阅读说明：本技术 一种音频信号补偿方法、装置、设备及存储介质 (Audio signal compensation method, device, equipment and storage medium ) 是由 薛俊朋 王奉宝 隋松亮 于 2021-07-27 设计创作，主要内容包括：本申请公开了一种音频信号补偿方法、装置、设备及存储介质。该方法包括：采集耳廓处的压力值；根据所述压力值判断用户是否佩戴口罩；若用户佩戴口罩,则对用户的语音进行音频信号补偿。由此以来,在感受到用户佩戴口罩情形下会智能补偿用户的语音,以此补偿由于口罩覆盖遮挡所造成的声损失,达到与不佩戴口罩相同,甚至更优的通话效果,避免了口罩佩戴对用户通话质量的影响,提高了口罩佩戴情况下用户的通话体验。(The application discloses an audio signal compensation method, an audio signal compensation device, audio signal compensation equipment and a storage medium. The method comprises the following steps: collecting a pressure value at the auricle; judging whether the user wears the mask or not according to the pressure value; and if the user wears the mask, audio signal compensation is carried out on the voice of the user. From this, can intelligent compensation user's pronunciation under the user wearing gauze mask condition is experienced to this compensation is because the gauze mask covers the acoustic loss who shelters from and cause, reaches and does not wear the gauze mask the same, and even more excellent conversation effect has avoided the gauze mask to wear the influence to user speech quality, has improved user's conversation under the gauze mask condition of wearing and has experienced.)

1. A method of audio signal compensation, comprising:

collecting a pressure value at the auricle;

judging whether the user wears the mask or not according to the pressure value;

and if the user wears the mask, audio signal compensation is carried out on the voice of the user.

2. The audio signal compensation method of claim 1, wherein the audio signal compensation of the voice of the user comprises:

determining a pressure grade corresponding to the pressure value;

and determining a pre-established target EQ curve corresponding to the pressure grade according to a mapping relation between the pre-established pressure grade and the EQ curve, and performing corresponding audio signal compensation on the voice of the user by using the target EQ curve.

3. The audio signal compensation method of claim 2, wherein the construction of any EQ curve comprises:

collecting voice in a standard state to obtain an original frequency response;

collecting voice under the state of wearing the mask to obtain sound loss frequency response;

and constructing and obtaining the EQ curve according to the difference between the original frequency response and the acoustic loss frequency response.

4. The audio signal compensation method of claim 1, wherein the determining whether the user wears the mask according to the pressure value comprises:

calculating the difference value between the pressure value and the historical pressure value acquired last time;

and judging whether the user wears the mask or not according to the size relation between the difference value and the pressure difference value threshold.

5. The audio signal compensation method of claim 1, wherein the determining whether the user wears the mask according to the pressure value comprises:

judging whether the user wears the mask or not according to the magnitude relation between the pressure value and the pressure threshold value;

before judging whether the user wears the gauze mask according to the magnitude relation of pressure value and pressure threshold, still include:

monitoring whether a threshold determination condition is currently met;

if the threshold value determination condition is met currently, it is determined that the ear device which collects the pressure value currently is worn at the auricle and the user does not wear the mask, then the pressure value at the current auricle is obtained, and the pressure value is determined as the pressure threshold value.

6. The audio signal compensation method of claim 5, wherein the monitoring whether a threshold determination condition is currently satisfied comprises:

detecting whether the current ear equipment is worn at an auricle, if so, playing a preset prompt tone and timing, then judging whether the timing duration reaches the preset duration, and if so, judging that the threshold value determining condition is met currently; the preset prompt tone is used for prompting a user to don the mask;

or monitoring whether an instruction triggered by a user through a preset instruction triggering interface is received at present, and if the instruction is received, judging that the threshold value determining condition is met at present.

7. The audio signal compensation method according to any one of claims 1 to 6, wherein before determining whether the user wears the mask according to the pressure value, the method further comprises:

judging whether a user is currently wearing ear equipment for collecting the pressure value at the auricle;

if the user is judged to be wearing the ear equipment currently, the step of judging whether the user wears the mask according to the pressure value is prohibited to be started;

otherwise, starting the step of judging whether the user wears the mask according to the pressure value.

