KR102031295B1 - System for measurement of nasal energy change and method thereof - Google Patents

Abstract

The present invention relates to a nasal energy change measurement system which comprises: a voice file normalization unit normalizing a voice file in which a voice of a user reading a nasal sentence is recorded by correcting a tone, an intensity and a length; a nasal score meter generating a nasal score waveform of the normalized voice file received from the voice file normalization unit; a gradient extracting unit extracting a gradient value corresponding to at least one analysis variable pre-selected from the nasal score waveform generated by the nasal score meter; and a control unit measuring a change in nasal energy by comparing a first gradient value extracted at a previous time and a second gradient value extracted at a current time for each analysis variable.

Description

Nasal energy change measuring system and the measuring method {SYSTEM FOR MEASUREMENT OF NASAL ENERGY CHANGE AND METHOD THEREOF}

A nasal energy change measurement system and a method of measuring the same are provided.

Articulation is the result of organic connecting movements of articulation organs based on vocal pulsation, which can lead to minor changes in speech signals when some of the connections are lost or the human environment changes.

In general, the sound produced in the vocal cords is divided into the nasal cavity and the oral cavity, and the nasal cavity and the oral cavity are divided according to the position of the resonance.

Here, the nasal cavity mainly appears when pronounced non-sound such as ㅁ, ㄴ, ㅇ, and the oral sound appears when all the other consonants except the vowels and nasal sounds.

At this time, since the ratio of the oral sound and the nasal sound is determined according to the anatomical and functional state of the study dog, it is possible to estimate the nasal state of the user through the nasal sound value calculated using the oral sound and the nasal sound.

Here, the nasalance score is a value obtained by dividing the nasal acoustic energy by the sum of the nasal and oral acoustic energy, and analyzing various variable values such as the average value, the minimum value, the maximum value, and the slope value of the non-negative waveform. The nasal condition of can be estimated.

However, since the human voice has its own characteristics and the voice speed, pronunciation level, and voice size differ from person to person, even if a non-negative waveform is derived from the voice file between the subjects, the comparison between the subjects is difficult. Not easy Moreover, variables such as slope values in non-negative waveforms are highly dependent on recording speed, sound quality, and intensity, providing information about the velocity of the opening, but are substantially inter-subject or Because of the difficulty of comparative analysis between intra-subjects, it is difficult to use in the clinical field and difficult to conduct research.

In addition, the sentences used to measure the non-negative to date are divided into oral sound sentences, oral nasal sentences, non-negative sentences according to the ratio of the non-negative of all sentences, each sentence consists of a word repeat form. Here, the non-negative sentences often use simple non-sentence sentences rather than sentences that consider both the Korean nasal system and syllable structure. In other words, the minimum and maximum average values are often measured as non-negative values only by% of nasal energy.

Therefore, the slope value in the non-negative waveform is a useful concept for estimating the motility of the user's research pad by providing information on the speed of the research pad, but it is practically low in the clinical field.
As a related prior document, Korean Patent No. 1,182,762 discloses a "non-invasive nasal acoustic analysis apparatus, a non-invasive nasal acoustic analysis system capable of remote data transmission, a non-invasive nasal acoustic analysis method and a recording medium on which the method is recorded."

One embodiment of the present invention normalizes the voice data measured from a plurality of users and obtains a nasal energy gradient that can grasp the palpable motility, which has been difficult to study in the past, to easily perform comparative analysis between the same individual or multiple users. It is possible to obtain accurate and rapid changes in the nasal energy of the user.

In addition to the above objects, it can be used to achieve other objects not specifically mentioned.

A nasal energy change measurement system according to an embodiment of the present invention is received from a voice file normalization unit and a voice file normalization unit for normalizing by correcting the soundness, intensity, and length of a voice file in which a voice of a user reading a non-voice sentence is recorded. A non-negometer for generating a non-negative waveform of the normalized speech file, a gradient extractor for extracting a gradient value corresponding to at least one predetermined analysis variable from the non-negative waveform generated by the non-negative meter, and for each analysis variable And a controller configured to measure a change in nasal energy by comparing a first slope value extracted at a previous time point and a second slope value extracted at a current time point.

The analysis variable is an analysis variable for nasal energy that rises as syllables move from vowels to non-sounds in the final position of Hangul in vowels. Rising m, rising n, rising o As an analysis variable for the nasal energy descending while moving to the vowel in the non-magnetic location of the location may include falling m, falling n.

