CN113476041B - A method and system for testing speech perception ability of children using cochlear implants - Google Patents

Abstract

The invention provides a method and a system for testing speech perception capability of a child using an artificial cochlea, wherein the method comprises the following steps: obtaining a first type masking sound and a second type masking sound; obtaining first and second masking effects of first and second types of masking sound; obtaining energy and information masking effects; the energy masking effect is input into an energy masking speech perception capability assessment model to obtain a first energy masking speech perception capability assessment result; the information masking effect is input into an information masking speech perception capability assessment model to obtain a first information masking speech perception capability assessment result; obtaining a first level of a first energy masking speech perception capability assessment; obtaining a second level of the first information masking speech perception capability assessment; obtaining a first weight ratio; and obtaining a speech perception capability evaluation result of the first child. The method solves the technical problem that the prior art lacks a quantitative qualitative assessment means for auditory masking effect of the artificial cochlea by using children in the context of multi-person competition.

Description

A method and system for testing speech perception ability of children using cochlear implants

Technical field

The present invention relates to the technical field related to biological simulation, and specifically relates to a method and system for testing the speech perception ability of children using cochlear implants.

Background technique

Cochlear implant is an electronic device that uses an external speech processor to convert sound into a certain coded form of electrical signals. It directly excites the auditory nerve through an implanted electrode system to restore, improve and reconstruct the auditory function of deaf people. It is currently the most commonly used device. Successful biomedical engineering device.

The use of cochlear implants in deaf-mute children is a popular application target, and noisy scenes in daily environments require cochlear implants to have a good auditory masking effect in the context of multi-person conversations, that is, multi-person competition, so the evaluation of the auditory masking effect It is of great significance to improve the auditory masking effect in the context of multi-person competition. Currently known technologies basically simulate the living environment and evaluate through feedback from cochlear implant users. However, the information fed back by children is not comprehensive, and there are no qualitative and quantitative evaluation results.

However, in the process of implementing the technical solutions invented in the embodiments of the present application, the inventor of the present application discovered that the above technology has at least the following technical problems:

There is a technical problem in the existing technology that there is a lack of quantitative and qualitative evaluation methods for the auditory masking effect of children using cochlear implants in a multi-person competition context.

Contents of the invention

The embodiments of the present application provide a speech perception ability testing method and system for children using cochlear implants, which solves the lack of quantitative and qualitative evaluation of the auditory masking effect of children using cochlear implants in a multi-person competition context in the prior art. technical issues of the means. By acquiring multiple types of masking sounds to simulate multiple contexts, and then separately acquiring the masking effects of children using cochlear implants on multiple masking sounds, the masking separation model was further used to divide the masking effects into energy masking effects and information masking effects, and the energy The masking effect and the information masking effect are evaluated separately to obtain an evaluation level, and then the proportion of the energy masking effect and the information masking effect can be evaluated based on the weight ratio of the evaluation level. The evaluation results can be expressed by the evaluation levels and weight ratios of energy masking effect and information masking effect, achieving the technical effect of qualitatively and quantitatively evaluating the auditory masking effect of children using cochlear implants in a multi-person competition context.

In view of the above problems, embodiments of the present application provide a method and system for testing the speech perception ability of children using cochlear implants.

In a first aspect, embodiments of the present application provide a method for testing the speech perception ability of children using cochlear implants, wherein the method includes: obtaining a first type of masking sound and a second type of masking sound, wherein the first type The masking sound is different from the second type of masking sound; the first masking effect of the first type of masking sound is obtained; the second masking effect of the second type of masking sound is obtained; the first masking effect and the The second masking effect is input into the masking separation model to obtain the energy masking effect and the information masking effect; the energy masking effect is input into the energy masking speech perception ability evaluation model to obtain the first energy masking speech perception ability evaluation result; the information masking effect is Input the information masked speech perception ability evaluation model to obtain the first information masked speech perception ability evaluation result; obtain the first level of the first energy masked speech perception ability evaluation result; obtain the first information masked speech perception ability evaluation result The second level; according to the ratio of the first level and the second level, obtain a first weight ratio; according to the first weight ratio, the first energy masked speech perception ability evaluation result and the first information Mask the speech perception ability assessment results to obtain the first child's speech perception ability assessment results.

On the other hand, embodiments of the present application provide a speech perception ability testing system for children using cochlear implants, wherein the system includes: a first obtaining unit, the first obtaining unit is used to obtain the first type of masking sound and A second type of masking sound, wherein the first type of masking sound and the second type of masking sound are different; a second obtaining unit, the second obtaining unit is used to obtain the first masking of the first type of masking sound effect; a third obtaining unit, the third obtaining unit is used to obtain the second masking effect of the second type of masking sound; a fourth obtaining unit, the fourth obtaining unit is used to combine the first masking effect and The second masking effect is input into the masking separation model to obtain the energy masking effect and the information masking effect; the fifth obtaining unit is used to input the energy masking effect into the energy masking speech perception ability evaluation model to obtain the third An energy masked speech perception ability evaluation result; a sixth acquisition unit, the sixth acquisition unit is used to input the information masking effect into the information masking speech perception ability evaluation model to obtain the first information masking speech perception ability evaluation result; seventh Obtaining unit, the seventh obtaining unit obtains the first level of the first energy masked speech perception ability evaluation result; the eighth obtaining unit, the eighth obtaining unit obtains the first information masking speech perception ability evaluation result of the first level the second level; the ninth obtaining unit, the ninth obtaining unit obtains the first weight ratio according to the ratio of the first level and the second level; the tenth obtaining unit, the tenth obtaining unit obtains the first weight ratio according to the ratio of the first level and the second level; The first weight ratio, the first energy masked speech perception ability evaluation result and the first information masking speech perception ability evaluation result are used to obtain the speech perception ability evaluation result of the first child.

