JP2014014543A - Determination system, determination method and program for determination system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a determination system, a determination method and a program for the determination system which can easily and conveniently determine whether a patient has a symptom of closed type apnea syndrome when he/she wakes up.SOLUTION: A determination system 1 includes: a sound acquisition unit 100 for acquiring a pseudo snore sound of an examinee; an analysis unit 110 for analyzing sound data of the pseudo snore sound acquired by the sound acquisition unit 100 and calculating a formant frequency included in the pseudo snore sound; a determination unit 120 for comparing the formant frequency calculated by the analysis unit 110 with a reference predetermined and determining whether the formant frequency meets the reference predetermined; and an output unit 130 for outputting the result of the determination by the determination unit 120.

Description

  The present invention relates to a determination system, a determination method, and a program for the determination system. In particular, the present invention relates to a determination system, a determination method, and a program for a determination system for obstructive apnea syndrome using pseudo snoring sounds.

  Conventionally, the snoring sound of the patient during sleep is acquired, the first formant frequency to the third formant frequency are calculated from the acquired snoring sound, and the patient is obstructed sleep apnea from the characteristics of the average frequency and standard deviation. It is known that it may be possible to detect whether there is a sign of a syndrome (for example, see Non-Patent Document 1).

Takahiro Enomoto, Udantha R Abeyratne, Tetsuya Enomoto et al., “Fundamental study on signs of apnea by snoring analysis”, IEICE technical report. MBE, ME and Bio Cybernetics, The Institute of Electronics, Information and Communication Engineers, 2008, 108 (126), 11-14

  However, in the method described in Non-Patent Document 1, it is necessary to obtain a snoring sound emitted from the patient while the patient is sleeping by installing a sound collecting microphone or the like around the patient. Since the measurement is performed after the sleep is obtained, unnecessary stress may be applied to the patient, and there is a demand for a simpler and simpler method for determining whether or not there is a sign of obstructive apnea syndrome.

  Accordingly, an object of the present invention is to provide a determination system, a determination method, and a program for a determination system that can determine whether or not there is a sign of obstructive apnea syndrome easily and easily when a patient wakes up.

To achieve the above object, the present invention calculates a formant frequency included in a pseudo snore sound by analyzing a voice acquisition unit that acquires a pseudo snore sound of a subject and voice data of the pseudo snore sound acquired by the voice acquisition unit The analyzing unit, the formant frequency calculated by the analyzing unit and a predetermined reference are compared, a determination unit that determines whether the formant frequency satisfies a predetermined reference, and the determination result of the determining unit is output And a determination system including an output unit.

  In the determination system, the formant frequency is the first formant frequency, and the analysis unit can calculate the first formant frequency by performing frequency analysis of the speech data using a linear prediction method.

  The determination system further includes a correction unit that performs a correction process on a predetermined reference based on the physique or posture of the subject, and the determination unit uses the predetermined reference after correction by the correction unit. You can also.

  In order to achieve the above object, the present invention obtains a subject's pseudo snoring sound, analyzes the sound data of the pseudo snoring sound obtained in the sound obtaining step, and analyzes the formant frequency included in the pseudo snoring sound. The analysis stage for calculating the frequency, the formant frequency calculated in the analysis stage and a predetermined standard are compared to determine whether the formant frequency satisfies the predetermined standard, and the determination in the determination stage A determination method is provided comprising an output stage for outputting a result.

  In order to achieve the above object, the present invention is a program for a determination system for determining whether or not a subject has a sign of obstructive sleep apnea syndrome. The voice acquisition function to be acquired, the voice data of the pseudo snore sound acquired by the voice acquisition function are analyzed, the analysis function for calculating the formant frequency included in the pseudo snore sound, and the formant frequency calculated by the analysis function are predetermined. There is provided a program for a determination system that realizes a determination function for comparing a reference and determining whether the formant frequency satisfies a predetermined reference and an output function for outputting a determination result of the determination function.

  According to the determination system, the determination method, and the program for the determination system according to the present invention, a determination system, a determination method, and a determination that can easily and easily determine whether there is a sign of obstructive apnea syndrome when the patient is awake. A system program can be provided.

