KR102350890B1 - Portable hearing test device - Google Patents

Abstract

A portable hearing inspection device according to one aspect includes: a headset including a microphone and a speaker; and a portable electronic device which interworks with the headset to perform the hearing inspection on a subject. The portable electronic device may include: a memory configured to store pure tone data for each frequency, monosyllabic speech data, and polysyllable speech data used for the hearing inspection; and a processor configured to perform the hearing inspection of the subject using the pure tone data for each frequency, the monosyllabic speech data, and the polysyllable speech data, and taking into account the pronunciation characteristics of the dialect area used by the subject.

Description

Portable hearing test device

It relates to a portable hearing test device.

Currently, millions of people around the world suffer from hearing loss, many of whom are unaware of their hearing loss. Decreased hearing ability can be due to a number of factors including age, health, occupation, injury and illness. Hearing loss can significantly reduce quality of life, damage relationships, and reduce access to employment. Recently, the number of people with hearing loss is increasing due to the use of sound devices, an increase in the proportion of the elderly population, and an increase in a noisy environment.

In order to treat such hearing loss, first of all, it is necessary to detect it early and take appropriate measures. In order to detect hearing loss at an early stage, it is necessary to periodically visit a hospital and have a hearing test.

Republic of Korea Patent Publication No. 10-2011-0018829 (2011.02.24.)

An object of the present invention is to provide a portable hearing test device.

A portable hearing test device according to an aspect includes a headset including a microphone and a speaker; and a portable electronic device for performing a hearing test on a subject in association with the headset. The portable electronic device includes: a memory for storing pure tone data for each frequency, monosyllabic speech data, and polysyllable speech data used for a hearing test; and a processor configured to perform a hearing test of the subject using the pure tone data for each frequency, the monosyllabic speech data, and the polysyllable speech data, and taking into account the pronunciation characteristics of the dialect area used by the subject. may include

The processor outputs a pure tone while adjusting the sound intensity for each frequency through the speaker, receives feedback on whether or not audible is heard from the subject, obtains a minimum threshold for each frequency, and receives a minimum threshold for each frequency based on the determined minimum threshold for each frequency The hearing threshold can be obtained.

The processor randomly selects a predetermined number of syllables from among a plurality of syllables, sequentially outputs each selected syllable at an initial sound intensity determined based on the minimum audible threshold through the speaker, and through the microphone The subject's voice is collected, the collected voice is recognized using a pre-trained voice recognition model in consideration of regional pronunciation characteristics, and the result of speech recognition and the output syllable are determined to match each syllable of each syllable. Recognition may be evaluated, and sound intensity may be adjusted according to the evaluation result.

The processor repeatedly performs selection of the syllable, output of each selected syllable, collection of the subject's voice, recognition of the collected voice, evaluation of whether each syllable is recognized, and adjustment of sound intensity to obtain a speech listening threshold can

The processor may output a specific sentence while adjusting a sound intensity through the speaker, and may determine a comfort threshold by receiving feedback from the subject.

The initial sound intensity for outputting the specific sentence may be determined based on the speech listening threshold.

The processor selects one of a plurality of monosyllabic word sets, sequentially outputs each monosyllabic word of the selected monosyllabic word set at the comfort threshold intensity through the speaker, collects the subject's voice through the microphone, and collects regional pronunciation characteristics Speech intelligibility can be obtained by recognizing the collected speech using a speech recognition model learned in advance in consideration of

The processor may match the subject's voice data collected through the microphone with word information corresponding to the voice data and store the matching in the memory.

The processor may generate an audiogram based on the minimum threshold for each frequency, display the generated audiogram on a display screen, and store the audiogram in the memory.

The processor may display the hearing test result on a display screen and store it in the memory.

The memory may store noise data for masking, and the processor may further use the noise data for masking to perform a hearing test of the subject.

By using a headset and a portable electronic device, it is possible to simply perform a hearing test, which is expensive and requires a visit to a hospital, regardless of location.

In addition, it is possible to secure independence from the test performer and provide a standardized test by using a pre-recorded voice file for syllable words rather than the voice of the test performer.

In addition, since the hearing test is performed in consideration of the pronunciation characteristics of the dialect region used by the subject, the accuracy of the hearing test can be improved.

1 is a diagram illustrating a portable hearing test apparatus according to an exemplary embodiment.
2 to 12 are exemplary views illustrating a user interface screen displayed during a hearing test process.
13 is a diagram illustrating a method for performing a hearing test according to an exemplary embodiment.