The non-speech sentence includes both non-choice in the first and last voices based on the Korean nasal system and the syllable structure, and the voice file can be recorded and stored in a two-channel manner in which the nasal and oral sounds are respectively measured.

The voice file normalization unit corrects the decibels of the voice file to a preset decibel band for input to a non-negative measuring instrument, resamples the frequency points of the voice file to 11025 Hz, and adjusts the length of the voice file to a preset time to normalize it. Can be.

The controller extracts a significant analysis variable from the measured changes in nasal energy for five analysis variables, selects a change in nasal energy corresponding to the extracted significant analysis variable, and estimates the user's nasal condition according to the change in the selected nasal energy. can do.

According to an exemplary embodiment of the present invention, there is provided a method of measuring a nasal energy change measurement system by normalizing a voice file in which a voice of a user reading a non-voice sentence is recorded by correcting soundness, intensity, and length, and receiving a normalized voice file. Generating a non-negative waveform of, extracting a slope value corresponding to at least one predetermined analysis variable from the non-negative waveform, and extracting the first slope value extracted from a previous time point and the current time point for each analysis variable Comparing the second slope value to measure a change in nasal energy.

One embodiment of the present invention can normalize the recorded voice file of each user, and can easily and accurately compare and analyze non-negative values between users, thereby providing a very convenient use in the clinic.

In one embodiment of the present invention, the non-speech according to the Korean nasal phonological system is a user by accurately and quickly measuring the minute change in the nasal energy of the user through the analysis variable according to the non-syllable sentences located in the beginning and the finality according to the syllable composition The nasal condition of can be estimated.

In addition, one embodiment of the present invention in the operation or treatment process, such as cleft palate patients, tonsils / adenoid surgery patients, sleep apnea patients, such as nasal problems, changes in the state before and after the operation or treatment, the effect of the operation or treatment, etc. In the process of analyzing and judging results, objective indicators can be provided.

1 is a block diagram showing a network including a nasal energy change measurement system according to an embodiment of the present invention.
2 is a block diagram showing a system according to an embodiment of the present invention.
3 is a flow chart illustrating a method for measuring change in nasal energy of a system in accordance with one embodiment of the present invention.
4 is an exemplary view showing a voice file before normalization of a system according to an embodiment of the present invention.
5 is an exemplary diagram illustrating a normalized voice file of a system according to an embodiment of the present invention.
6 is an exemplary view of extracting a non-negative waveform from the voice files of FIGS. 4 and 5.
7 is an exemplary diagram for explaining a process of extracting an analysis variable from a non-negative waveform of a system according to an exemplary embodiment of the present invention.

DETAILED DESCRIPTION Embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art may easily practice the present invention. As those skilled in the art would realize, the described embodiments may be modified in various different ways, all without departing from the spirit or scope of the present invention. The drawings and description are to be regarded as illustrative in nature and not restrictive. Like reference numerals designate like elements throughout the specification. In addition, in the case of well-known technology, a detailed description thereof will be omitted.

Throughout the specification, when a part is said to "include" a certain component, it means that it can further include other components, without excluding other components unless specifically stated otherwise.

Hereinafter, a nasal energy change measurement system according to an embodiment of the present invention will be described in detail with reference to FIGS. 1 and 2.

1 is a block diagram showing a network including a nasal energy change measurement system according to an embodiment of the present invention, Figure 2 is a block diagram showing a system according to an embodiment of the present invention.

As shown in FIG. 1, the nasal energy change measurement system 100, the two-channel recording apparatus 200, and the database 300 are connected to each other through a communication network, and transmit and receive data with each other.

The communication network may include any type of communication network for transferring data, such as a wired communication network, a short-range or long distance wireless communication network, or a mixed network thereof.

The nasal energy change measurement system 100 may receive a voice file recorded directly from the two-channel recording apparatus 200 through a communication network or search for and collect a voice file stored in the database 300.

The nasal energy change measurement system 100 may perform normalization to a preset standard using an original or a copy of a user's voice file, and generate a non-negative waveform from the normalized voice file. In addition, the nasal energy change measurement system 100 may measure the nasal energy of the user by extracting a slope value corresponding to at least one analysis variable from the non-negative waveform.

As shown in FIG. 2, the nasal energy change measurement system 100 includes a voice file normalization unit 110, a non-negative sound detector 120, a gradient extractor 130, and a controller 140.

First, the voice file normalization unit 110 corrects the soundness, the intensity, and the length by using the voice file recorded by the 2-channel recording apparatus 200 and normalizes it.