It is a schematic diagram of the judgment system concerning an embodiment. It is a functional block diagram of the judgment system concerning an embodiment. It is an outline figure of judgment in a judgment part of a judgment system concerning an embodiment. It is an outline figure of judgment in a judgment part of a judgment system concerning an embodiment. It is a flowchart of the process of the determination of the determination system which concerns on this Embodiment. It is a hardware block diagram of the judgment system which concerns on embodiment. It is a figure which shows the time change of the 1st formant frequency contained in a test subject's pseudo snoring sound.

[Embodiment]
FIG. 1 shows an outline of a determination system according to an embodiment of the present invention.

(Outline of judgment system 1)
The determination system 1 according to the present embodiment includes a subject 200 in a state of being awakened lying on the bed 300 (that is, not in a sleeping state), a subject 205 in a state of being awakened by sitting on a chair 305, etc. Alternatively, a pseudo snoring sound emitted by a subject who is awake in a standing state or the like is acquired. In the present embodiment, the pseudo snoring sound is a soft palate vibration sound that a test subject makes in a pseudo manner when the test subject is awake. In other words, the pseudo snoring sound is a “sound that simulates snoring” generated when the subject wakes up by vibrating the back of his / her throat.

  Specifically, a sound acquisition unit 100 such as a microphone provided in the determination system 1 is disposed in the vicinity of the subject's mouth. And the audio | voice acquisition part 100 acquires the pseudo snoring sound which a test subject emits. The determination system 1 calculates the formant frequency (for example, the first formant frequency) included in the pseudo snore sound by analyzing the acquired pseudo snore sound.

  Here, the formant frequency is a frequency that resonates in the “vocal tract”. Human voices are emitted when air in the lungs passes through the respiratory tract, throat, oral cavity, and the like. The route to the respiratory tract, throat and mouth is referred to as the “vocal tract”. When a human utters a voice, the shape of the vocal tract changes. As the shape of the vocal tract changes, the formant frequency also changes. Due to this change in formant frequency, sounds such as “A”, “I”, “U” are emitted from the vocal tract to the outside. The formant frequencies are called the first formant frequency, the second formant frequency, the third formant frequency,...

  The determination system 1 compares the calculated formant frequency with a predetermined reference (for example, a predetermined frequency), and determines whether or not the predetermined reference is satisfied. The determination system 1 can also perform correction processing according to the subject's posture and / or physique on the predetermined reference, and determine whether the calculated formant frequency satisfies the corrected reference. The determination system 1 outputs a determination result from an audio output unit such as a speaker, an image output unit such as a monitor, and / or a printing unit such as a printer. Thereby, the judgment system 1 presents a screening result as to whether or not the subject has a sign of obstructive apnea syndrome to a subject who uses the judgment system 1 and / or other users other than the subject. be able to.

  The determination system 1 is realized in the form of an information terminal such as a personal computer, a portable information terminal such as a smartphone or a mobile phone, or a small information terminal having a shape that can be attached to the wrist of a subject.

  FIG. 2 shows an example of a functional configuration of the determination system according to the embodiment of the present invention.

  The determination system 1 according to the present embodiment includes an audio acquisition unit 100 that acquires a pseudo snore sound of a subject, an audio data storage unit 105 that stores data of the pseudo snore sound acquired by the audio acquisition unit 100 as audio data, An analysis unit 110 that analyzes audio data stored in the audio data storage unit 105 and calculates a formant frequency; and a correction unit 140 that performs a correction process according to a posture and / or physique of a subject according to a predetermined reference; The formant frequency calculated by the analysis unit 110 is compared with a predetermined reference or a standard subjected to correction processing, and whether or not the formant frequency satisfies the predetermined reference or the standard subjected to the correction processing. And a determination unit 120 for determining

  Further, the determination system 1 includes a reference data storage unit 150 that stores a predetermined reference used by the determination unit 120 for determination, an input unit 160 that inputs information on the posture and / or physique of the subject, And an output unit 130 for outputting the determination result to the outside.

(Voice acquisition unit 100)
The sound acquisition unit 100 is installed in the vicinity of the mouth of the subject in the awake state (that is, not in the sleep state), and acquires the pseudo snoring sound emitted by the subject. Specifically, the voice acquisition unit 100 acquires a pseudo snoring sound emitted by the subject at a predetermined interval. The voice acquisition unit 100 is, for example, a microphone. The voice acquisition unit 100 supplies the acquired pseudo snoring sound to the voice data storage unit 105.