8. An audio signal compensation apparatus, comprising:

the pressure value acquisition module is used for acquiring a pressure value at the auricle;

the judging module is used for judging whether the user wears the mask or not according to the pressure value;

and the compensation module is used for compensating the audio signal of the voice of the user if the judgment result of the judgment module indicates that the user wears the mask.

9. An electronic device, comprising:

the pressure sensor is used for outputting a corresponding pressure value when sensing pressure;

a memory for storing a computer program;

a processor for executing the computer program to implement the audio signal compensation method of any one of claims 1 to 7.

10. A computer-readable storage medium for storing a computer program; wherein the computer program when executed by a processor implements the audio signal compensation method of any of claims 1 to 7.

Technical Field

The present invention relates to the field of signal compensation, and in particular, to a method, an apparatus, a device, and a storage medium for audio signal compensation.

Background

At present, the mask is increasingly a necessity of people, and the mask must be worn in public places such as outgoing travel and public transportation. However, wearing of the mask has certain influence on the communication quality of a user, for example, when the user wears the mask, the voice of the user of the earphone is attenuated and lost due to shielding of the mask, and the using effect and experience of a far end are directly influenced. Therefore, how to avoid the influence of mask wearing on the user communication quality is a problem to be solved urgently at present, and the improvement of the user communication experience under the mask wearing condition is needed.

Disclosure of Invention

In view of this, the present invention provides an audio signal compensation method, apparatus, device and medium, which can avoid the influence of mask wearing on the user's communication quality and improve the user's communication quality under the mask wearing condition. The specific scheme is as follows:

in a first aspect, the present application discloses an audio signal compensation method, including:

collecting a pressure value at the auricle;

judging whether the user wears the mask or not according to the pressure value;

and if the user wears the mask, audio signal compensation is carried out on the voice of the user.

Optionally, the performing audio signal compensation on the voice of the user includes:

determining a pressure grade corresponding to the pressure value;

and determining a pre-established target EQ curve corresponding to the pressure grade according to a mapping relation between the pre-established pressure grade and the EQ curve, and performing corresponding audio signal compensation on the voice of the user by using the target EQ curve.

Optionally, the process of constructing any EQ curve includes:

collecting voice in a standard state to obtain an original frequency response;

collecting voice under the state of wearing the mask to obtain sound loss frequency response;

and constructing and obtaining the EQ curve according to the difference between the original frequency response and the acoustic loss frequency response.

Optionally, the pressure value according to judge whether the user wears the gauze mask, include:

calculating the difference value between the pressure value and the historical pressure value acquired last time;

and judging whether the user wears the mask or not according to the size relation between the difference value and the pressure difference value threshold.

Optionally, the pressure value according to judge whether the user wears the gauze mask, include:

judging whether the user wears the mask or not according to the magnitude relation between the pressure value and the pressure threshold value;

before judging whether the user wears the gauze mask according to the magnitude relation of pressure value and pressure threshold, still include:

monitoring whether a threshold determination condition is currently met;

if the threshold value determination condition is met currently, it is determined that the ear device which collects the pressure value currently is worn at the auricle and the user does not wear the mask, then the pressure value at the current auricle is obtained, and the pressure value is determined as the pressure threshold value.

Optionally, the monitoring whether the threshold determination condition is currently met includes:

detecting whether the current ear equipment is worn at an auricle, if so, playing a preset prompt tone and timing, then judging whether the timing duration reaches the preset duration, and if so, judging that the threshold value determining condition is met currently; the preset prompt tone is used for prompting a user to don the mask;

or monitoring whether an instruction triggered by a user through a preset instruction triggering interface is received at present, and if the instruction is received, judging that the threshold value determining condition is met at present.