The voice file normalization unit 110 may correct decibels and lengths by matching pitch periods in the collected voice files, and may normalize them by resampling at a preset frequency.

In this case, the voice file normalization unit 110 normalizes certain conditions in the same manner without affecting the energy of nasal and consonant syllables in the voice file.

Next, the non-negative sound measurer 120 generates a non-negative waveform of the normalized voice file received from the voice file normalization unit 110.

Nasal value is a value obtained by dividing nasal acoustic energy by the sum of nasal and oral acoustic energy. Nasal value measuring instrument 120 calculates nasal values using the values of the oral and nasal sounds previously recorded from the two-channel recording apparatus. Non-negative waveforms can be generated by graphically displaying the non-negative values.

Here, the non-measurement meter 120 may be replaced with a two-channel recording device 200.

The gradient extractor 130 extracts a slope value corresponding to at least one analysis variable selected in advance from the non-negative waveform generated by the non-negative measuring instrument.

In other words, the analysis variable represents the slope value before and after the non-syllable syllable in the non-syllable sentence. The non-sound is ㅁ, ㄴ, ㅇ and can be located at the beginning and the end of the grammatical language suitable for the Korean syllable structure. When the non-sound ㅇ is located at the beginning, it is not pronounced, so 5 analysis variables are selected and analyzed. A slope value corresponding to each variable may be extracted.

The controller 140 compares the first slope value extracted from the previous time point and the second slope value extracted from the current time point for each analysis variable to measure the change in nasal energy.

The controller 140 may calculate a significant probability value using the first slope value of the analysis variable at the previous time point and the second slope value of the analysis variable at the current time point. In addition, meaningful analysis variables can be extracted from the significance probability value. Although the control unit 140 is significant, the user's nasal condition may be estimated through a change in the slope value of the analysis variable.

Referring to FIG. 1, the two-channel recording apparatus 200 may separate the channel for recording the oral sound and the channel for recording the nasal sound in the process of reading a specific sentence by the user to record the oral sound and the nasal sound through a unique channel. have.

In addition, the two-channel recording apparatus 200 may derive a graph or a result table to check the non-tone value through the voice file recorded through the two channels.

The two-channel recording apparatus 200 as described above may represent a device such as a Nasometer (Nasometer) of Kaypentx, but is not limited thereto.

Next, the database 300 stores the voice file recorded from the 2-channel recording apparatus 200 or the change value of the analysis file and the normalized voice file from the nasal energy change measurement system 100. Here, the database 300 may be located separately or embedded in the nasal energy change measurement system 100 or the two-channel recording apparatus 200.

Meanwhile, the nasal energy change measurement system 100 may be a server, a terminal, or a combination thereof.

A terminal is a collective term for a device having an arithmetic processing capability by providing a memory and a processor, respectively. For example, there are a personal computer, a handheld computer, a personal digital assistant, a mobile phone, a smart device, a tablet, and the like.

The server is a memory that stores a plurality of modules (module), the processor is connected to the memory and reacts to the plurality of modules, the processor for processing the service information or action information for controlling the service information provided to the terminal, communication Means, and a user interface (UI) display means.

Memory is a device for storing information. It is a non-volatile solid-state memory device such as high-speed random access memory, magnetic disk storage, flash memory devices, and other non-volatile solid-state memory devices. Various types of memory, such as volatile memory, may be included.

The communication means transmits and receives service information or action information with the terminal in real time.

The UI display means outputs service information or action information of the system in real time. The UI display means may be a separate device that directly or indirectly outputs or displays the UI, or may be part of the device.

Hereinafter, a method for measuring nasal energy change according to an embodiment of the present invention will be described in detail with reference to FIGS. 3 to 7.

3 is a flowchart illustrating a method for measuring change in nasal energy of a system according to an exemplary embodiment of the present invention, and FIG. 4 is an exemplary diagram illustrating a voice file before normalization of the system according to an exemplary embodiment of the present invention. Is an exemplary view showing a normalized voice file of a system according to an embodiment of the present invention.

As shown in FIG. 3, the two-channel recording apparatus 200 records a voice of a user who reads a non-voice sentence (S310).

Here, the non-syllable sentence may include both non-syllables in the beginning and finality based on the Korean nasal system and syllable structure.

For example, a sentence such as "mom goodbye" refers to a sentence consisting of words that are located in Korean and Jongsung, respectively, which are non-sound b, ㅁ, ㅇ in Korean.