  Note that the determination system 1 uses a plurality of sound acquisition units 100 for the purpose of reducing the influence of other sounds excluding the snoring sound, for example, the air conditioning sound of the room where the subject exists, power supply noise, and other noises. It can also be provided. In this case, one voice acquisition unit 100 is installed toward the subject's mouth. And the other audio | voice acquisition part 100 is installed toward the direction different from a test subject's mouth.

(Audio data storage unit 105)
The voice data storage unit 105 stores the pseudo snoring sound acquired by the voice acquisition unit 100 as voice data in association with a subject identifier that uniquely identifies the subject. The voice data storage unit 105 stores a plurality of voice data in association with the time when each voice data is acquired, in association with the subject identifier. The voice data storage unit 105 can further store subject information, which is information indicating the posture and / or physique of the subject input from the input unit 160, in association with the subject identifier. The information indicating the posture of the subject is information indicating the posture such as a sitting position, a standing position, or a supine position, for example. The information indicating the physique is, for example, a body mass index (BMI index). The voice data storage unit 105 supplies voice data and subject information to the analysis unit 110.

(Analysis unit 110)
The analysis unit 110 analyzes the audio data received from the audio data storage unit 105 and calculates a formant frequency included in the pseudo snoring sound. Specifically, the analysis unit 110 performs frequency analysis of speech data using a linear prediction method (for example, a linear prediction method of an autoregressive model used for time-series signal analysis), so that the first formant frequency is time-series. Calculate along. The analysis unit 110 can also calculate the second formant frequency and the third formant frequency.

  The analysis unit 110 can also have a differential amplifier circuit. When the analysis unit 110 includes a differential amplifier circuit, the differential amplifier circuit uses the pseudo snoring sound data acquired by the one sound acquisition unit 100 and other sounds (that is, noises) acquired by the other sound acquisition unit 100. ) In-phase signal with noise data is suppressed. Then, the differential amplifier circuit of the analysis unit 110 amplifies the difference between the audio data and the noise data. Thereby, the analysis part 110 suppresses the noise emitted from the position far from a test subject. The analysis unit 110 supplies the calculated formant frequency to the determination unit 120. In the present embodiment, the analysis unit 110 supplies the first formant frequency to the determination unit 120.

(Judgment unit 120, reference data storage unit 150)
The determination unit 120 compares the first formant frequency received from the analysis unit 110 with a predetermined reference stored in the reference data storage unit 150. Then, the determination unit 120 determines whether or not the first formant frequency satisfies the predetermined standard. For example, the reference data storage unit 150 stores a value of “330 Hz” as a threshold value of the first formant frequency included in the pseudo snoring sound emitted by a patient with obstructive apnea syndrome. The determination unit 120 determines whether or not the first formant frequency received from the analysis unit 110 exceeds “330 Hz”.

  When the first formant frequency exceeds “330 Hz”, the determination unit 120 determines that the first formant frequency has exceeded the threshold value. If the threshold is exceeded, the subject may have signs of obstructive apnea syndrome. On the other hand, when the first formant frequency is “330 Hz” or less, the determination unit 120 determines that the first formant frequency does not exceed the threshold value. If the threshold is not exceeded, the subject has few signs of obstructive apnea syndrome. The determination unit 120 supplies information indicating the determination result to the output unit 130.

  In addition, obstructive apnea syndrome is considered to be one of the causes that the subject's airway is obstructed or the airway becomes narrower. The present inventor has found that the first formant frequency of the pseudo snoring sound emitted when the patient with obstructive apnea syndrome awakens is higher than the first formant frequency of the pseudo snoring sound of a healthy person who is awake. A specific threshold is found.

  Here, the determination unit 120 can also determine with an index different from the above. For example, the determination unit 120 determines that the first formant exceeds “330 Hz” before a predetermined time (hereinafter, “scheduled elapsed time”) elapses from the time when the voice acquisition unit 100 starts acquiring the pseudo snore sound. When the analysis unit 110 calculates the frequency, it is determined that the threshold has been exceeded before the scheduled elapsed time has elapsed. If the threshold is exceeded before the scheduled elapsed time, the subject may have signs of obstructive apnea syndrome. The estimated elapsed time is calculated by, for example, calculating the first formant frequency included in the pseudo snoring sounds of a plurality of healthy persons along the time series, and from the start of the acquisition of the pseudo snoring sounds to the pseudo snoring sound of each healthy person. It is set from the average time until the first formant frequency exceeding 330 Hz is included.

