output unit 25 then outputs information based on the sound signals acquired by the acquisition unit 23 while controlling the directivity of the multiple microphones 11-1 to 11-6 to increase sensitivity at the second position. Thus, the sound detection system 1 of this embodiment can improve detection sensitivity for weak sounds within a living body.

[0104] Furthermore, the sound detection system 1 of this embodiment can detect weak sounds such as coronary artery stenosis murmurs by simple measurement using the plurality of microphones 11 - 1 to 11 - 6 by increasing the detection sensitivity for weak sounds inside a living body.

[0105] (Second embodiment)

[0106] Figure 7 1 is a functional block diagram of a sound detection system 2 according to a second embodiment of the present invention. The sound detection system 2 includes a sound detection device 15 , an information processing device 20 , an external sound detection microphone 30 , and an imaging device 40 .

[0107] Regarding the sound detection system 2 of the second embodiment, the differences from the sound detection system 1 of the first embodiment will be mainly described, and description of common and similar points with the sound detection system 1 of the first embodiment will be appropriately omitted.

[0108] The sound detection device 15 includes a plurality of microphones 11-1 to 11-6 and a second coupling member 13. Figure 7 Although six microphones 11 - 1 to 11 - 6 are shown in FIG, the number of microphones 11 is not limited to 6. The number of microphones 11 may be any number of two or more.

[0109] The second connecting member 13 and Figure 1 Unlike the first coupling member 12 shown in FIG, the second coupling member 13 couples the microphones 11-1 to 11-6 so that the relative positions of the microphones 11-1 to 11-6 can be changed.

[0110] exist Figure 7In the example shown, the second coupling component 13 couples the microphone 11-1 to the microphone 11-2. Furthermore, the second coupling component 13 couples the microphone 11-3 to the microphone 11-4. Furthermore, the second coupling component 13 couples the microphone 11-5 to the microphone 11-6. Furthermore, the second coupling component 13 couples the microphone 11-1 to the microphone 11-3. Furthermore, the second coupling component 13 couples the microphone 11-3 to the microphone 11-5. Furthermore, the second coupling component 13 couples the microphone 11-2 to the microphone 11-4. Furthermore, the second coupling component 13 couples the microphone 11-4 to the microphone 11-6.

[0111] Figure 8 , an example of a case where multiple microphones 11-1 to 11-16 are attached near the heart of a human body 100 is shown. In the sound detection device 15 of the second embodiment, the second coupling member 13 couples the multiple microphones 11-1 to 11-6 so that their relative positions are variable. This allows the multiple microphones 11-1 to 11-6 to be attached to desired positions on the human body 100 with a high degree of freedom. For example, the user can attach the multiple microphones 11-1 to 11-6 without obstructions such as the ribs.

[0112] The imaging device 40 can capture images of the plurality of microphones 11 - 1 to 11 - 6 attached to a living body. When a user captures images of the plurality of microphones 11 - 1 to 11 - 6 , the imaging device 40 outputs the captured images to the information processing device 20 .

[0113] The camera 40 may be connected to the information processing device 20 by wire. Alternatively, the camera 40 may have a wireless communication function. If the camera 40 has a wireless communication function, the camera 40 may also transmit the captured image to the information processing device 20 wirelessly.

[0114] The acquisition unit 23 of the information processing device 20 acquires the images of the plurality of microphones 11 - 1 to 11 - 6 captured by the imaging device 40 .

[0115] The control unit 26 of the information processing device 20 analyzes the images of the plurality of microphones 11-1 to 11-6 acquired by the acquisition unit 23 and calculates the relative positions of the plurality of microphones 11-1 to 11-6. By using the calculated relative positions of the plurality of microphones 11-1 to 11-6, the control unit 26 can determine the first position based on the sound signal acquired by the acquisition unit 23, similar to the first embodiment.

[0116] The other operations of the sound detection system 2 of the second embodiment are the same as those of the sound detection system 1 of the first embodiment. The sound detection system 2 of the second embodiment has the same effects as those of the sound detection system 1 of the first embodiment.

[0117] The present invention is not limited to the structures specified in the above-described embodiments, and various modifications are possible without departing from the spirit of the invention as described in the claims. For example, the functions included in each component or step can be rearranged to avoid logical inconsistencies, and multiple components or steps can be combined into one or divided.

[0118] For example, in Figure 1 In the figure, the sound detection device 10, the information processing device 20, and the external sound detection microphone 30 are shown as independent devices, but the present invention is not limited to this configuration. The sound detection device 10 can also be incorporated into the information processing device 20. The external sound detection microphone 30 can also be incorporated into the information processing device 20.