Hereinafter, an embodiment of the present invention will be described in detail with reference to the accompanying drawings. In adding reference numerals to the components of each drawing, it should be noted that the same components are given the same reference numerals as much as possible even though they are indicated on different drawings. In addition, when it is determined that a detailed description of a known function or configuration related to the present invention may unnecessarily obscure the gist of the present invention, the detailed description thereof will be omitted.

On the other hand, in each step, each step may occur differently from the specified order unless the specific order is clearly stated in context. That is, each step may be performed in the same order as specified, may be performed substantially simultaneously, or may be performed in a reverse order.

The terms to be described below are terms defined in consideration of functions in the present invention, which may vary depending on the intention or custom of a user or operator. Therefore, the definition should be made based on the content throughout this specification.

Terms such as first, second, etc. may be used to describe various elements, but the elements should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from another. The singular expression includes the plural expression unless the context clearly dictates otherwise, and terms such as 'comprise' or 'have' refer to the features, numbers, steps, operations, components, parts, or combinations thereof described in the specification. It is to be understood that this is not intended to indicate the existence of one or more other features or numbers, steps, operations, components, parts, or combinations thereof, or to exclude in advance the possibility of addition or existence of one or more other features.

In addition, in the present specification, the classification of the constituent units is merely classified according to the main functions each constituent unit is responsible for. That is, two or more components may be combined into one component, or one component may be divided into two or more for each more subdivided function. In addition to the main functions that each of the constituent units is responsible for, each of the constituent units may additionally perform some or all of the functions of other constituent units, and some of the main functions of each constituent unit are dedicated to other constituent units. may be performed. Each component may be implemented as hardware or software, or may be implemented as a combination of hardware and software.

1 is a diagram illustrating a portable hearing test apparatus according to an exemplary embodiment.

Referring to FIG. 1 , a portable hearing test apparatus 100 according to an exemplary embodiment may include a headset 110 and an electronic device 120 .

The headset 110 is connected to the electronic device 120 by wire or wirelessly, receives and outputs audio for a hearing test from the electronic device 120 , and collects the subject's voice data and transmits it to the electronic device 120 . .

According to an exemplary embodiment, the headset 110 may include a speaker 111 , a microphone 112 , a soundproofing unit 113 , and a communication unit 114 .

The speaker 111 may output audio for a hearing test received from the electronic device 120 . The speaker 111 includes a left ear speaker for outputting audio for a hearing test to the left ear of a subject wearing the headset 110 and a right ear speaker for outputting audio for a hearing test to the right ear of a subject wearing the headset 110 can do.

The microphone 112 may collect voice data of a subject wearing the headset 110 .

The soundproofing unit 113 may be formed on a portion of the headset 110 in contact with the subject's ear, and may wrap the subject's ear wearing the headset 110 . As the soundproofing unit 113 wraps around the subject's ear, it is possible to block external noise when outputting an audio signal for a hearing test, thereby establishing an environment for a hearing test.

The communication unit 114 may be connected to the electronic device 120 by wire or wirelessly to communicate with the electronic device 120 . For example, the communication unit 114 may receive audio for a hearing test from the electronic device 120 , and transmit the subject's voice data collected through the microphone 112 to the electronic device 120 .

The electronic device 120 may interwork with the headset 110 to perform a hearing test on the subject. Here, the hearing test may include a pure tone hearing test, a speech listening threshold test, a speech intelligibility test, and the like.

According to an exemplary embodiment, the electronic device 120 is a portable electronic device, such as a mobile phone, a smart phone, a tablet, a notebook computer, a personal digital assistant (PDA), a portable multimedia player (PMP), a navigation device, an MP3 player, and a digital camera. , a wearable device, and the like.

The electronic device 120 may include a memory 121 , a display 122 , an input unit 123 , a communication unit 124 , a power management unit 125 , a battery 126 , an output unit 129 , and a processor 127 . can

The memory 121 may store programs or commands for operation of the electronic device 120 , and data input to the electronic device 120 , data processed by the electronic device 120 , and data of the electronic device 120 . Data necessary for processing can be stored.

The memory 121 may store audio data for a hearing test, for example, pure tone data for each frequency used for a hearing test, monosyllabic speech data, polysyllable speech data, and masking noise data.