  Further, the determination unit 120 has the amplitude width of the frequency fluctuation in the case of creating a graph with the time on the horizontal axis and the frequency on the vertical axis for the first formant frequency calculated by the analysis unit 110 along the time series. When the amplitude is larger than a predetermined amplitude width (hereinafter referred to as “reference amplitude”), it is determined that the reference amplitude has exceeded a specified value. If the reference amplitude exceeds a specified value, the subject may have signs of obstructive apnea syndrome. This reference amplitude is set, for example, from the average value of the frequencies when the first formant frequencies included in the pseudo snoring sounds of a plurality of healthy individuals are respectively calculated along the time series.

  In addition, for example, the determination unit 120 is configured such that the first formant frequency calculated along the time series by the analysis unit 110 exceeds a predetermined number of times “330 Hz” within a predetermined time, When an average value calculated from a plurality of first formant frequencies 110 calculated in time series is equal to or greater than a predetermined value, it is determined that a predetermined reference has been exceeded. If these predetermined criteria are exceeded, the subject may have signs of obstructive apnea syndrome.

  Further, the determination unit 120 uses the degree of dispersion of the first formant frequency, the degree of bias, the randomness, the slope of the change in the first formant frequency over time, and the like calculated in advance by the analysis unit 110 in time series. It is also possible to determine whether or not a predetermined standard has been exceeded.

(Correction unit 140)
The correction unit 140 performs a correction process on a predetermined reference stored in the reference data storage unit 150 based on the physique or posture of the subject. The correcting unit 140 uses the subject information stored in the voice data storage unit 105 in association with the subject identifier. The correction unit 140 executes correction processing using the subject information and a predetermined correction formula.

  For example, the correction unit 140 performs correction processing on a predetermined reference using the BMI index. As an example, the correction unit 140 uses a correlation equation obtained from the BMI index of each of a plurality of persons and a plurality of first formant frequency values obtained from the pseudo snoring sounds of each of the plurality of persons as a correction equation. The correction unit 140 sets a corrected reference value calculated by substituting the subject's BMI index into the correction formula as a new reference. There is a positive correlation between the BMI index and the first formant frequency. That is, as the value of BMI increases, the first formant frequency also increases.

  Moreover, the correction | amendment part 140 can also perform a correction process to a predetermined reference | standard based on a test subject's attitude | position. As an example, the correction unit 140 can use a correction formula corresponding to each of a plurality of postures of a person. That is, the correction unit 140 can perform correction processing according to a predetermined reference using correction expressions corresponding to cases where the posture of the person is a sitting position, a standing position, a lying position, or the like. Then, the determination unit 120 determines whether or not the subject has a sign of obstructive apnea syndrome using the reference for which the correction unit 140 has performed the correction process.

(Output unit 130)
The output unit 130 outputs a determination result indicating whether or not a predetermined reference of the determination unit 120 has been exceeded. It is difficult for the output unit 130 to determine whether the subject has a sign of obstructive apnea syndrome, when the subject has no sign of obstructive apnea syndrome, and whether the subject has a sign of obstructive apnea syndrome. The judgment result is output to the outside according to a plurality of stages. For example, the output unit 130 outputs the determination result to the outside as text, sound, and / or an image.

  3 and 4 show an outline of the determination in the determination unit of the determination system according to the embodiment of the present invention.

  First, referring to FIG. A graph 400 is a graph in which the first formant frequency calculated from the pseudo snoring sound of the first subject is plotted along a time series. On the other hand, the graph 405 is a graph in which the first formant frequency calculated from the pseudo snoring sound of the second subject different from the first subject is plotted along the time series.

  Referring to graph 400, the first formant frequency exceeds 330 Hz at time t1. When the reference data storage unit 150 stores “330 Hz” as a threshold, the determination unit 120 determines that a predetermined reference has been exceeded. In this case, there is an indication of obstructive apnea syndrome for the first subject. On the other hand, referring to the graph 405, the first formant frequency reaches the peak at time t2 after time t1, but does not exceed “330 Hz”. In this case, the determination unit 120 determines that it does not exceed a predetermined standard. In this case, there is no sign of obstructive apnea syndrome for the second subject.