The user can read the non-speech text, and the user's voice can be recorded in a two-channel manner so that the non-speech text and the oral sound generated while reading the non-speech text can be measured.

As shown in FIG. 4, when the two-channel recording device 200 records each oral sound and a nasal sound using Channel and Channel 2, the two-channel recording device 200 may diagram the recorded voice file.

Fig. 4 shows the first point of time (Mom goodbye 1) and the second point of time (Mom goodbye 2) recorded when the user reads the non-voice sentence "Mom goodbye". Although it is shown through FIG. 4 that the voice file is the same person, it can be seen that data of the voice file is differently represented due to a change in the oral cavity state of the user according to a viewpoint.

In order to perform a more objective comparative analysis of such changes in data, the nasal energy change measurement system 100 should equally correct the conditions of the voice files.

In other words, the nasal energy change measurement system 100 receives the recorded voice file and performs normalization to correct the voice file in terms of loudness, intensity, and length (S320).

The nasal energy change measurement system 100 may separately receive a phrase to be normalized from a received voice file from a user.

In other words, in the case of repeatedly recording "Goodbye Mom" or a sentence containing "Inner Mom", when the user inputs the "Goodbye Mom" part to analyze in the voice file, the section is extracted and normalized. Can be performed.

The nasal energy change measurement system 100 may normalize a voice file with the same conditions to facilitate comparative analysis among multiple users, where the same conditions are not only preset values for loudness, intensity, and length, but also a predetermined range. Can be represented.

For example, the nasal energy change measurement system 100 may perform normalization by setting the decibel to 70 dB, adjusting the length to 1 sec, and correcting the voice file to 11025 Hz.

5 is an exemplary diagram illustrating a normalized voice file of a system according to an embodiment of the present invention.

As shown in FIG. 5, the nasal energy change measurement system 100 maintains two channels for the recorded voice file of FIG. 4 and transforms the strength to a condition of 70 dB, DuR = 1 sec, and frequency 11025 hz.

In other words, the nasal energy change measurement system 100 may use a pitch-synchronus overlap add (PSOLA) method of copying each variable of the loudness, the intensity, and the length to increase a certain amount ratio in order to process the voice data. In addition, the nasal energy change measurement system 100 may apply a PSOLA method to correct a voice file, and then perform frequency correction through a voice file correction program such as Pratt.

The nasal energy change measurement system 100 may sequentially correct intensity, length, and frequency in the analysis section of "mom well", and the order of correction is not limited thereto.

Meanwhile, the normalization condition for correcting the loudness, the intensity, and the length may be set to match the input conditions required by the non-negative measuring device 120.

Next, the nasal energy change measurement system 100 generates a non-negative waveform of the normalized voice file (S330).

The nasal energy change measurement system 100 may generate a non-negative waveform using two-channel voice data from a normalized voice file through the non-negative meter 120, where the non-negative meter 120 is a two-channel recording device. 200 may be replaced.

As shown in FIG. 6, the nasal energy change measurement system 100 may generate a non-negative waveform corresponding to a normalized speech file.

6 (a) shows a non-negative waveform for a normalized voice file, and (b) shows a non-negative waveform for a normalized voice file.

The nasal energy change measurement system 100 calculates the nasal sound value by dividing the nasal acoustic energy by the sum of the nasal cavity and the oral acoustic energy in the two-channel speech file of the normalized speech file as shown in FIG. Can be provided.

Comparing the non-negative waveform (a) of the voice file and the non-negative waveform (b) of the normalized voice file before normalization, it can be seen that the peak values in the non-negative waveform become clear while maintaining the overall waveform shape.

In addition, the nasal energy change measurement system 100 extracts a slope value corresponding to at least one predetermined analysis variable (S340).

The nasal energy change measurement system 100 selects analytical variables representing nasal energy that rises as syllables move from vowels to non-vowels in non-negative waveforms and nasal energy that falls as syllables move from non-vowels to vowels in non-negative waveforms. Can be.

As shown in FIG. 7, the nasal energy change measurement system 100 may analyze rising variables na and n, and rising analytical variables corresponding to rising nasal energy and falling nasal energy, respectively, for the nasal sound b, ㅁ, ㅇ. o, falling m, falling n can be extracted.

More specifically, in response to the nasal sentence of "Mom Goodbye", the rising nasal energy is increased when the non-sound 'ㅁ' of the final position is pronounced in the vowel 'ㅓ' and the vowel ' When we pronounce ㅏ ', we select the analytical variable as falling m as the falling nasal energy. Similarly, the nasal energy rising when pronounced non-sound 'n' in the final position in vowel 'ㅓ' is rising and the nasal energy descending when pronounced vowel 'ㅕ' in non-sound 'n' in initial position. Select the analysis variable with falling n.