Here, the frequency may include, but is not limited to, 125Hz, 250Hz, 500Hz, 750Hz, 1KHz, 1.5KHz, 2KHz, 3KHz, 4KHz, 6KHz, 8KHz, 12KHz, and the like. Monosyllabic words and polysyllable words are divided into pre-school, school-age, and general use, and may include monosyllabic words and polysyllable words included in the standard monosyllabic table and standard polysyllable table. Monosyllabic words may be grouped by a predetermined number to constitute a plurality of sets. For example, one set of monosyllabic words may include 25 or 50 monosyllabic words.

If there is a difference in hearing between the left and right ears, the noise data for masking is the noise that is heard in the untested ear so that the audio for the hearing test (eg, pure tone, monosyllabic speech, and disyllable speech by frequency) is not heard in the ear that is not tested. can

The memory 121 may pair and store the input subject information and the collected subject's voice data. Here, the subject information may include a name, age, gender, address, phone number, e-mail, SNS, region of the dialect used, and the like. The subject's voice data is a voice signal uttered by the subject and collected through the microphones 112 and 128, and may be matched with word information corresponding to the voice data and stored.

The memory 121 may store a voice recognition model. The speech recognition model is pre-trained in consideration of regional pronunciation characteristics, and may include an acoustic model and a language model.

The memory 121 may store hearing test result data. For example, the memory 121 may store pure tone hearing test result data, speech listening threshold test result data, speech intelligibility test result data, and the like.

The memory 121 may store a matching table capable of representing the volume output from the electronic device 120 as output in decibel units from the speaker 111 of the headset 110 . Through this, the electronic device 120 may adjust the sound intensity output from the headset 110 in units of decibels.

The display 122 may display data handled by the electronic device 120 or processing result data of the electronic device 120 .

The display 122 may output a user interface screen for inputting, adjusting, and displaying a result required for a hearing test.

According to an exemplary embodiment, the display 122 may be implemented as a touch screen. In this case, the touch screen may receive data according to a direct or indirect touch of the user's body or the touch pen. When the display 122 is implemented as a touch screen, the display 122 may also function as the input unit 123 .

The input unit 123 may receive various manipulation signals from the user. According to an embodiment, the input unit 123 may include a key pad, a dome switch, a jog wheel, a jog switch, and a hardware/software button.

The communication unit 124 may be connected to the headset 110 by wire or wirelessly to communicate with the headset 110 . For example, the communication unit 124 may transmit audio for a hearing test to the headset 110 and receive voice data of a subject collected through the headset 110 from the headset 110 .

The power management unit 125 may manage power of the electronic device 120 . For example, the power manager 125 may charge the battery 126 with electricity and control and manage power supply to the electronic device 120 .

The battery 126 may supply power for the operation of the electronic device 120 to the electronic device 120 .

The output unit 129 may output audio for a hearing test. The audio for the hearing test output from the output unit 129 may be transmitted to the headset 110 through the communication unit 124 .

The processor 127 may control the overall operation of the electronic device 120 .

The processor 127 may control a plurality of hardware or software components connected to the processor 127 by driving an operating system or an application program, and may perform various data processing and operations.

The processor 127 may perform a pure tone hearing test using pre-stored pure tone data for each frequency. Here, the pure tone audiometry may be performed on each of the left and right ears for the purpose of finding the lowest sound intensity (hereinafter referred to as the minimum audible threshold) that the subject can hear.

According to the exemplary embodiment, the processor 127 outputs the pure tone by adjusting the sound intensity for each frequency through the headset 110 , and receives feedback on whether or not audibility is heard from the subject through the input unit 123 to set the minimum audible threshold. can judge Here, the feedback may indicate whether the subject has heard the pure tone output through the headset 110 , and the unit of sound intensity may be decibels (dB).

For example, the processor 127 outputs a pure tone while adjusting the sound intensity for each frequency in the order of 125Hz, 250Hz, 500Hz, 750Hz, 1KHz, 1.5KHz, 2KHz, 3KHz, 4KHz, 6KHz, 8KHz, 12KHz, and the subject It is possible to determine the smallest sound intensity that the subject can hear for each frequency (hereinafter, referred to as the minimum threshold value for each frequency) through the feedback of audibleness input from the . In addition, the processor 127 may generate an audiogram based on the determined minimum threshold for each frequency, and obtain a minimum audible threshold by averaging some or all of the minimum thresholds for each frequency.