Optionally, before judging whether the user wears the mask according to the pressure value, the method further includes:

judging whether a user is currently wearing ear equipment for collecting the pressure value at the auricle;

if the user is judged to be wearing the ear equipment currently, the step of judging whether the user wears the mask according to the pressure value is prohibited to be started;

otherwise, starting the step of judging whether the user wears the mask according to the pressure value.

In a second aspect, the present application discloses an audio signal compensation apparatus, comprising:

the pressure value acquisition module is used for acquiring a pressure value at the auricle;

the judging module is used for judging whether the user wears the mask or not according to the pressure value;

and the compensation module is used for compensating the audio signal of the voice of the user if the judgment result of the judgment module indicates that the user wears the mask.

In a third aspect, the present application discloses an electronic device, comprising:

the pressure sensor is used for outputting a corresponding pressure value when sensing pressure;

a memory for storing a computer program;

a processor for executing the computer program to implement the aforementioned audio signal compensation method.

In a fourth aspect, the present application discloses a computer readable storage medium for storing a computer program; wherein the computer program realizes the aforementioned audio signal compensation method when being executed by a processor.

In the application, the pressure value at the auricle is acquired; then judging whether the user wears the mask or not according to the pressure value; and if the user wears the mask, audio signal compensation is carried out on the voice of the user. It is visible, through the pressure value of gathering, judge whether the user wears the gauze mask, if the user wears the gauze mask, then carry out audio signal compensation to user's pronunciation, from this, can intelligent compensation user's pronunciation under the user wears the gauze mask situation experiencing, because the gauze mask covers the acoustic loss who shelters from and cause with this compensation, reach and not wear the gauze mask the same, even more excellent conversation effect, avoided the gauze mask to wear the influence to user speech quality, user's conversation is experienced under the gauze mask condition of wearing has been improved.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.

Fig. 1 is a flowchart of an audio signal compensation method provided in the present application;

fig. 2 is a schematic wearing diagram of an earphone provided in the present application;

fig. 3 is a schematic view of another headset provided in the present application;

FIG. 4 is a schematic diagram of the relative position of a pressure sensor and an earphone provided by the present application;

fig. 5 is a flowchart illustrating the operation of an earphone according to the present application;

FIG. 6 is a flowchart of a specific audio signal compensation method provided in the present application;

fig. 7 is a schematic diagram of a relative position of a wireless headset and an ear according to the present application;

FIG. 8 is a flowchart of a specific audio signal compensation method provided in the present application;

fig. 9 is a schematic structural diagram of an audio signal compensation apparatus provided in the present application;

FIG. 10 is a block diagram of an electronic device provided herein;

fig. 11 is a schematic structural diagram of a pressure sensor provided in the present application.

Detailed Description

At present, the mask is increasingly a necessity of people, and the mask must be worn in public places such as outgoing travel and public transportation. However, wearing of the mask has certain influence on the communication quality of a user, for example, when the user wears the mask, the voice of the user of the earphone is attenuated and lost due to shielding of the mask, and the using effect and experience of a far end are directly influenced. In order to overcome the technical problem, the application provides an audio signal compensation method, which can avoid the influence of mask wearing on the conversation quality of a user and improve the conversation experience of the user under the mask wearing condition.

The embodiment of the application discloses an audio signal compensation method, and referring to fig. 1, the method may include the following steps:

step S11: pressure values at the pinna are collected.

In this embodiment, the pressure value at the auricle is collected first. Specifically, the pressure value at the pinna of the human ear may be collected by an ear device provided with a pressure sensor, which may be a wireless headset, a TWS headset, a hearing aid, or the like.

Step S12: and judging whether the user wears the mask or not according to the pressure value.

In this embodiment, after obtaining the pressure value, it is determined whether the user wears the mask according to the pressure value. It can be understood that, when the user wears the ear device and wears the gauze mask, the lanyard of the gauze mask can produce an effort to the auricle of the user, therefore, the ear device worn on the ear of the user can acquire the effort that the gauze mask brought through the pressure sensor that self set up to obtain corresponding pressure value, and above-mentioned pressure sensor can set up the optional position that can experience the pressure that the gauze mask lanyard extrudes the auricle and bring when the ear device is worn.