  Further, for example, when the scheduled elapsed time T1 that is a predetermined time from the time when the voice acquisition unit 100 starts acquiring the pseudo snoring sound is set between the time t1 and the time t2, in the graph 400, Since the first formant frequency exceeds “330 Hz” at a time earlier than the scheduled elapsed time T1, the determination unit 120 determines that the predetermined reference is exceeded. In this case, there is an indication of obstructive apnea syndrome for the first subject. The scheduled elapsed time is determined as follows, for example. First, for a plurality of healthy subjects, the first formant frequency calculated from the repeated snoring sound is monitored along the time series until the first formant frequency closest to “330 Hz” is calculated from the start of the plot. Are calculated respectively. Then, an arithmetic average value of a plurality of calculated times or a value obtained by subtracting a predetermined time from the arithmetic average value can be set as the scheduled elapsed time.

  Reference is now made to FIG. First, in FIG. 4, a graph 420 is a graph in which the first formant frequency calculated from the pseudo snoring sound of a healthy person is plotted along a time series. In the case of a healthy person, the first formant frequency changes stably at a low frequency.

  On the other hand, the graph 410 is a graph in which the first formant frequency calculated from the pseudo snoring sound of the third subject is plotted along the time series. In the case of the third subject, the first formant frequency exceeds “330 Hz” at time t3, falls below “330 Hz” again after time t3, and exceeds “330 Hz” again at time t4, which is a time after time t3. Yes. That is, the determination unit 120 determines that the first formant frequency of the third subject exceeds the threshold value “330 Hz” a plurality of times (that is, the first formant frequency varies greatly). In this case, there is an indication of obstructive apnea syndrome for the third subject.

  The graph 415 is a graph in which the first formant frequency calculated from the pseudo snoring sound of the fourth subject is plotted along the time series. In the case of the fourth subject, the first formant frequency does not exceed “330 Hz”, but changes in the vicinity of “330 Hz” from time t3 to time t5, which is a time after time t3. In other words, the determination unit 120 changes over a predetermined time in the vicinity of “330 Hz” where the first formant frequency of the fourth subject is the threshold (that is, within a predetermined frequency range from “330 Hz”). Judge that In this case, there is an indication of obstructive apnea syndrome for the fourth subject.

(Outline of judgment method and processing of program for judgment system)
FIG. 5 shows an example of a part of the determination processing flow of the determination system according to the present embodiment.

  First, the voice acquisition unit 100 acquires a pseudo snoring sound emitted by a subject at a predetermined time interval (step 10; hereinafter, step is expressed as “S”). The voice acquisition unit 100 stores the acquired voice data of the pseudo snore sound in the voice data storage unit 105. Subsequently, the analysis unit 110 analyzes the sound data of the pseudo snore sound stored in the sound data storage unit 105, and calculates the formant frequency (for example, the first formant frequency) included in the pseudo snore sound (S20). .

  Next, the determination unit 120 compares a predetermined reference stored in the reference data storage unit 150 in advance with the formant frequency calculated by the analysis unit 110 (S30). Then, the determination unit 120 determines whether or not the formant frequency calculated by the analysis unit 110 satisfies the predetermined standard or exceeds the predetermined standard (S40). The determination unit 120 supplies the determination result to the output unit 130. The output unit 130 outputs the determination result received from the determination unit 120 to the outside (S50).

(Effect of embodiment)
The determination system 1 according to the present embodiment is information that simply determines whether or not the subject has a sign of obstructive apnea syndrome by analyzing a pseudo snoring sound emitted by the subject who is awake. Therefore, for example, it is possible to screen a subject who may have obstructive apnea syndrome in a short time in a health checkup or the like. Thereby, the judgment system 1 can raise the consciousness with respect to obstruction type apnea syndrome with respect to a test subject, and can raise the motivation to a close examination.

  Moreover, since the judgment system 1 installs the voice acquisition unit 100 in the vicinity of the subject's mouth and acquires the subject's pseudo snoring sound, it does not impose a large burden on the subject compared to the case where various sensors are attached to the subject. . And in the judgment system 1, since the test subject should just be awakening, it is not necessary to wait for the test subject to sleep until it snore, and it can judge a sign in a short time.

  Further, the determination system 1 corrects the formant frequency according to the posture and physique of the subject, and determines whether the subject has a sign of obstructive apnea syndrome using the corrected formant frequency. Signs can be judged more accurately than when snoring sound is analyzed as it is.

  FIG. 6 shows an example of a hardware configuration of the determination system according to the embodiment of the present invention.