In addition, an analytical variable can be set to rising nasal energy as rising o when pronounced non-nodal 'ㅇ' in the final position in the vowel 'ㅕ'. Since non-sound is not pronounced when it is located at the beginning, 5 analysis variables for non-sound b, ㅁ, and ㅇ can be selected.

In other words, the nasal energy change measurement system 100 may extract a slope value of a position corresponding to five analysis variables selected according to the change of nasal energy.

Next, the nasal energy change measurement system 100 compares the first slope value extracted at the previous time point and the second slope value extracted at the present time point to measure the nasal energy change (S350).

The nasal energy change measurement system 100 may extract an analysis variable having a statistically significant value from the first slope values extracted at a previous time point and the second slope value extracted at the current time point using a significant probability value.

Here, the significance probability value represents the probability that the test statistic appears in the hypothesis test to reject the null hypothesis. If the probability value is lower than the significance level, the data can be interpreted as reliable and meaningful.

In addition, the nasal energy change measurement system 100 uses a significant probability value to extract an analysis variable having a significant value, but is not necessarily limited thereto.

In addition, the nasal energy change measurement system 100 may select a change in nasal energy of the user through a change value of a slope value corresponding to an analysis variable having a significant value.

For example, as shown in Table 1 below, the nasal energy change measurement system 100 compares and analyzes each of five variable values at a first time point Pre and a second time point Post and a significant probability value (P ^$). ) Is calculated. Here, the applied significance level value is 0.05, and when the significance probability value (P ^$ ) is lower than the significance level value, it may be recognized as meaningful data.

TABLE 1

표 1은 다수의 대상자들에 대해 제1 시점(Pre)과 제2 시점(Post)간 5개의 분석변수 값을 비교한 결과를 나타낸 표이다.

Table 1 shows a result of comparing five analysis variable values between a first time point Pre and a second time point Post for a plurality of subjects.

Table 1 shows the lower 25% of the measured values, the median of the 50% of the measured values, and 75%, depending on the magnitude of the value of each analysis variable at the first time point Pre and the second time point Post. It represents the measured value and the significance probability value (P ^$ ) for each analysis variable.

As shown in Table 1, the nasal energy change measurement system 100 may confirm that only the significant probability value P ^$ of Rising m has a significant value of 0.012 among the variables of the non-negative waveform. In other words, through the statistically significant result value of the rising m slope value it can be seen that the siege / ㅁ / was affected by surgery or treatment. Accordingly, the nasal energy change measurement system 100 selects a value of the significant analytical variable Rising m, and compares the slope values with respect to the non-negative waveform of the same patient with a time difference from the result of the statistically significant slope of Rising m. Or it can be seen that it is easy to compare the slope value for the non-negative waveform between a plurality of patients.

Referring to Table 1, it can be seen that only the numerical value of the significant analysis variable Risign m has a consistently larger value at the second time point (Post) than at the first time point (Pre). As such, when the rising m shows a higher value at the second post than the first point Pre, the nasal energy change measuring system 100 is in the nasal cavity in front of the user's nasal cavity where the non-sound k is resonant. It can be assumed that the energy has changed. In other words, the nasal energy change measurement system 100 may estimate a case in which a user's velum falls rapidly or a peak of a non-negative value rises.

In fact, Table 1 shows the significant probability values for the results of comparison between the time point just before the operation and the time point 3 months after surgery in 15 patients who had snoring surgery. Because the patients had both snoring and septal curvature, the energy actually changed in front of their nasal passages.

Therefore, it can be seen that the method of estimating the minute nasal energy change of the user has high accuracy through the rising m showing the change in the front of the nasal cavity selected as a significant analysis variable in the present invention. As described above, the nasal energy change measurement system 100 may extract a significant analysis variable and estimate a user's nasal condition according to the change of nasal energy corresponding to the extracted significant analysis variable.

The nasal energy change measuring system or program for measuring the nasal energy change may be recorded on a computer readable recording medium.

Computer-readable media may include, alone or in combination with the program instructions, data files, data structures, and the like. The media may be those specially designed and constructed or those known and available to those skilled in the computer software arts. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tape, optical recording media such as CD-ROMs, DVDs, magnetic-optical media such as floppy disks, and ROM, RAM, flash memory, and the like. Hardware devices specifically configured to store and execute the same program instructions are included. In this case, the medium may be a transmission medium such as an optical or metal wire, a waveguide, or the like including a carrier wave for transmitting a signal specifying a program command, a data structure, and the like. Examples of program instructions include not only machine code generated by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like.