Furthermore, according to the ergonomic comfort level survey and the pressure sensor performance sensitivity test, the pressure sensor can be arranged at a position close to the auricle when the ear device is worn, for example, the concha cavity, the pressure sensor is exposed out of the ear device shell through the windowing, and meanwhile, a silk dustproof net can be arranged at the windowing position of the ear device shell, so that the dust protection effect is achieved, and meanwhile, the sensitivity of the pressure sensor can be improved. When wearing, pressure sensor can with the fine contact of auricle to pressure sensor responds to the auricle and receives the pressure that the string rope led to when wearing the gauze mask, and, wears the comfort level this moment and is higher, and pressure sensor sensitivity is also more accurate. For example, fig. 2 and fig. 3 are schematic views of wearing two kinds of earphones respectively, where fig. 3 specifically shows a position of the pressure sensor relative to the human ear when the earphones are worn, that is, the pressure sensor is in contact with the concha cavity when the earphones are worn, and correspondingly, fig. 4 specifically shows a schematic view of a relative position of the pressure sensor on the earphones.

In this embodiment, whether the user wears the gauze mask is judged according to the pressure value, can include: calculating the difference value between the pressure value and the historical pressure value acquired last time; and judging whether the user wears the mask or not according to the size relation between the difference value and the pressure difference value threshold. It can be understood that, by subtracting the collected pressure value from the last collected historical pressure value, it can be determined whether the user changes from not wearing the mask to wearing the mask during the period according to the magnitude relation between the difference value and the pressure difference value threshold. Besides, the pressure value can be compared with a preset pressure fixed value, and when the obtained pressure value is larger than the fixed value, the user can be judged to wear the ear equipment and wear the mask.

In this embodiment, before judging whether the user wears the mask according to the pressure value, the method may further include: judging whether a user is currently wearing ear equipment for collecting the pressure value at the auricle; if the user is judged to be wearing the ear equipment currently, the step of judging whether the user wears the mask according to the pressure value is prohibited to be started; otherwise, starting the step of judging whether the user wears the mask according to the pressure value. That is, whether the user is wearing the ear device or not is judged, if the user is wearing the ear device, the step of judging whether the user wears the mask or not according to the pressure value is prohibited from being started, and it can be understood that in the wearing process of the ear device, due to improper wearing, if the ear device is plugged into the ear, the pressure sensor may be subjected to the pressure from the auricle. Therefore, in order to prevent the false triggering of the mask wearing mode caused by such situations, in the embodiment, before judging whether the user wears the mask according to the pressure value, whether the user is currently wearing the ear device is judged, and then corresponding subsequent operations are performed according to the judgment result.

In this embodiment, specifically, the infrared sensing signal sent by the infrared sensor in the ear device and the acceleration sensing signal sent by the acceleration sensor may be obtained; if the sensing value corresponding to the infrared sensing signal is larger than a preset infrared threshold value and the sensing value corresponding to the acceleration sensor is larger than a preset acceleration threshold value, judging that the current user wears the ear equipment, and forbidding starting the step of judging whether the user wears the mask according to the pressure value; otherwise, starting the step of judging whether the user wears the mask according to the pressure value. It can be understood that when the infrared sensor detects a signal, the ear device can embody wearing action in the change of the signal in the auricle, and when the acceleration sensor detects a signal, the ear device can embody wearing action in the change of the acceleration in the wearing process, so that whether the user wears the ear device or not is comprehensively judged by combining the infrared sensor and the acceleration sensor, and the mask is prevented from being mistakenly worn by the user. The acceleration sensor may be a gravity sensor.

Step S13: and if the user wears the mask, audio signal compensation is carried out on the voice of the user.