  The determination system 1 according to the present embodiment includes a CPU 1500, a graphic controller 1520, a random access memory (RAM), a memory 1530 such as a read-only memory (ROM) and / or a flash ROM, a storage device 1540 for storing data, A read / write device 1545 for reading data from and / or writing data to a recording medium, an input device 1560 for inputting data, a communication interface 1550 for transmitting / receiving data to / from an external communication device, a CPU 1500 and a graphic controller 1520 A chip set 1510 that connects the memory 1530, the storage device 1540, the read / write device 1545, the input device 1560, and the communication interface 1550 so that they can communicate with each other. Provided.

  The chip set 1510 includes a memory 1530, a CPU 1500 that accesses the memory 1530 and executes predetermined processing, and a graphic controller 1520 that controls display on an external display device. Perform data passing. The CPU 1500 operates based on a program stored in the memory 1530 and controls each component. The graphic controller 1520 displays an image on a predetermined display device based on the image data temporarily stored on the buffer provided in the memory 1530.

  The chip set 1510 connects a storage device 1540, a read / write device 1545, and a communication interface 1550. The storage device 1540 stores programs and data used by the CPU 1500 of the determination system 1. The storage device 1540 is, for example, a flash memory. The read / write device 1545 reads the program and / or data from the storage medium storing the program and / or data, and stores the read program and / or data in the storage device 1540. For example, the reading / writing device 1545 acquires a predetermined program from a server on the Internet via the communication interface 1550 and stores the acquired program in the storage device 1540.

  The communication interface 1550 executes data transmission / reception with an external device via a communication network. Further, when the communication network is disconnected, the communication interface 1550 can execute data transmission / reception with an external device without going through the communication network. An input device 1560 such as a tablet or a microphone is connected to the chipset 1510 via a predetermined interface.

  The program of the determination system 1 stored in the storage device 1540 is provided to the storage device 1540 via a communication network such as the Internet or a recording medium such as a magnetic recording medium or an optical recording medium. Then, the program for determination system 1 stored in storage device 1540 is executed by CPU 1500.

  The determination system program executed by the determination system 1 according to the present embodiment works on the CPU 1500 to make the determination system 1 the sound acquisition unit 100, the sound data storage unit 105, and the analysis described with reference to FIGS. Unit 110, determination unit 120, output unit 130, correction unit 140, reference data storage unit 150, and input unit 160.

  FIG. 7 shows the change with time of the first formant frequency included in the pseudo snoring sounds of four subjects.

  First, each subject in the standing state was made to make a pseudo snoring sound, and the first formant frequency in the standing state was calculated. In FIG. 7, the graph is plotted on the “standing state” axis (that is, on the axis of −5 minutes on the horizontal axis). Next, each subject was laid on his / her back, and a pseudo snore sound was emitted at a predetermined interval (that is, every 5 minutes) to obtain the generated pseudo snore sound. The acquisition of the pseudo snoring sound was continued for 30 minutes (however, subject A continued for 25 minutes). Then, by analyzing the obtained pseudo snore sound, the first formant frequency included in the pseudo snore sound is calculated. As shown in FIG. 7, the horizontal axis is time and the vertical axis is the first formant frequency axis. And plotted.

  The four subjects are as follows.

Subject A: Standard build (standard range of BMI values), no signs of apnea.
Subject B: Body size is obese (BMI value is in the range of obesity) and does not snore during sleep.
Subject C: Body size is obese (BMI value obesity range) and neck is thick.
Subject D: Physique is standard (BMI value is in the standard range), and there is a sign of apnea when sleeping on the back.

  Table 1 shows values of the first formant frequency of the pseudo snoring sound of each subject for each time.

  Referring to the plot 500 of the subject A, the first formant frequency of the pseudo snore sound in the “standing state” is 194 Hz, and the first formant frequency of the pseudo snore sound in the state of lying on the back is substantially 173 Hz or less. It changed with the frequency of. That is, all the first formant frequencies were 330 Hz or less, and the first formant frequencies in the state of lying on the back also stably shifted at a frequency lower than the first formant frequency in the “standing state”. Therefore, the possibility that the subject A has the obstructive apnea syndrome is low, and the determination system 1 can output that the possibility that the subject A has the obstructive apnea syndrome is low as the determination result.