In a third aspect, embodiments of the present application provide a speech perception ability testing system for children using cochlear implants, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor The steps of the method described in any one of the first aspects are implemented when the program is executed.

One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

Due to the method of obtaining the first type of masking sound and the second type of masking sound, wherein the first type of masking sound and the second type of masking sound are different; obtaining the first masking effect of the first type of masking sound; obtaining The second masking effect of the second type of masking sound; input the first masking effect and the second masking effect into the masking separation model to obtain the energy masking effect and the information masking effect; input the energy masking effect into the energy masking Speech perception ability evaluation model, obtaining the first energy masking speech perception ability evaluation result; inputting the information masking effect into the information masking speech perception ability evaluation model, obtaining the first information masking speech perception ability evaluation result; obtaining the first energy masking The first level of the speech perception ability evaluation result; obtain the second level of the first information masking speech perception ability evaluation result; obtain the first weight ratio according to the ratio of the first level and the second level; according to the The first weight ratio, the first energy masked speech perception ability evaluation result and the first information masked speech perception ability evaluation result are the technical solutions for obtaining the speech perception ability evaluation results of the first child, by obtaining a variety of masked sounds Simulate the context of multi-person competition, and then separately obtain the masking effects of children using cochlear implants on various masking sounds. The masking separation model is further used to divide the masking effects into energy masking effects and information masking effects, and the energy masking effects and information masking effects are analyzed. The evaluation levels are obtained through separate evaluations, and then the proportion of the energy masking effect and the information masking effect can be evaluated based on the weight ratio of the evaluation levels. The evaluation results can be expressed by the evaluation levels and weight ratios of energy masking effect and information masking effect, achieving the technical effect of qualitatively and quantitatively evaluating the auditory masking effect of children using cochlear implants in a multi-person competition context.

The above description is only an overview of the technical solutions of the present application. In order to have a clearer understanding of the technical means of the present application, they can be implemented according to the content of the description, and in order to make the above and other purposes, features and advantages of the present application more obvious and understandable. , the specific implementation methods of the present application are specifically listed below.

Description of drawings

Figure 1 is a schematic flow chart of a method for testing the speech perception ability of children using cochlear implants according to an embodiment of the present application;

Figure 2 is a schematic structural diagram of a speech perception ability testing system for children using cochlear implants according to an embodiment of the present application;

FIG. 3 is a schematic structural diagram of an exemplary electronic device according to an embodiment of the present application.

Explanation of reference numerals: first obtaining unit 11, second obtaining unit 12, third obtaining unit 13, fourth obtaining unit 14, fifth obtaining unit 15, sixth obtaining unit 16, seventh obtaining unit 17, eighth obtaining unit Unit 18, ninth acquisition unit 19, tenth acquisition unit 20, electronic device 300, memory 301, processor 302, communication interface 303, bus architecture 304.

Detailed ways

The embodiments of the present application provide a speech perception ability testing method and system for children using cochlear implants, which solves the lack of quantitative and qualitative evaluation of the auditory masking effect of children using cochlear implants in a multi-person competition context in the prior art. technical issues of the means. By acquiring multiple types of masking sounds to simulate multiple contexts, and then separately acquiring the masking effects of children using cochlear implants on multiple masking sounds, the masking separation model was further used to divide the masking effects into energy masking effects and information masking effects, and the energy The masking effect and the information masking effect are evaluated separately to obtain an evaluation level, and then the proportion of the energy masking effect and the information masking effect can be evaluated based on the weight ratio of the evaluation level. The evaluation results can be expressed by the evaluation levels and weight ratios of energy masking effect and information masking effect, achieving the technical effect of qualitatively and quantitatively evaluating the auditory masking effect of children using cochlear implants in a multi-person competition context.

Application Overview

Cochlear implant is an electronic device that uses an external speech processor to convert sound into a certain coded form of electrical signals. It directly excites the auditory nerve through an implanted electrode system to restore, improve and reconstruct the auditory function of deaf people. It is currently the most commonly used device. Successful biomedical engineering device. The use of cochlear implants in deaf-mute children is a popular application target, and noisy scenes in daily environments require cochlear implants to have a good auditory masking effect in the context of multi-person conversations, that is, multi-person competition, so the evaluation of the auditory masking effect It is of great significance to improve the auditory masking effect in the context of multi-person competition. Currently known technologies basically simulate the living environment and evaluate through feedback from cochlear implant users. However, the information fed back by children is not comprehensive, and there are no qualitative and quantitative evaluation results. However, there are shortcomings in the existing technology. Technical issues regarding quantitative and qualitative assessment of auditory masking effects in children using cochlear implants in multi-person competition contexts.