In this embodiment, if it is determined that the user wears the mask, audio signal compensation is performed on the voice of the user. For example, if it is determined that the user wears the mask, the microphone receiving the user's voice may be compensated for the corresponding audio signal using a pre-constructed EQ (Equalizer) curve, specifically, the microphone may be compensated for the low and medium frequency audio signal, and the EQ curve may be constructed based on the difference between the audio signals of the worn mask and the audio signal of the unworn mask, which are obtained through a test in advance. That is, as shown in fig. 5, taking the earphone as an example, when the pressure sensor built in the earphone senses the pressure from the auricle caused by wearing the mask, the low-medium frequency response of the microphone of the earphone is actively compensated, and the low-medium frequency performance is ensured not to be influenced by wearing the mask. And if the user does not wear the mask, the user is considered to be in a normal state, and audio signal compensation is not carried out.

As can be seen from the above, the pressure value at the auricle is collected in the present embodiment; then judging whether the user wears the mask or not according to the pressure value; and if the user wears the mask, audio signal compensation is carried out on the voice of the user. It is visible, through the pressure value of gathering, judge whether the user wears the gauze mask, if the user wears the gauze mask, then carry out audio signal compensation to user's pronunciation, from this, can intelligent compensation user's pronunciation under the user wears the gauze mask situation experiencing, because the gauze mask covers the acoustic loss who shelters from and cause with this compensation, reach and not wear the gauze mask the same, even more excellent conversation effect, avoided the gauze mask to wear the influence to user speech quality, user's conversation is experienced under the gauze mask condition of wearing has been improved.

The embodiment of the present application discloses a specific audio signal compensation method, and as shown in fig. 6, the method may include the following steps:

step S21: pressure values at the pinna are collected.

Step S22: and judging whether the user wears the mask or not according to the pressure value.

Step S23: and if the user wears the mask, determining the pressure grade corresponding to the pressure value.

In this embodiment, if it is determined that the user wears the mask, the pressure level corresponding to the pressure value is determined according to the collected pressure value.

Step S24: and determining a pre-established target EQ curve corresponding to the pressure grade according to a mapping relation between the pre-established pressure grade and the EQ curve, and performing corresponding audio signal compensation on the voice of the user by using the target EQ curve.

In this embodiment, after the pressure level is determined, a pre-created target EQ curve corresponding to the current pressure level is determined according to a mapping relationship between the pre-created pressure level and the EQ curve, and the target EQ curve is used to perform corresponding audio signal compensation on the voice of the user. It can be understood that the different types of protective masks are different in material, different in the blocking degree of the speaking sound of people, different in the tightness of the corresponding mask hanging rope, different in the acting force on the ears of people, and normally correlated with the thickness of the mask protective face, such as a disposable mask and a KN95 mask. Therefore, in the embodiment, by constructing the mapping relationship between the pressure level and the EQ curve, different EQ curves are adopted to compensate for different pressures, so as to adapt to different types of protective masks.

In this embodiment, the process of constructing any EQ curve may include: collecting voice in a standard state to obtain an original frequency response; collecting voice under the state of wearing the mask to obtain sound loss frequency response; and constructing and obtaining the EQ curve according to the difference between the original frequency response and the acoustic loss frequency response. The standard state is a state that the user does not wear the mask, namely, the EQ curves corresponding to different pressures are constructed through the frequency response difference of collected voices under two states of not wearing the mask and wearing the mask. The construction process of the EQ curve may be obtained through testing during actual use by a user, or may be determined through simulation experiments.