  Referring to the plot 505 of the subject B, the first formant frequency of the pseudo snore sound in the “standing state” is 177 Hz, and the first formant frequency of the pseudo snore sound in the state of lying on the back is substantially constant at 189 Hz or less. It changed with the frequency of. That is, all the first formant frequencies are 330 Hz or less, and the first formant frequency in the state of lying on its back is also in the “standing state” except for one point (189 Hz) 20 minutes after the start of measurement. It was stable at a frequency lower than the first formant frequency. Therefore, the possibility that the subject B has the obstructive apnea syndrome is low, and the determination system 1 can output as a determination result that the subject B is less likely to have the obstructive apnea syndrome.

  Referring to the plot 510 of the subject C, the first formant frequency of the pseudo snore sound in the “standing state” is 302 Hz, and the first formant frequency of the pseudo snore sound in the state of lying on the back is 10 minutes from the start of measurement. It was 347 Hz later, 341 Hz after 20 minutes, 338 Hz after 30 minutes, and sometimes exceeded 330 Hz. In the case of the subject C, the case where the first formant frequency exceeds 330 Hz and the case where the first formant frequency does not exceed 330 Hz were alternately observed, and the first formant frequency fluctuated greatly. Therefore, there is a possibility that the subject C has obstructive apnea syndrome, and the determination system 1 can output that the subject C may have obstructive apnea syndrome as a determination result.

  Referring to the plot 515 of the subject D, the first formant frequency of the pseudo snore sound in the “standing state” is 194 Hz, and the first formant frequency of the pseudo snore sound in the state of lying on the back is approximately 221 Hz or more and substantially constant. It changed with the frequency of. That is, although all the first formant frequencies were 330 Hz or less, the first formant frequency in the state of lying on its back changed at a higher frequency than the first formant frequency in the “standing state”. Therefore, there is a possibility that the subject D has the obstructive apnea syndrome, and the determination system 1 can output as a determination result that there is a possibility that the subject D has the obstructive apnea syndrome.

  While the embodiments of the present invention have been described above, the embodiments described above do not limit the invention according to the claims. In addition, not all the combinations of features described in the embodiments are essential to the means for solving the problems of the invention.

DESCRIPTION OF SYMBOLS 1 Judgment system 100 Audio | voice acquisition part 105 Audio | voice data storage part 110 Analysis part 120 Judgment part 130 Output part 140 Correction | amendment part 150 Reference | standard data storage part 160 Input part 200, 205 Subject 300 Bed 305 Chair 400, 405, 410, 415, 420 Graph 500, 505, 510, 515 Plot 1500 CPU
1510 chip set 1520 graphic controller 1530 memory 1540 storage device 1545 read / write device 1550 communication interface 1560 input device

Claims (5)

A voice acquisition unit that acquires the subject's pseudo snoring sound;
Analyzing the pseudo snore sound data acquired by the sound acquisition unit, and calculating a formant frequency included in the pseudo snore sound;
A determination unit that compares the formant frequency calculated by the analysis unit with a predetermined reference and determines whether the formant frequency satisfies the predetermined reference;
A determination system comprising: an output unit that outputs a determination result of the determination unit. The formant frequency is a first formant frequency;
The determination system according to claim 1, wherein the analysis unit calculates the first formant frequency by performing frequency analysis on the speech data using a linear prediction method. Based on the physique or posture of the subject, further comprising a correction unit that performs a correction process on the predetermined reference,
The determination system according to claim 2, wherein the determination unit uses the predetermined reference after correction by the correction unit. A voice acquisition stage for acquiring a subject's pseudo snoring sound;
Analyzing the sound data of the pseudo snoring sound acquired in the sound acquiring step, and calculating a formant frequency included in the pseudo snoring sound;
A determination step of comparing the formant frequency calculated in the analysis step with a predetermined reference and determining whether the formant frequency satisfies the predetermined reference;
A determination method comprising: an output step of outputting a determination result in the determination step. A program for a determination system that determines whether a subject has signs of obstructive sleep apnea syndrome,
In the judgment system,
A voice acquisition function for acquiring the subject's pseudo snoring sound;
Analyzing the sound data of the pseudo snore sound acquired by the sound acquisition function, and calculating the formant frequency included in the pseudo snore sound;
A determination function for comparing the formant frequency calculated by the analysis function with a predetermined reference and determining whether the formant frequency satisfies the predetermined reference;
A program for a determination system for realizing an output function for outputting a determination result of the determination function.

Images