In response to the above technical problems, the general idea of the technical solution provided by this application is as follows:

Embodiments of the present application provide a method for testing the speech perception ability of children using cochlear implants, wherein the method includes: obtaining a first type of masking sound and a second type of masking sound, wherein the first type of masking sound and the The second type of masking sound is different; the first masking effect of the first type of masking sound is obtained; the second masking effect of the second type of masking sound is obtained; the first masking effect and the second masking effect are obtained Input the masking separation model to obtain the energy masking effect and the information masking effect; input the energy masking effect into the energy masked speech perception ability evaluation model to obtain the first energy masking speech perception ability evaluation result; input the information masking effect into the information masking speech A perceptual ability evaluation model, obtains a first information masked speech perceptual ability evaluation result; obtains a first level of the first energy masked speech perceptual ability evaluation result; obtains a second level of the first information masked speech perceptual ability evaluation result; According to the ratio of the first level and the second level, a first weight ratio is obtained; according to the first weight ratio, the first energy masked speech perception ability evaluation result and the first information masked speech perception ability Assessment results, obtain the first child's speech perception ability assessment results.

After introducing the basic principles of the present application, various non-limiting implementations of the present application will be specifically introduced below in conjunction with the accompanying drawings.

Embodiment 1

As shown in Figure 1, an embodiment of the present application provides a method for testing the speech perception ability of children using cochlear implants, wherein the method includes:

S100: Obtain a first type of masking sound and a second type of masking sound, wherein the first type of masking sound and the second type of masking sound are different;

Specifically, noise masking refers to the phenomenon that a person's hearing threshold for a sound is increased due to the influence of noise. The sound causing this phenomenon is called masking noise, which is the masking sound defined here. The first type of masking sound and the second type of masking sound refer to masking noises that simulate different contexts in daily life, such as steady background noise, dynamic noise, spectrogram noise and multi-person speaking noise, etc.; so The first type of masking sound and the second type of masking sound cannot be the same type of noise.

S200: Obtain the first masking effect of the first type of masking sound;

S300: Obtain the second masking effect of the second type of masking sound;

Specifically, the first masking effect refers to the amount by which the hearing valve for another sound is raised due to the first type of masking sound; the second masking effect refers to the amount of increase in the listening valve to another sound due to the second type of masking sound. The sound causes the valve to rise in response to another sound. To give an example without limitation: the masking effect can be evaluated using the listening valve elevation value or the masking similarity. The other sound is preferably a fixed closed phrase. The unchanged target information ensures that the influencing factors of the masking effect are only different types of masking sounds.

S400: Input the first masking effect and the second masking effect into the masking separation model to obtain the energy masking effect and the information masking effect;

Specifically, the energy masking effect refers to the masking that occurs in the auditory periphery due to the superposition of the target signal and the masking signal on the spectrum; the information masking effect refers to the masking that occurs in the auditory center and is caused by the target signal and the masking signal. Masking caused by the similarity of signals in information patterns; the masking separation model refers to the method that can separate the first masking effect and the second masking effect into the energy masking effect and the information masking effect. The neural network model trains the masking separation model through multiple sets of the masking effect information, the corresponding energy masking effect identification information and the information masking effect identification information. When the output result of the masking separation model converges, Supervised learning is over. The energy masking effect and the information masking effect can be accurately separated from the first masking effect and the second masking effect through the masking separation model, and the impact of different influencing factors on the information masking effect can be further evaluated. Or the energy masking effect reduces the evaluation variables.

S500: Input the energy masking effect into the energy masking speech perception ability evaluation model to obtain the first energy masking speech perception ability evaluation result;

Specifically, the first energy masked speech perception ability evaluation result is a scoring result obtained by inputting the energy masking effect into the energy masked speech perception ability evaluation model for intelligent analysis, and the energy masked speech perception ability evaluation model is It is established based on the neural network model and has the characteristics of the neural network model. Among them, the artificial neural network is proposed and developed on the basis of modern neuroscience. It is an abstract mathematical model designed to reflect the structure and function of the human brain. The network is a computing model, which is composed of a large number of nodes (or neurons) connected to each other. Each node represents a specific output function called an excitation function. The connection between every two nodes represents a The weighted value of the connection signal is called a weight, which is equivalent to the memory of the artificial neural network. The output of the network is an expression of a logical strategy based on the connection method of the network. The energy established based on the neural network model The masked speech perception ability evaluation model can output accurate first energy masked speech perception ability evaluation result information, thereby possessing strong analysis and calculation capabilities and achieving accurate and efficient technical effects.

S600: Input the information masking effect into the information masking speech perception ability evaluation model to obtain the first information masking speech perception ability evaluation result;

Specifically, the first information masking speech perception ability evaluation result is a scoring result obtained by inputting the information masking effect into the information masking speech perception ability evaluation model for intelligent analysis, and the energy masking speech perception ability evaluation model is The same type of neural network model as the energy masked speech perception ability evaluation model. The information masking speech perception ability evaluation model established based on the neural network model can output accurate first information masked speech perception ability evaluation result information, so that It has strong analytical and computing capabilities and achieves accurate and efficient technical results.

S700: Obtain the first level of the first energy masked speech perception ability evaluation result;

S800: Obtain the second level of the first information masked speech perception ability evaluation result;

Specifically, the first level refers to the level of the energy masking effect of the first type of masking sound and the second type of masking sound on the target sound, which is evaluated from the first energy masking speech perception ability. The result can be obtained; the second level refers to the level of the information masking effect of the first type of masking sound and the second type of masking sound on the target sound, which is evaluated from the first information masking speech perception ability Results are available. The energy masking effect and the information masking effect of the two types of masking sounds can be quantified and evaluated respectively through the first level and the second level.