For example, a standard microphone is used for collecting the playing sound of a simulation mouth in a simulation human head in a standard state at a target collecting position corresponding to the simulation human head so as to obtain an original frequency response; collecting the playing sound of a simulated mouth in the simulated human head in a state that the simulated human head is worn on a protective mask by utilizing the standard microphone at the target collecting position so as to obtain sound loss frequency response; constructing and obtaining the EQ curve according to the difference between the original frequency response and the acoustic loss frequency response; the target acquisition position is the position of a call microphone corresponding to the ear equipment relative to the simulated human head when the ear equipment is worn on the simulated human head; and the standard state is the state when the simulated head does not wear the protective mask and the decibels acquired at the mouth reference point corresponding to the simulated mouth are the standard sound pressure. That is, the simulated Mouth may be calibrated to a standard sound pressure, i.e., 94dBSPL, at the Mouth Reference Point (MRP) first to ensure that the simulated Mouth performance meets the requirements. Then, the ear device is worn on the simulated human ear of the simulated human head, and a position point where the call microphone corresponding to the ear device is projected to the simulated human head is identified as a target collection position, so as to determine a position of the microphone, for example, a relative position between the wireless headset and the ear as illustrated in fig. 7, it can be understood that the target collection position of the wireless headset is approximately at a position near the wireless headset. And then, a standard microphone is placed at the target acquisition position, and the standard microphone is used for acquiring the playing sound of the simulated mouth to obtain an original frequency response which is FR 0. And then wearing the protective mask meeting the epidemic situation protection requirement on the head of a simulated person, covering the simulated mouth with the mask meeting the wearing requirement, and collecting the playing sound of the simulated mouth by using the standard microphone again to obtain the sound loss frequency response which is FR 1. By comparison and calculation, FR1 has a slight difference in the medium and low frequencies compared with FR0, and shows that the mask slightly attenuates the medium and low frequencies of the simulated mouth. Namely, when the mask is worn, the low-frequency performance of the microphone of the earphone is slightly lost due to the fact that the mouth is covered by the mask, and the low-frequency performance of the microphone is slightly attenuated, and the difference is stable through multiple times of measurement verification. Finally, the difference is equivalent to an EQ curve to compensate the performance attenuation of the microphone caused by the low-frequency sound attenuation when the mouth of the microphone is covered by the mask when the mask is worn.

For the specific processes of step S21 and step S22, reference may be made to the corresponding contents disclosed in the foregoing embodiments, and details are not repeated here.

As can be seen from the above, in this embodiment, if it is determined that the user wears the mask, the pressure level corresponding to the pressure value is determined first; and then according to a mapping relation between the pre-constructed pressure level and the EQ curve, determining a pre-created target EQ curve corresponding to the pressure level, and performing corresponding audio signal compensation on the voice of the user by using the target EQ curve. From this, can carry out the accurate compensation of different audio signal's of intelligence to the gauze mask of different grade type to the protection gauze mask of adaptation different grade type has improved user's conversation under the gauze mask wearing conditions and has experienced.

The embodiment of the application discloses a specific audio signal compensation method, and referring to fig. 8, the method may include the following steps:

step S31: pressure values at the pinna are collected.

Step S32: it is monitored whether a threshold determination condition is currently satisfied.

In this embodiment, whether real-time supervision is present satisfies threshold value and confirms the condition, judges promptly whether the current state of ear equipment is fit for gathering and confirms the pressure threshold value, and also whether current ear equipment is in the condition of wearing the state and the user does not wear the gauze mask promptly. Wherein, the monitoring step can be performed at any time during the start-up operation of the ear device.

In this embodiment, the monitoring whether the current threshold determination condition is satisfied may include: detecting whether the current ear equipment is worn at an auricle, if so, playing a preset prompt tone and timing, then judging whether the timing duration reaches the preset duration, and if so, judging that the threshold value determining condition is met currently; the preset prompt tone is used for prompting a user to don the mask; or monitoring whether an instruction triggered by a user through a preset instruction triggering interface is received at present, and if the instruction is received, judging that the threshold value determining condition is met at present. It can be understood that, can wear the back through broadcast in this embodiment and predetermine the suggestion pronunciation, the suggestion user temporarily does not wear the gauze mask at present to with the time of predetermineeing the duration back as satisfying the threshold value and confirming the condition with the suggestion sound, in order to guarantee that the user has taken off the gauze mask, wherein, the detection that whether above-mentioned ear equipment was worn at auricle department can detect through infrared sensor etc.. In this embodiment, an instruction triggered by a user may also be acquired through a preset instruction triggering interface, and if the instruction is received, it is determined that a preset threshold determination condition is currently satisfied.