According to an exemplary embodiment, the processor 127 may display the generated audiogram on the screen of the display 122 and store it in the memory 121 .

The processor 127 may perform a speech listening threshold test using the polysyllable speech data. Here, the speech hearing threshold test may be performed on each of the left and right ears for the purpose of evaluating the reliability of the pure tone audiometry test result and the speech sensitivity.

Specifically, the processor 127 randomly selects a predetermined number (eg, 5, etc.) of syllables from among a plurality of syllables, and sequentially sets the selected syllables to the initial sound intensity of the speaker 111 ), and answer voice data spoken by the subject according to the syllable heard may be collected through the microphone 112 of the headset 110 . Here, the initial sound intensity may be determined based on the minimum audible threshold. For example, the initial sound intensity may be a value obtained by adding a predetermined intensity (eg, 10 decibels or 30 decibels) to the minimum audible threshold.

The processor 127 analyzes the subject's answer voice data using the voice recognition model to recognize a syllable, and determines whether the recognition result matches the syllable output through the headset 110 to determine whether each syllable is recognized. can be evaluated As described above, since the voice recognition model is pre-trained in consideration of regional pronunciation characteristics, the processor 127 may recognize the subject's voice in consideration of the pronunciation characteristics of the dialect region used by the subject.

The processor 127 decreases the sound intensity by a predetermined intensity (eg, 10 decibels, etc.) when it is determined that the recognition rate is 50% or more as a result of the recognition evaluation of the syllables used in the test, and the above-described predetermined number of syllables The process from selection to recognition rate determination can be repeated.

In addition, when it is determined that the recognition rate is less than 50% as a result of the recognition evaluation of the disyllable words used in the examination, the processor 127 increases the sound intensity by a predetermined intensity (eg, 5 decibels, etc.), and The process from selecting a syllable to determining the recognition rate can be repeated.

The processor 127 may match the test subject's response voice data collected during the speech listening threshold test with the output bisyllable words and store them in the memory 121 .

The processor 127 repeatedly performs sound intensity adjustment, selection of a predetermined number of syllables, sequentially outputting each selected syllable, collecting response voice data of the subject, and repeatedly evaluating the subject's recognition of the syllables, so that the subject is output A speech listening threshold, which is the minimum speech strength that can recognize more than 50% of polysyllable words, can be obtained.

The processor 127 may determine the comfort threshold and perform a speech intelligibility test using monosyllabic speech data. Here, the comfort threshold indicates an intensity suitable for the subject to listen comfortably, and the speech intelligibility test may be performed for the purpose of evaluating how accurately a monosyllabic word can be understood at the comfort threshold level. The comfort threshold judgment and speech intelligibility test may be performed for each of the left and right ears.

Specifically, the processor 127 outputs a specific sentence (eg, “Can you hear me?”) through the speaker 111 of the headset 110 while adjusting the sound intensity, and provides feedback from the subject through the input unit 123 . can be input to determine the comfort threshold. Here, the feedback may indicate whether the sound intensity output through the speaker 111 of the headset 110 is suitable for the subject to comfortably listen to. At this time, the sound intensity is initially determined as the sound intensity obtained by adding a predetermined strength (eg, 30 decibels or 40 decibels, etc.) to the speech listening threshold, and may be adjusted to a predetermined strength (eg, ㅁ5 decibels) according to the subject's feedback. .

When the comfort threshold is determined, the processor 127 selects one of a plurality of monosyllabic word sets, and sequentially outputs each monosyllabic word of the selected monosyllabic set at a comfort threshold intensity through the speaker 111 of the headset 110, and the headset ( 110) Through the microphone 112, the subject's answer voice data may be collected.

The processor 127 analyzes the subject's answer voice data using the voice recognition model to recognize monosyllabic words, and determines whether the recognition result matches the monosyllabic words output through the headset 110 to evaluate whether each monosyllabic word is recognized. As described above, since the voice recognition model is pre-trained in consideration of regional pronunciation characteristics, the processor 127 may recognize the subject's voice in consideration of the pronunciation characteristics of the dialect region used by the subject.

The processor 127 may obtain speech intelligibility based on the recognition evaluation result for each monosyllabic word used in the test. In this case, the speech intelligibility may be a recognition rate for all monosyllabic words used in the test.

The processor 127 may match the subject's answer voice data collected during the speech intelligibility test with the output monosyllabic word and store it in the memory 121 .