S900: Obtain the first weight ratio based on the ratio of the first level and the second level;

S1000: Obtain the speech perception ability evaluation result of the first child based on the first weight ratio, the first energy masked speech perception ability evaluation result and the first information masking speech perception ability evaluation result.

Specifically, the first weight ratio refers to calculating the ratio of the first level and the second level, and obtaining the proportion of the first level and the second level, which is preferably represented by a percentage, The first weight ratio can be used to understand the proportion of the energy masking effect and the information masking effect in the context of the first type of masking sound or the second masking sound, and further determine the impact on Research on the influencing factors of the larger masking effect can improve the performance of cochlear implants. Further, the masking effect is divided into the energy masking effect and the information masking effect for separate evaluation, and the first energy masking speech perception ability evaluation result and the first information masking speech perception ability evaluation result are obtained, and Calculate the first weight ratio by calculating the degree of influence of the two to obtain the proportion of the energy masking effect and the information masking in different contexts, and obtain the speech perception ability evaluation result of the first child. By evaluating the Assessment of speech perception abilities in children using cochlear implants provides certain directions for further research.

Further, based on the obtaining the first masking effect of the first type of masking sound, step S300 also includes:

S310: Obtain the language intelligibility of the first type of masking sound;

S320: Obtain target sound keyword information;

S330: Obtain masking similarity based on the first type of masking sound and the keyword information of the target sound;

S340: Obtain the first masking effect according to the language intelligibility and the masking similarity.

Specifically, the language intelligibility of the first type of masking sound refers to the language clarity of the first type of masking sound, that is, the degree of intelligibility. The higher the language intelligibility, the higher the language intelligibility of the first type of masking sound. The stronger the masking effect; the target sound keyword information refers to the keywords for understanding the target sound. For example, if a closed phrase is Zhang San eats rice for lunch, then the name, eat, rice, can be the key word of the target sound. Word information; the masking similarity refers to comparing the first type of masking sound with the target keyword information, and determining the masking similarity based on the number of target keywords repeated by the first type of masking sound. The greater the number, the higher the masking similarity, and the better the first masking effect. Characterizing the first masking effect by the language intelligibility and the masking similarity is beneficial to qualitative and quantitative processing of the masking effect. In addition, the second masking effect is also determined in the same way.

Further, the method also includes step S1100:

S1110: Obtain the first position information of the target sound;

S1120: Obtain the second position information of the masking sound;

S1130: Obtain the position difference information between the first position information and the second position information;

S1140: Construct a regression model of spatial position and the information masking effect based on the incident angle information, incident height information and incident distance information;

S1150: Obtain the first spatial position influence parameter according to the position difference information and the regression model;

S1160: Modify the first information-masked speech perception ability evaluation result according to the first spatial position influence parameter, and obtain the second information-masked speech perception ability evaluation result.

Specifically, the first position information of the target sound refers to the sounding position information of the target sound; the second position information of the masking sound refers to the sounding position information of the masking sound; the first The position difference information between the position information and the second position information refers to the distance between the sounding position information of the target sound and the sounding position information of the masking sound; the incident angle, the incident height information, the The optional determination method of the incident distance is: use a sound sensor to capture the horizontal propagation time and vertical propagation time of the target sound and the masking sound, determine the horizontal incidence distance and vertical incidence distance based on the propagation time, and obtain it according to the Pythagorean theorem. The incident distance is the hypotenuse, and then the incident angle and incident height are determined; further, based on the impact relationship of the incident angle, the incident height information, and the incident distance on the information masking effect, a The influence relationship between the regression model of the spatial position and the information masking effect is determined according to the specific application example, and is not limited here; further, based on the influence of the position difference information on the information masking effect, combined with the Using the above regression model, the correlation between the spatial position and the information masking effect is obtained, which is the influence parameter of the first spatial position. Generally speaking, when other variables are constant, the smaller the position difference, the smaller the position difference. The smaller the influence parameter of a spatial position, the specific value is not limited here. The first information-masked speech perception ability evaluation result is corrected through the first spatial position influence parameter. The correction method is preferably as follows: the greater the first spatial position influence parameter, the greater the first information-masked speech perception ability evaluation result. The higher the level corresponding to the result, the corrected result is the second information masked speech perception ability evaluation result. By adding the influence of the first spatial location on the information masking effect to the first information masking speech perception ability evaluation result, the obtained second information masking speech perception ability evaluation result is more comprehensive because of the obtained information. So the evaluation results are more accurate.

Furthermore, based on the obtaining the first position information of the target sound and the second position information of the masking sound, step S1140 also includes:

S1141: Obtain the first incident angle information, the first incident height information and the first incident distance information of the target sound;

S1142: Obtain the first position information based on the first incident angle information, first incident height information and first incident distance information;

S1143: Obtain the second incident angle information, the second incident height information and the second incident distance information of the masking sound;

S1144: Obtain the second position information according to the second incident angle information, second incident height information and second incident distance information.