Step S33: if the threshold value determination condition is met currently, it is determined that the ear device which collects the pressure value currently is worn at the auricle and the user does not wear the mask, then the pressure value at the current auricle is obtained, and the pressure value is determined as the pressure threshold value.

In this embodiment, if the threshold determination condition is currently satisfied, it is determined that the ear device that acquires the pressure value at present is worn at the auricle and the user does not wear the mask, then the pressure value at the current auricle is obtained, and the pressure value is determined as the pressure threshold, that is, the pressure threshold obtained at this time is the single pressure that the user wears the ear device but does not wear the mask, and the ear brings the ear device.

Step S34: and judging whether the user wears the mask or not according to the magnitude relation between the pressure value and the pressure threshold value.

In this implementation, according to the big or small relation of pressure value and pressure threshold value, according to the single pressure value that pressure value and people's ear brought for ear equipment promptly, judge whether the user wears the gauze mask. Therefore, the pressure brought by the mask is avoided being mistaken for the situation that the user only wears the ear equipment but does not wear the mask by judging the pressure value and the pressure threshold value. In addition, the pressure value may be acquired by the pressure sensor in real time, or may be an average value of pressures acquired by the pressure sensor at consecutive preset times.

Step S35: and if the user wears the mask, audio signal compensation is carried out on the voice of the user.

For the specific processes of step S31 and step S35, reference may be made to the corresponding contents disclosed in the foregoing embodiments, and details are not repeated here.

As can be seen from the above, in the present embodiment, the threshold determination condition is monitored to be currently satisfied; if the threshold value determining condition is met currently, determining that the ear equipment which acquires the pressure value currently is worn on the auricle and the user does not wear a mask, then acquiring the pressure value at the current auricle and determining the pressure value as the pressure threshold value; and then judging whether the user wears the mask or not according to the magnitude relation between the pressure value and the pressure threshold value. Therefore, when the user is ensured to wear the ear device and does not wear the mask, the pressure value acquired by the pressure sensor is used as the pressure threshold value, whether the mask is worn by the user is judged based on the pressure threshold value subsequently, the influence of the human ear on the acting force of the ear device can be eliminated, and the accuracy of mode judgment is improved.

Accordingly, the embodiment of the present application further discloses an audio signal compensation apparatus, as shown in fig. 9, the apparatus includes:

the pressure value acquisition module 11 is used for acquiring a pressure value at an auricle;

the judging module 12 is used for judging whether the user wears the mask according to the pressure value;

and the compensation module 13 is configured to perform audio signal compensation on the voice of the user if the judgment result of the judgment module indicates that the user wears the mask.

As can be seen from the above, the pressure value at the auricle is collected in the present embodiment; then judging whether the user wears the mask or not according to the pressure value; and if the user wears the mask, audio signal compensation is carried out on the voice of the user. It is visible, through the pressure value of gathering, judge whether the user wears the gauze mask, if the user wears the gauze mask, then carry out audio signal compensation to user's pronunciation, from this, can intelligent compensation user's pronunciation under the user wears the gauze mask situation experiencing, because the gauze mask covers the acoustic loss who shelters from and cause with this compensation, reach and not wear the gauze mask the same, even more excellent conversation effect, avoided the gauze mask to wear the influence to user speech quality, user's conversation is experienced under the gauze mask condition of wearing has been improved.

In some specific embodiments, the compensation module 13 may specifically include:

the pressure grade determining unit is used for determining the pressure grade corresponding to the pressure value;

and the target EQ curve determining unit is used for determining a pre-established target EQ curve corresponding to the pressure level according to the mapping relation between the pre-established pressure level and the EQ curve, and performing corresponding audio signal compensation on the voice of the user by using the target EQ curve.

In some specific embodiments, the determining module 12 may specifically include:

the first judgment unit is used for calculating the difference value between the pressure value and the historical pressure value acquired last time; and judging whether the user wears the mask or not according to the size relation between the difference value and the pressure difference value threshold.

In some specific embodiments, the determining module 12 may specifically include:

and the second judging unit is used for judging whether the user wears the mask or not according to the magnitude relation between the pressure value and the pressure threshold value.