Also, when the speech intelligibility test is completed, the processor 127 may display the speech intelligibility test result in a report form on the screen of the display 122 and store it in the memory 121 . Also, the processor 127 may transmit the speech intelligibility test result to an external device (eg, a printer) according to a user's command.

Meanwhile, according to an exemplary embodiment, the processor 127 may output noise data for masking through an untested ear speaker during a pure tone audiometry test, a speech listening threshold test, and/or a speech intelligibility test.

According to an exemplary embodiment, the electronic device 120 may further include a microphone 128 . In this case, the electronic device 120 may collect the subject's voice data through the microphone 128 .

2 to 12 are exemplary views illustrating a user interface screen displayed during a hearing test process.

Referring to FIG. 2 , the processor 127 may display a first user interface screen for inputting subject information through the display 122 .

The first user interface screen includes a text box for inputting subject information, such as name, age, gender, phone number, region of the dialect used, and buttons (Back/Next) for moving to the previous and next steps. may include

Referring to FIG. 3 , the processor 127 may display a second user interface screen for a pure tone hearing test through the display 122 . The second user interface screen may be displayed when a next step button (Next) of the first user interface screen is selected.

), 피험자 피드백 입력 버튼("I can't hear it!"/ "I can hear it!"), 검사 종료 버튼(Finish), 최소가청역치(PTA) 입력 및 표시 영역, 청력도(audiogram) 도시 영역을 포함할 수 있다.The second user interface screen includes left/right ear selection buttons (LEFT/RIGHT), frequency control buttons (▽), volume control buttons (▲/▼), and play buttons (

), subject feedback input button ("I can't hear it!"/ "I can hear it!"), test end button (Finish), minimum audible threshold (PTA) input and display area, audiogram illustration It may contain areas.

When the subject feedback indicating that the subject has heard the reproduced pure tone is input, that is, when the 'I can hear it' button is pressed, the processor 127 may display the corresponding frequency and the corresponding sound intensity on the audiogram of the audiogram city area. . In this case, the left ear may be represented by X (blue) and the right ear may be represented by O (red) in accordance with the audiological standard. Meanwhile, since the audiogram records the frequency and sound intensity when the 'I can hear it' button is last pressed, when each frequency is changed to a different sound intensity, the audiogram may be updated with the changed sound intensity.

4 to 7 , the processor 127 may display a third user interface screen for the speech listening threshold test through the display 122 . The third user interface screen may be displayed when an inspection end button (Finish) of the second user interface screen is selected.

), 다시듣기 버튼(

), 인식 여부 평가 버튼(INCORRECT/CORRECT), 검사 종료 버튼(DONE), 인식(Correct) 및 오인식(Incorrect) 단어 숫자 표시 영역, 어음청취역치 표시 영역(Final Volume)을 포함할 수 있다. 이때 인식 여부 평가 버튼(INCORRECT/CORRECT)은 사용자 또는 피험자가 인식 여부를 판단하여 수동으로 선택하기 위한 방법이며, 음성인식 기능을 이용하는 경우 프로세서(127)에 의하여 인식 여부 평가가 자동으로 처리될 수도 있다.The third user interface screen includes a word selection button (Select Words), a left/right ear selection button (LEFT/RIGHT), and a play button (

), the listen button (

), a recognition evaluation button (INCORRECT/CORRECT), a test end button (DONE), a recognition (Correct) and incorrect recognition (Incorrect) word number display area, and a speech listening threshold display area (Final Volume). At this time, the recognition evaluation button (INCORRECT/CORRECT) is a method for the user or the subject to determine whether to recognize and manually select it, and when using the voice recognition function, the recognition evaluation may be automatically processed by the processor 127. .

When the word selection button (Select Words) is selected, the processor 127 displays a pop-up window for selecting a word category, for example, Preschool, School Children, and Adult on the third user interface screen. can be displayed (see FIG. 5). In addition, when a word category is selected, the processor 127 randomly selects a predetermined number (eg, five) of syllables from a plurality of syllables of the corresponding word category and displays the selected syllable on the third user interface screen. There is (see Fig. 6). Also, when the evaluation of whether each syllable is recognized is completed, the processor 127 may display a result of evaluating whether each syllable is recognized on each syllable (refer to FIG. 7 ).