Specifically, according to the first incident angle information, the first incident height information and the first incident distance information of the target sound, the first incident angle can be an acute angle, and the first incident height can be a right-angled side. , the first incident distance is the hypotenuse, determine the horizontal distance between the target sound and the child using the cochlear implant, and further, obtain the spatial position information of the target sound, which is the first position information. The second position information determination method of the masking sound is preferably the same as the first position information determination method. By quantifying the positions of the target sound and the masking sound through the first position information and the second position information, the information masking effect can be evaluated qualitatively and quantitatively.

Further, the method also includes S1200:

S1210: Obtain the first time information when the target sound reaches both ears;

S1220: Obtain the second time information when the masking sound reaches both ears;

S1230: Obtain the time difference information between the first time information and the second time information;

S1240: Obtain the first intensity information of the target sound reaching both ears;

S1250: Obtain the second intensity information of the masking sound reaching both ears;

S1260: Obtain intensity difference information between the first intensity information and the second intensity information;

S1270: Obtain the first intensity difference influence parameter according to the intensity difference information;

S1280: Modify the first information-masked speech perception ability evaluation result according to the first intensity difference influence parameter, and obtain a third information-masked speech perception ability evaluation result.

Specifically, the first time information refers to recording the propagation time of the target sound reaching both ears. Preferably, a sound sensor can be used to record the propagation time; the second time information refers to recording the time the masking sound reaches both ears. The propagation time of the ears is determined in the same way as the first time information; the first intensity information refers to the sound intensity when the target sound reaches both ears, and the second intensity information refers to the masking sound The intensity of sound when it reaches both ears, preferably characterized in decibels, is determined using a sound sensor. Further, the difference between the first intensity information and the second intensity information is calculated to obtain the intensity difference information. Furthermore, the greater the intensity difference, the more obvious the influence on the masking effect. Based on this relationship, the first intensity difference influence parameter is obtained. Furthermore, the first information-masked speech perception ability evaluation result is modified according to the first intensity difference influence parameter to obtain the third information-masked speech perception ability evaluation result. The evaluation influencing factors are supplemented to achieve the technical effect of making the evaluation results more accurate.

Further, the method also includes step S1300:

S1310: Obtain the quantity information of the masking sound;

S1320: Perform vector conversion on the quantity information of the masking sound, and obtain the vector module corresponding to the quantity information;

S1330: Obtain the first quantity influence parameter according to the vector module;

S1340: Modify the first information-masked speech perception ability evaluation result according to the first quantitative influence parameter to obtain a fourth information-masked speech perception ability evaluation result.

Specifically, the quantity information of the masking sound refers to the number of utterances of the masking sound, and the number of different decibel intervals can optionally be used to determine the masking sound; the vector module corresponding to the quantity information refers to the The quantity information of the masking sound is identified by a vector, the quantity corresponds to the vector module, and the direction of the masking sound corresponds to the direction of the vector; the first quantity influence parameter is established according to the influence of the quantity of the masking sound on the information masking effect. , Generally speaking, the larger the vector module is, the more obvious the information masking effect will be. Further, the first information masked speech perception ability evaluation result is modified according to the first quantitative influence parameter to obtain the fourth information masked speech perception ability evaluation result, and the masked speech perception ability is modified by the first quantitative influence parameter. The influence of the quantity on the information masking effect is added to the first information masking speech perception ability evaluation result, making the fourth information masking speech perception ability evaluation result more accurate and comprehensive.

Further, based on the input of the energy masking effect into the energy masking speech perception ability evaluation model, the first energy masking speech perception ability evaluation result is obtained. Steps S500 and S600 also include:

S510: Use the energy masking effect in historical data as a training data set to train the neural network model until the model reaches a convergence state, and build the energy masking speech perception ability evaluation model;

S520: Input the energy masking effect as input information into the energy masking speech perception ability evaluation model;

S530: Obtain the output information of the energy masked speech perception ability evaluation model, where the output information includes the first energy masked speech perception ability evaluation result.

Specifically, the energy masked speech perception ability evaluation model is also a neural network model. The neural network model is a neural network model in machine learning. It reflects many basic characteristics of human brain functions and is a highly complex non-linear model. Linear dynamic learning systems. Among them, it can continuously perform self-training learning based on training data, and use the energy masking effect in historical data as a training data set to train the neural network model. The energy masked speech perception ability evaluation model continuously corrects itself. When the output information of the first intelligent evaluation model reaches a predetermined accuracy/convergence state, the supervised learning process ends. By performing data training on the energy masked speech perception ability evaluation model, the input data processed by the energy masked speech perception ability evaluation model is more accurate, thereby making the output information of the first energy masked speech perception ability evaluation result more accurate. , achieving the technical effect of accurately obtaining data information and improving the intelligence of evaluation results. In addition, the information masking speech perception ability evaluation model is preferably constructed based on the same principle.