Although one preferred embodiment of the present invention has been described in detail above, the scope of the present invention is not limited thereto, and various modifications and improvements of those skilled in the art using the basic concept of the present invention defined in the following claims are also provided. It belongs to the scope of the present invention.

100: nasal energy change measurement system 110: voice file normalization unit
120: non-negative measuring instrument 130: gradient extraction unit
140: control unit 200: two-channel recording device
300: database

Claims (10)

Voice file normalization unit for normalizing the voice file recorded by the user's voice reading the non-speech text by correcting the tone, intensity and length,
A non-negative measuring device for generating a non-negative waveform of the normalized voice file received from the voice file normalizer;
A gradient extracting unit for extracting a gradient value corresponding to at least one analysis variable previously selected from the non-negative waveform generated by the non-negative measuring instrument, and
Control unit for measuring the change in nasal energy by comparing the first slope value extracted from the previous time point and the second slope value extracted at the current time point for each analysis variable
Including
The analysis variable is a nasal energy change measurement system representing the nasal energy rising as the syllables move from vowels to non-vowels in the non-negative waveform and the nasal energy falling from non-needs to vowels in the non-negative waveform.
In claim 1,
The analysis variable,
In the non-negative waveform, the syllables are rising m, rising n, rising o, and the syllables in the non-negative waveform are shifted from the vowel to the non-negative sound of the final position of Hangul. Nasal energy change measurement system including falling m, falling n as an analysis variable for the falling nasal energy moving from vowel to vowel.
The method of claim 1 or 2,
The non-voice sentence
Based on Korean nasal system and syllable structure
The voice file,
Recorded and stored in a two-channel method for measuring nasal and oral sounds
Nasal energy change measurement system.
In claim 3,
The voice file normalization unit,
A nasal cavity that corrects the decibels of the voice file to a predetermined decibel band for input to the non-negative meter, resamples the frequency points of the voice file to 11025 Hz, and adjusts and normalizes the length of the voice file to a preset time. Energy change measurement system.
In claim 4,
The control unit,
The nasal condition of the user according to the change of the nasal energy selected by extracting a significant analysis variable among the measured change of nasal energy for the five analysis variables and selecting the change of nasal energy corresponding to the extracted significant analysis variable Nasal energy change measurement system to estimate.
The voice file normalization unit normalizes the voice file in which the voice of the user reading the non-speech text is recorded by correcting the soundness, intensity, and length of the voice file.
The non-negative meter generating a non-negative waveform of the received normalized speech file;
A slope extracting unit extracting a slope value corresponding to at least one analysis variable previously selected from the non-negative waveform, and
The control unit measures the nasal energy change by comparing the first slope value extracted from the previous time point and the second slope value extracted from the current time point for each analysis variable.
Including,
The analysis variable is a method of measuring a nasal energy change measurement system representing nasal energy rising as syllables move from vowels to non-vowels in the non-negative waveform and falling nasal energy moving from vowels to non-vowels in the non-negative waveform. .
In claim 6,
The analysis variable,
In the non-negative waveform, the syllables are rising m, rising n, rising o, and the syllables in the non-negative waveform are shifted from the vowel to the non-negative sound of the final position of Hangul. Measurement method of the nasal energy change measurement system including falling m, falling n as an analysis variable for the nasal energy falling while moving from vowel to vowel.
In claim 6 or 7,
The non-voice sentence
Based on the Korean nasal system and syllable structure, all non-sounds are included in the first and last
The voice file,
Recorded and stored in a two-channel method for measuring nasal and oral sounds
Method of measurement of nasal energy change measurement system.
In claim 8,
The normalizing step is
A nasal cavity that corrects the decibels of the voice file to a predetermined decibel band for input to the non-negative meter, resamples the frequency points of the voice file to 11025 Hz, and adjusts and normalizes the length of the voice file to a preset time. Method of measuring energy change measurement system.
In claim 9,
Measuring the change of nasal energy,
The nasal condition of the user according to the change of the nasal energy selected by extracting a significant analysis variable among the measured change of nasal energy for the five analysis variables and selecting the change of nasal energy corresponding to the extracted significant analysis variable Method of measurement of nasal energy change measurement system to estimate the.

Images