Referring to FIG. 8 , the processor 127 may display a fourth user interface screen for determining the comfort threshold through the display 122 . The fourth user interface screen may be displayed when the test end button DONE of the third user interface screen is selected.

), 소리 강도 조절 버튼(▲/▼), 피험자 피드백 입력 버튼(NO/YES), 검사 종료 버튼(DONE), 쾌적역치 표시 영역(Final Volume)을 포함할 수 있다.The fourth user interface screen is left/right ear selection buttons (LEFT/RIGHT). Gender selection button (▽), play button (

), a sound intensity control button (▲/▼), a test subject feedback input button (NO/YES), a test end button (DONE), and a comfort threshold display area (Final Volume).

9 to 11 , the processor 127 may display a fifth user interface screen for the speech intelligibility test through the display 122 . The fifth user interface screen may be displayed when the test end button DONE of the fourth user interface screen is selected.

), 다시듣기 버튼(

), 인식 여부 평가 버튼(INCORRECT/CORRECT), 검사 종료 버튼(DONE), 인식(Correct) 및 오인식(Incorrect) 단어 숫자 표시 영역을 포함할 수 있다.The fifth user interface screen includes a monosyllable set list display button (Select a List), left/right ear selection buttons (LEFT/RIGHT), and a play button (

), the listen button (

), a recognition evaluation button (INCORRECT/CORRECT), an examination end button (DONE), and recognition (Correct) and incorrect recognition (Incorrect) words and numbers display areas.

When the monosyllabic set list display button (Select a List) is selected, the processor 127 selects a word category (eg, Preschool, School Children, and Adult) and a list of monosyllabic word sets of each category. may be displayed on the display 122 (see FIG. 10 ). In this case, the monosyllable set list of each category may be displayed as a separate user interface screen from the fifth user interface screen, or may be displayed as a pop-up window on the fifth user interface screen. Each set of monosyllabic words may be displayed in a different color depending on usage. For example, a set of monosyllabic words that are relatively frequently used may be displayed in a first color (eg, blue), and a set of monosyllable words that are relatively rarely used may be displayed in a second color (eg, red). By displaying the monosyllabic word sets in different colors according to the usage amount, it is possible to induce the selection of a relatively few monosyllabic word sets, and through this, various voice data of the subject can be collected in a balanced way.

When one of the displayed monosyllabic word sets list is selected, the processor 127 may display the selected monosyllabic word set on the fifth user interface screen (refer to FIG. 11 ). In addition, the processor 127 may display the evaluation result of whether each monosyllable word is recognized on each disyllable word (refer to FIG. 11 ). For example, as shown in FIG. 11 , when the presented monosyllabic word is correctly recognized, a green frame may be formed on the presented monosyllabic word, and when the presented monosyllabic word is incorrectly recognized, a red frame may be formed on the presented monosyllabic word.

Referring to FIG. 12 , the processor 127 may display a sixth user interface screen displaying the speech intelligibility test result through the display 122 . The sixth user interface screen may be displayed when the test end button DONE of the fifth user interface screen is selected.

The sixth user interface screen may include statistics on whether monosyllabic words are recognized, speech intelligibility, recognition results of each monosyllabic word, and a save button.

13 is a diagram illustrating a method for performing a hearing test according to an exemplary embodiment. The method of performing the hearing test of FIG. 13 may be performed by the portable hearing test apparatus 100 of FIG. 1 .

Referring to FIG. 13 , the portable hearing test apparatus may receive subject information ( S205 ). Here, the subject information may include a name, age, gender, address, phone number, e-mail, SNS, region of the dialect used, and the like.

The portable hearing test apparatus may perform a pure tone hearing test using pure tone data for each frequency ( 210 ). Here, pure-tone audiometry may be performed on each of the left and right ears for the purpose of finding the minimum audible threshold, which is the smallest sound intensity that the subject can hear.

According to an exemplary embodiment, the portable hearing test apparatus may output a pure tone by frequency through a speaker of the headset while adjusting the sound intensity, and may obtain a minimum audible threshold by receiving feedback on whether or not audibility is heard from a subject. For example, the portable hearing test device outputs a pure tone while adjusting the sound intensity for each frequency in the order of 125Hz, 250Hz, 500Hz, 750Hz, 1KHz, 1.5KHz, 2KHz, 3KHz, 4KHz, 6KHz, 8KHz, 12KHz, and the subject The minimum threshold for each frequency, which is the smallest sound intensity that the subject can hear for each frequency, can be obtained through the feedback received from the . In addition, the portable hearing test apparatus may generate an audiogram based on the determined minimum threshold for each frequency, and obtain a minimum audible threshold by averaging some or all of the minimum thresholds for each frequency.