In summary, the speech perception ability testing method and system for children using cochlear implants provided by the embodiments of the present application have the following technical effects:

1. Due to the method of obtaining the first type of masking sound and the second type of masking sound, wherein the first type of masking sound and the second type of masking sound are different; obtaining the first masking effect of the first type of masking sound ; Obtain the second masking effect of the second type of masking sound; input the first masking effect and the second masking effect into the masking separation model to obtain the energy masking effect and the information masking effect; input the energy masking effect An energy masked speech perception ability evaluation model is used to obtain a first energy masked speech perception ability evaluation result; the information masking effect is input into the information masking speech perception ability evaluation model to obtain a first information masking speech perception ability evaluation result; and the first information masking speech perception ability evaluation result is obtained; The first level of the energy masking speech perception ability evaluation result; obtaining the second level of the first information masking speech perception ability evaluation result; obtaining a first weight ratio based on the ratio of the first level and the second level; According to the first weight ratio, the first energy masked speech perception ability evaluation result and the first information masked speech perception ability evaluation result, the technical solution for obtaining the speech perception ability evaluation result of the first child is to obtain a variety of The masking sound simulates a multi-person competition context, and then the masking effects of children with cochlear implants on various masking sounds are obtained separately. The masking separation model is further used to divide the masking effect into energy masking effect and information masking effect, and the energy masking effect and information The masking effect is evaluated separately to obtain an evaluation grade, and then the proportion of the energy masking effect and the information masking effect can be evaluated based on the weight ratio of the evaluation grade. The evaluation results can be expressed by the evaluation levels and weight ratios of energy masking effect and information masking effect, achieving the technical effect of qualitatively and quantitatively evaluating the auditory masking effect of children using cochlear implants in a multi-person competition context.

2. Add the influence of the first spatial position influence parameter, the first intensity difference influence parameter, and the first quantity influence parameter on the information masking effect into the first information masking speech perception ability evaluation result. , making the masked speech perception ability assessment results more accurate and comprehensive.

Embodiment 2

Based on the same inventive concept as the speech perception ability testing method of children using cochlear implants in the previous embodiment, as shown in Figure 2, embodiments of the present application provide a speech perception ability testing system for children using cochlear implants, wherein, The system includes:

A first obtaining unit 11, the first obtaining unit 11 is used to obtain a first type of masking sound and a second type of masking sound, wherein the first type of masking sound and the second type of masking sound are different;

a second obtaining unit 12, the second obtaining unit 12 is used to obtain the first masking effect of the first type of masking sound;

A third obtaining unit 13, the third obtaining unit 13 is used to obtain the second masking effect of the second type of masking sound;

The fourth obtaining unit 14 is configured to input the first masking effect and the second masking effect into the masking separation model to obtain the energy masking effect and the information masking effect;

The fifth obtaining unit 15 is configured to input the energy masking effect into the energy masking speech perception ability evaluation model to obtain the first energy masking speech perception ability evaluation result;

The sixth obtaining unit 16 is configured to input the information masking effect into the information masking speech perception ability evaluation model and obtain the first information masking speech perception ability evaluation result;

A seventh obtaining unit 17, the seventh obtaining unit 17 obtains the first level of the first energy masked speech perception ability evaluation result;

An eighth obtaining unit 18, the eighth obtaining unit 18 obtains the second level of the first information masked speech perception ability evaluation result;

The ninth obtaining unit 19 obtains the first weight ratio according to the ratio of the first level and the second level;

The tenth obtaining unit 20 obtains the first child's score based on the first weight ratio, the first energy masked speech perception ability evaluation result, and the first information masked speech perception ability evaluation result. Speech perception ability assessment results.

Further, the system also includes:

An eleventh obtaining unit, the eleventh obtaining unit is used to obtain the language intelligibility of the first type of masking sound;

A twelfth obtaining unit, the twelfth obtaining unit is used to obtain target sound keyword information;

A thirteenth obtaining unit, the thirteenth obtaining unit is used to obtain masking similarity based on the first type of masking sound and the keyword information of the target sound;

A fourteenth obtaining unit, the fourteenth obtaining unit is configured to obtain the first masking effect according to the language intelligibility and the masking similarity.

Further, the system also includes:

A fifteenth obtaining unit, the fifteenth obtaining unit is used to obtain the first position information of the target sound;

A sixteenth obtaining unit, the sixteenth obtaining unit obtains the second position information of the masking sound;

A seventeenth obtaining unit, the seventeenth obtaining unit is used to obtain the position difference information of the first position information and the second position information;

An eighteenth obtaining unit, the eighteenth obtaining unit is used to construct a regression model of the spatial position and the information masking effect based on the incident angle information, the incident height information and the incident distance information;

A nineteenth obtaining unit, the nineteenth obtaining unit is used to obtain the first spatial position influence parameter according to the position difference information and the regression model;

The twentieth obtaining unit is configured to modify the first information masked speech perception ability evaluation result according to the first spatial position influence parameter, and obtain the second information masked speech perception ability evaluation result. .

Further, the system also includes:

The twenty-first obtaining unit, the twenty-first obtaining unit is used to obtain the first incident angle information, the first incident height information and the first incident distance information of the target sound;

A twenty-second obtaining unit, the twenty-second obtaining unit is configured to obtain the first position information according to the first incident angle information, the first incident height information and the first incident distance information;

A twenty-third obtaining unit, the twenty-third obtaining unit is used to obtain the second incident angle information, the second incident height information and the second incident distance information of the masking sound;

The twenty-fourth obtaining unit is configured to obtain the second position information according to the second incident angle information, the second incident height information and the second incident distance information.