[0119] In addition, for example, in the description of the second embodiment, it is described that the images of the plurality of microphones 11-1 to 11-6 captured by the camera device 40 are analyzed and the relative positions of the plurality of microphones 11-1 to 11-6 are calculated, but the method of calculating the relative positions of the plurality of microphones 11-1 to 11-6 whose relative positions are variable is not limited to this. The sound detection system 2 of the second embodiment may include a relative position measuring mechanism capable of measuring the relative positions of the plurality of microphones 11-1 to 11-6, and the control unit 26 may calculate the relative positions of the plurality of microphones 11-1 to 11-6 based on the relative positions of the plurality of microphones 11-1 to 11-6 measured by the relative position measuring mechanism. The relative position measuring mechanism may include, for example, a strain sensor and an angle sensor. If it is composed of a stretchable strain sensor, for example Figure 7 The second coupling member 13 shown in FIG. 1 can measure the distance between the microphones 11 using a strain sensor. Furthermore, the angle sensor can measure the angle between the microphones 11. The control unit 26 can calculate the relative positions of the plurality of microphones 11-1 to 11-6 based on the measurement results of the strain sensor and the angle sensor. Furthermore, the relative position measurement mechanism can include, for example, a magnetic field generating device and magnetic sensors provided on the plurality of microphones 11-1 to 11-6. The magnetic sensors can measure the angle between the microphones 11. The control unit 26 can calculate the relative positions of the plurality of microphones 11-1 to 11-6 based on the measurement results of the magnetic sensors.

[0120] In addition, Figure 7In the figure, the sound detection device 15, the information processing device 20, the external sound detection microphone 30, and the camera 40 are shown as independent devices, but this configuration is not limited to this. The sound detection device 15 can also be incorporated into the information processing device 20. The external sound detection microphone 30 can also be incorporated into the information processing device 20. The camera 40 can also be incorporated into the information processing device 20.

[0121] In addition, each embodiment describes the case where a coronary artery stenosis murmur is detected as a weak sound. However, the weak sound to be detected is not limited to coronary artery stenosis murmur. The sound detection system 1 of the first embodiment and the sound detection system 2 of the second embodiment can also be applied to the case where weak sounds other than coronary artery stenosis murmur are detected.

[0122] Industrial applicability

[0123] The present invention relates to a sound detection system and an information processing device.

[0124] Description of Reference Numerals

[0125] 1.2 Sound detection system

[0126] 10 Sound detection device

[0127] 11 Microphone

[0128] 12 First connecting part

[0129] 13 Second connecting part

[0130] 15 Sound detection device

[0131] 20 Information processing device

[0132] 21 Ministry of Communications

[0133] 22 Storage

[0134] 23 Acquisition Department

[0135] 24 Input section

[0136] 25 Output

[0137] 26 Control Department

[0138] 30 External sound detection microphone

[0139] 40 Camera

[0140] 100 Human Body

Claims

1. A sound detection system, characterized in that: include: a plurality of microphones that detect sounds inside a living body and are capable of outputting sound signals based on the detected sounds; as well as information processing device, The information processing device includes: an acquisition unit configured to acquire sound signals from the plurality of microphones; Control Department; and Output section, The control unit determines a first position as a position of a predetermined living body part based on the sound signal acquired by the acquisition unit, estimating a second position that is in a predetermined relative positional relationship with the first position, controlling the directivity of the plurality of microphones to increase sensitivity at the second position, The output unit outputs information based on the sound signal acquired by the acquisition unit in a state in which the directivities of the plurality of microphones are controlled so as to increase sensitivity with respect to the second position.

2. The sound detection system according to claim 1, wherein: The information processing device further includes a storage unit that stores information on the predetermined relative positional relationship between the first position and the second position.

3. The sound detection system according to claim 1 or 2, wherein: The control unit specifies the first position based on the amplitude and phase of the sound signal acquired from each of the microphones and the relative positions of the plurality of microphones for the sound having the predetermined body part as a sound source.

4. The sound detection system according to claim 1 or 2, wherein: The control unit controls the directivity of the plurality of microphones by adjusting and synthesizing the delay amount of the sound signal acquired from each microphone.

5. The sound detection system according to claim 1 or 2, wherein: The control unit determines the intensity of the sound signal acquired from the second position, and causes the output unit to output an index based on the determination result.

6. The sound detection system according to claim 1 or 2, wherein: The control unit controls the directivity of at least two microphones among the plurality of microphones so as to increase sensitivity at the second position.

7. The sound detection system according to claim 1 or 2, wherein: The control unit causes the output unit to output notification information recommending that the positions of the plurality of microphones be moved when the first position is separated from the positions of the plurality of microphones by a predetermined distance or more.

8. The sound detection system according to claim 1 or 2, wherein: The relative positions of the plurality of microphones are fixed.

9. The sound detection system according to claim 1 or 2, wherein: The relative positions of the plurality of microphones are variable. It also includes a relative position measuring mechanism that measures the relative positions of the plurality of microphones. The control unit calculates the relative positions of the plurality of microphones based on the relative positions of the plurality of microphones measured by the relative position measuring mechanism.

10. The sound detection system according to claim 1 or 2, wherein: It also has a camera device. The relative positions of the plurality of microphones are variable. The control unit calculates relative positions of the plurality of microphones based on the images of the plurality of microphones captured by the imaging device.

11. An information processing device, characterized in that: include: a plurality of microphones that detect sounds inside a living body and are capable of outputting sound signals based on the detected sounds; an acquisition unit configured to acquire sound signals from the plurality of microphones; Control Department; as well as Output section, The control unit determines a first position as a position of a predetermined living body part based on the sound signal acquired by the acquisition unit, estimating a second position that is in a predetermined relative positional relationship with the first position, controlling the directivity of the plurality of microphones to increase sensitivity at the second position, The output unit outputs information based on the sound signal acquired by the acquisition unit in a state in which the directivities of the plurality of microphones are controlled so as to increase sensitivity with respect to the second position.

Images