The portable hearing test apparatus may perform a speech hearing threshold test using the polysyllable speech data ( 220 ). Here, the speech hearing threshold test may be performed on each of the left and right ears for the purpose of evaluating the reliability of the pure tone audiometry test result and the speech sensitivity.

Specifically, the portable hearing test device randomly selects a predetermined number of syllables from among a plurality of syllables (eg, 5, etc.), and sequentially outputs each selected syllable at an initial sound intensity through the speaker of the headset, The response voice data spoken by the subject along the syllable heard may be collected through the microphone of the headset. Here, the initial sound intensity may be determined based on the minimum audible threshold. For example, the initial sound intensity may be a value obtained by adding a predetermined intensity (eg, 10 decibels or 30 decibels) to the minimum audible threshold.

In addition, the portable hearing test device analyzes the subject's response voice data using a voice recognition model to recognize a syllable, and to evaluate whether each syllable is recognized by determining whether the recognition result matches the syllable output through the headset. can As described above, since the voice recognition model is pre-trained in consideration of regional pronunciation characteristics, the portable hearing test apparatus may recognize the subject's voice in consideration of the pronunciation characteristics of the dialect region used by the subject.

In addition, when it is determined that the recognition rate is 50% or more as a result of the recognition evaluation of the syllables used in the test, the portable hearing test device reduces the sound intensity by a predetermined intensity (eg, 10 decibels, etc.), and the above-described predetermined number of syllables The process from selecting a word to determining the recognition rate can be repeated.

In addition, when it is determined that the recognition rate is less than 50% as a result of the recognition evaluation of the syllables used in the test, the portable hearing test apparatus increases the sound intensity by a predetermined intensity (eg, 5 decibels, etc.), The process from selecting a syllable to determining the recognition rate can be repeated. In addition, the portable hearing test apparatus adjusts the sound intensity, selects a predetermined number of syllables, sequentially outputs each selected syllable, collects the subject's response voice data, and repeatedly evaluates the subject's recognition for the syllables, so that the subject can A speech listening threshold, which is the minimum speech strength at which 50% or more of the output syllables can be recognized, can be obtained.

According to an exemplary embodiment, the portable hearing test apparatus may match the subject's answer voice data collected during the speech listening threshold test with the output syllable and store it in the memory.

The portable hearing test apparatus may determine the comfort threshold ( 230 ).

For example, the portable hearing test device outputs a specific sentence (eg, "Can you hear me?") through the speaker of the headset while adjusting the sound intensity, and receives feedback from the subject to obtain an appropriate intensity for the subject to hear comfortably. The displayed comfort threshold can be determined. Here, the feedback may indicate whether the sound intensity output through the headset is suitable for the subject to comfortably listen to. In this case, the sound intensity is initially set as the sound intensity obtained by adding a predetermined strength (eg, 30 decibels or 40 decibels, etc.) to the speech listening threshold, and may be adjusted to a predetermined strength (eg, ㅁ5 decibels) according to the subject's feedback. The comfort threshold may be determined for each of the left ear and the right ear.

The portable hearing test apparatus may perform a speech intelligibility test using monosyllabic speech data ( 240 ). Here, the speech intelligibility test can be performed for the purpose of evaluating how accurately one can understand monosyllabic words at the comfort threshold level. Speech intelligibility testing can be performed on each of the left and right ears.

For example, when the comfort threshold is determined, the portable hearing test device selects one of a plurality of monosyllabic word sets, sequentially outputs each monosyllabic word of the selected monosyllabic set as a comfort threshold through the speaker of the headset, and through the microphone of the headset The test subject's response voice data may be collected.

In addition, the portable hearing test device analyzes the subject's response voice data using the voice recognition model to recognize monosyllabic words, and determines whether the recognition result matches the monosyllabic words output through the headset to evaluate whether each monosyllabic word is recognized. . As described above, since the voice recognition model is pre-trained in consideration of regional pronunciation characteristics, the portable hearing test apparatus may recognize the subject's voice in consideration of the pronunciation characteristics of the dialect region used by the subject.