Further, the system also includes:

The twenty-fifth obtaining unit is used to obtain the first time information of the target sound reaching both ears;

A twenty-sixth obtaining unit, the twenty-sixth obtaining unit is used to obtain the second time information when the masking sound reaches both ears;

The twenty-seventh obtaining unit, the twenty-seventh obtaining unit is used to obtain the time difference information of the first time information and the second time information;

The twenty-eighth obtaining unit, the twenty-eighth obtaining unit is used to obtain the first intensity information of the target sound reaching both ears;

The twenty-ninth obtaining unit is used to obtain the second intensity information of the masking sound reaching both ears;

The thirtieth obtaining unit, the thirtieth obtaining unit is used to obtain the intensity difference information of the first intensity information and the second intensity information;

The thirty-first obtaining unit, the thirty-first obtaining unit is configured to obtain the first intensity difference influence parameter according to the intensity difference information;

The thirty-second obtaining unit is configured to modify the evaluation result of the first information-masked speech perception ability according to the first intensity difference influence parameter, and obtain the third information-masked speech perception ability. evaluation result.

Further, the system also includes:

A thirty-third obtaining unit, the thirty-third obtaining unit is used to obtain the quantity information of the masking sound;

The thirty-fourth obtaining unit, the thirty-fourth obtaining unit is used to perform vector conversion on the quantity information of the masking sound, and obtain the vector module corresponding to the quantity information;

The thirty-fifth obtaining unit, the thirty-fifth obtaining unit is used to obtain the first quantity influence parameter according to the vector module;

A first correction unit, the first correction unit is configured to correct the first information-masking speech perception ability evaluation result according to the first quantitative influence parameter, and obtain a fourth information-masking speech perception ability evaluation result.

Further, the system also includes:

A first building unit, the first building unit is used to train the neural network model using the energy masking effect in historical data as a training data set until the model reaches a convergence state, and build the energy masking speech perception ability evaluation model;

A first input unit configured to input the energy masking effect as input information into the energy masking speech perception ability assessment model;

A first output unit, the first output unit is used to obtain output information of the energy masked speech perception ability evaluation model, where the output information includes the first energy masked speech perception ability evaluation result.

Example electronic device

The electronic device according to the embodiment of the present application will be described below with reference to Figure 3.

Based on the same inventive concept as the speech perception ability testing method of children using cochlear implants in the previous embodiment, embodiments of the present application also provide a speech perception ability testing system for children using cochlear implants, including: a processor, The processor is coupled to a memory, and the memory is used to store a program. When the program is executed by the processor, the system is configured to perform the method described in any one of the first aspects.

The electronic device 300 includes: a processor 302, a communication interface 303, and a memory 301. Optionally, the electronic device 300 may also include a bus architecture 304. Among them, the communication interface 303, the processor 302 and the memory 301 can be connected to each other through a bus architecture 304; the bus architecture 304 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (extended industry Standard architecture, referred to as PCI) bus. EISA) bus, etc. The bus architecture 304 can be divided into an address bus, a data bus, a control bus, etc. For ease of presentation, only one thick line is used in Figure 3, but it does not mean that there is only one bus or one type of bus.

The processor 302 may be a CPU, a microprocessor, an ASIC, or one or more integrated circuits used to control the execution of the program of the present application.

Communication interface 303 uses any device such as a transceiver to communicate with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), wired Access network, etc.

Memory 301 may be ROM or other types of static storage devices that can store static information and instructions, RAM or other types of dynamic storage devices that can store information and instructions, or it may be electrically erasable programmable read-only memory (electrically erasable programmable). read-only memory (EEPROM), compactdisc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures that can be accessed by a computer, without limitation. The memory may exist independently and be connected to the processor through the bus architecture 304. Memory can also be integrated with the processor.

Among them, the memory 301 is used to store computer execution instructions for executing the solution of the present application, and the processor 302 controls the execution. The processor 302 is configured to execute computer execution instructions stored in the memory 301, thereby implementing the speech perception ability testing method of children using cochlear implants provided in the above embodiments of the present application.

Optionally, the computer-executed instructions in the embodiments of the present application may also be called application codes, which are not specifically limited in the embodiments of the present application.

Embodiments of the present application provide a method for testing the speech perception ability of children using cochlear implants, wherein the method includes: obtaining a first type of masking sound and a second type of masking sound, wherein the first type of masking sound and the The second type of masking sound is different; the first masking effect of the first type of masking sound is obtained; the second masking effect of the second type of masking sound is obtained; the first masking effect and the second masking effect are obtained Input the masking separation model to obtain the energy masking effect and the information masking effect; input the energy masking effect into the energy masked speech perception ability evaluation model to obtain the first energy masking speech perception ability evaluation result; input the information masking effect into the information masking speech A perceptual ability evaluation model, obtains a first information masked speech perceptual ability evaluation result; obtains a first level of the first energy masked speech perceptual ability evaluation result; obtains a second level of the first information masked speech perceptual ability evaluation result; According to the ratio of the first level and the second level, a first weight ratio is obtained; according to the first weight ratio, the first energy masked speech perception ability evaluation result and the first information masked speech perception ability Evaluation results, the technical solution to obtain the first child's speech perception ability evaluation results, simulates a multi-person competition context by obtaining multiple masking sounds, and then separately obtains the masking effects of children using cochlear implants on multiple masking sounds, and further utilizes masking separation The model divides the masking effect into energy masking effect and information masking effect, and evaluates the energy masking effect and information masking effect respectively to obtain an evaluation level. Then based on the weight ratio of the evaluation level, the proportion of the energy masking effect and the information masking effect can be evaluated. The evaluation results can be expressed by the evaluation levels and weight ratios of energy masking effect and information masking effect, achieving the technical effect of qualitatively and quantitatively evaluating the auditory masking effect of children using cochlear implants in a multi-person competition context.