Correspondingly, the audio signal compensation device may specifically include:

a monitoring unit for monitoring whether a threshold determination condition is currently satisfied;

and the pressure threshold value determining unit is used for determining that the ear equipment which acquires the pressure value at present is worn at the auricle and the user does not wear the mask if the threshold value determining condition is met at present, then acquiring the pressure value at the current auricle and determining the pressure value as the pressure threshold value.

In some specific embodiments, the monitoring unit may specifically include:

the first monitoring unit is used for detecting whether the current ear equipment is worn at an auricle, playing a preset prompt tone and timing if the current ear equipment is detected to be worn at the auricle, then judging whether the timing duration reaches the preset duration, and if the timing duration reaches the preset duration, judging that the threshold value determining condition is met currently; the preset prompt tone is used for prompting a user to don the mask;

and the second monitoring unit is used for monitoring whether an instruction triggered by a preset instruction triggering interface is received by a user at present, and if the instruction is received, judging that the threshold value determining condition is met at present.

In some embodiments, the audio signal compensation apparatus may specifically include:

the wearing judgment unit is used for judging whether the user is wearing the ear equipment for collecting the pressure value at the auricle at present;

a start prohibiting unit, configured to prohibit starting the step of determining whether the user wears the mask according to the pressure value if the wearing determining unit determines that the user is currently wearing the ear device;

and the starting unit is used for starting the step of judging whether the user wears the mask according to the pressure value if the wearing judgment unit judges that the user does not wear the ear equipment currently.

Further, the embodiment of the present application also discloses an electronic device, which is shown in fig. 10, and the content in the drawing cannot be considered as any limitation to the application scope.

Fig. 10 is a schematic structural diagram of an electronic device according to an embodiment of the present application. The device may specifically include: at least one pressure sensor, at least one processor, and at least one memory.

In this embodiment, the pressure sensor may include: the pressure sensing surface is used for contacting with the auricle when the protective mask is worn so as to sense the pressure of the protective mask; the force sensor is used for generating corresponding electric signals under the action of the pressure transmitted by the pressure sensing surface through the rubber layer; the rubber layer is respectively connected with the pressure sensing surface and the force sensor in an interference fit manner; and the circuit board is connected with the force sensor and used for determining and outputting the corresponding pressure value according to the electric signal. The Circuit Board may be a PCB (Printed Circuit Board) or an FPC (Flexible Printed Circuit). For example, as shown in fig. 11, the pressure Sensor structure includes a pressure sensing surface, i.e., the upper surface (Top surface), the Force Sensor (Force Sensor) and the Rubber layer (Rubber) on the Force Sensor, as well as the lower surface (Bottom surface) and the circuit board in fig. 11; the Rubber is in interference fit with the pressure sensing surface and the Force Sensor respectively to ensure that the sensitivity of the Force Sensor can detect the pressure of the mask hanging rope on the auricle. When the pressure sensor is used, a reserved space is arranged on the ear shell, and the pressure sensor is in contact with the auricle of a human body through the Top surface.

Wherein the memory is used for storing a computer program, and the computer program is loaded and executed by the processor to implement the relevant steps in the audio signal compensation method disclosed in any of the foregoing embodiments. In addition, the memory is used as a carrier for resource storage, and may be a read-only memory, a random access memory, a magnetic disk, an optical disk, or the like, where the stored resources include an operating system, a computer program, data including a pressure value, and the like, and the storage manner may be a transient storage or a permanent storage.

Further, an embodiment of the present application also discloses a computer storage medium, in which computer executable instructions are stored, and when the computer executable instructions are loaded and executed by a processor, the steps of the audio signal compensation method disclosed in any of the foregoing embodiments are implemented.

The embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.

The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

The audio signal compensation method, apparatus, device and storage medium provided by the present invention are described in detail above, and the principle and implementation of the present invention are described herein by applying specific examples, and the description of the above examples is only used to help understanding the method and core idea of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.