In addition, the portable hearing test apparatus may obtain speech intelligibility based on the recognition evaluation result for each monosyllabic word used in the test. In this case, the speech intelligibility may be a recognition rate for all monosyllabic words used in the test.

According to an exemplary embodiment, the portable hearing test apparatus may match the test subject's answer voice data collected during the speech intelligibility test with the output monosyllabic words and store them in the memory.

Meanwhile, according to an exemplary embodiment, the portable hearing test apparatus may output noise data for masking through a non-tested ear speaker during a pure tone audiometry test, a speech listening threshold test, and/or a speech intelligibility test.

The above-described embodiments may be implemented as computer-readable codes on a computer-readable recording medium. The computer-readable recording medium may include any type of recording device in which data readable by a computer system is stored. Examples of the computer-readable recording medium may include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical disk, and the like. In addition, the computer-readable recording medium may be distributed in network-connected computer systems, and may be written and executed as computer-readable codes in a distributed manner.

100: portable hearing test device 110: headset
111: speaker 112, 128: microphone
113: soundproof unit 114: communication unit
120: electronic device 121: memory
122: display 123: input unit
124: communication unit 125: power management unit
126: battery 127: processor
129: output unit

Claims (11)

a headset including a microphone and a speaker; and
a portable electronic device that interworks with the headset to perform a hearing test on a subject; includes,
The portable electronic device comprises:
a memory for storing pure tone data for each frequency, monosyllabic speech data, and polysyllabic speech data used in the hearing test; and
Using the pure tone data for each frequency, the monosyllabic speech data, and the polysyllable speech data, a pure tone hearing test, a speech hearing threshold test, and a speech intelligibility test are performed on the subject in consideration of the pronunciation characteristics of the dialect used by the subject. the processor; including,
The processor displays a monosyllabic set list on the display screen during speech intelligibility testing using monosyllabic words, and displays each monosyllabic word set on the monosyllabic set list in different colors according to usage amount. The method of claim 1,
The processor is
Outputting a pure tone while adjusting the sound intensity for each frequency through the speaker, obtaining a minimum threshold for each frequency by receiving feedback on whether audible is from the subject, and obtaining a minimum audible threshold based on the minimum threshold for each frequency, portable hearing test device. 3. The method of claim 2,
The processor is
A predetermined number of syllables are randomly selected from among a plurality of syllables, and each selected syllable is sequentially output through the speaker at an initial sound intensity determined based on the minimum audible threshold, and the subject's voice through the microphone , recognizes the collected speech using a pre-learned speech recognition model in consideration of regional pronunciation characteristics, and evaluates whether each polysyllable is recognized by determining whether the speech recognition result matches the output polysyllable And, to adjust the sound intensity according to the evaluation result, a portable hearing test device. 4. The method of claim 3,
The processor is
Portable hearing test to obtain a speech listening threshold by repeatedly performing the selection of the syllable, outputting each of the selected syllables, collecting the subject's voice, recognizing the collected voice, evaluating whether each syllable is recognized, and adjusting the sound intensity Device. 5. The method of claim 4,
The processor is
A portable hearing test apparatus for outputting a specific sentence while controlling sound intensity through the speaker, and determining a comfort threshold by receiving feedback from the subject. 6. The method of claim 5,
The initial sound intensity for outputting the specific sentence is determined based on the speech listening threshold. 6. The method of claim 5,
The processor is
Selecting one of a plurality of monosyllabic word sets, sequentially outputting each monosyllabic word of the selected monosyllabic word set as the comfort threshold through the speaker, collecting the subject's voice through the microphone, and pre-learning in consideration of regional pronunciation characteristics A portable hearing test apparatus for recognizing the collected speech using a recognized speech recognition model, determining whether the recognized speech and the output monosyllabic words match, and evaluating whether each monosyllabic word is recognized to obtain speech intelligibility. According to claim 1,
The processor is
A portable hearing test apparatus that matches and stores the subject's voice data collected through the microphone with word information corresponding to the voice data in the memory. 3. The method of claim 2,
The processor is
A portable hearing test apparatus for generating an audiogram based on the minimum threshold for each frequency, displaying the generated audiogram on a display screen, and storing the audiogram in the memory. According to claim 1,
The processor is
A portable hearing test device that displays the hearing test result on a display screen and stores it in the memory. According to claim 1,
The memory stores noise data for masking,
The processor further uses the noise data for masking to perform a hearing test of the subject.

Images