Persons of ordinary skill in the art can understand that the first, second, and other numerical numbers involved in this application are only for convenience of description, and are not used to limit the scope of the embodiments of this application, nor do they indicate a sequence. "And/or" describes the relationship between related objects, indicating that there can be three relationships. For example, A and/or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the related objects are in an "or" relationship. "At least one" means one or more. At least two means two or more. "At least one", "any one" or similar expressions refer to any combination of these items, including any combination of single items (items) or plural items (items). For example, at least one of a, b, or c can mean: a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, c can be single or Multiple.

In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, e.g., the computer instructions may be transferred from a website, computer, server, or data center Transmission to another website, computer, server or data center by wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center integrated with one or more available media. The available media may be magnetic media (eg, floppy disk, hard disk, magnetic tape), optical media (eg, DVD), or semiconductor media (eg, solid state disk (Solid State Disk, SSD)), etc.

The various illustrative logic units and circuits described in the embodiments of this application can be implemented by a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, Discrete gate or transistor logic, discrete hardware components, or any combination of the foregoing are designed to implement or operate the functions described. The general-purpose processor may be a microprocessor. Alternatively, the general-purpose processor may also be any conventional processor, controller, microcontroller or state machine. A processor may also be implemented as a combination of computing devices, such as a digital signal processor and a microprocessor, a plurality of microprocessors, one or more microprocessors combined with a digital signal processor core, or any other similar configuration. accomplish.

The steps of the method or algorithm described in the embodiments of this application can be directly embedded in hardware, a software unit executed by a processor, or a combination of the two. The software unit may be stored in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, register, hard disk, removable disk, CD-ROM or any other form of storage medium in the art. For example, the storage medium can be connected to the processor, so that the processor can read information from the storage medium and can store and write information to the storage medium. Optionally, the storage medium can also be integrated into the processor. The processor and the storage medium can be installed in the ASIC, and the ASIC can be installed in the terminal. Optionally, the processor and the storage medium may also be provided in different components in the terminal. These computer program instructions may also be loaded onto a computer or other programmable data processing device, causing a series of operating steps to be performed on the computer or other programmable device to produce computer-implemented processing, thereby executing on the computer or other programmable device. Instructions provide steps for implementing the functions specified in a process or processes of a flowchart diagram and/or a block or blocks of a block diagram.

Although the present application has been described in conjunction with specific features and embodiments thereof, it will be apparent that various modifications and combinations may be made without departing from the spirit and scope of the application. Accordingly, the specification and drawings are intended to be merely illustrative of the application as defined by the appended claims and are to be construed to cover any and all modifications, variations, combinations or equivalents within the scope of the application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. In this way, if these modifications and variations of the present application fall within the scope of the claims of the present application and their technical equivalents, the present application is intended to include these modifications and variations.

Claims (9)

1. A method for testing the speech perception ability of children using cochlear implants, wherein the method includes: Obtaining a first type of masking sound and a second type of masking sound, wherein the first type of masking sound and the second type of masking sound are different; Obtain a first masking effect of the first type of masking sound; Obtain a second masking effect of the second type of masking sound; Input the first masking effect and the second masking effect into the masking separation model to obtain the energy masking effect and the information masking effect; Input the energy masking effect into the energy masking speech perception ability evaluation model to obtain the first energy masking speech perception ability evaluation result; Input the information masking effect into the information masking speech perception ability evaluation model to obtain the first information masking speech perception ability evaluation result; Obtaining a first level of the first energy masking speech perception ability evaluation result, the first level refers to the degree of masking of the energy masking effect of the first type of masking sound and the second type of masking sound on the target sound. Level, obtained from the first energy masked speech perception ability assessment result; Obtain a second level of the first information masking speech perception ability evaluation result, the second level refers to the degree of masking of the information masking effect of the first type of masking sound and the second type of masking sound on the target sound Level, obtained from the first information masked speech perception ability assessment result; Obtain a first weight ratio according to the ratio of the first level and the second level; According to the first weight ratio, the first energy masked speech perception ability evaluation result and the first information masking speech perception ability evaluation result, the speech perception ability evaluation result of the first child is obtained. 2. The method of claim 1, wherein obtaining the first masking effect of the first type of masking sound includes: Obtain the language intelligibility of the first type of masking sound; Obtain target sound keyword information; Obtain masking similarity based on the first type of masking sound and the keyword information of the target sound; The first masking effect is obtained based on the language intelligibility and the masking similarity. 3. The method of claim 1, wherein the method includes: Obtain the first position information of the target sound; Obtain the second position information of the masking sound; Obtain position difference information between the first position information and the second position information; Construct a regression model of spatial position and the information masking effect based on the incident angle information, incident height information and incident distance information; According to the position difference information and the regression model, a first spatial position influence parameter is obtained; According to the first spatial position influencing parameter, the first information-masked speech perception ability evaluation result is modified to obtain a second information-masked speech perception ability evaluation result. 4. The method of claim 3, wherein obtaining the first position information of the target sound and obtaining the second position information of the masking sound includes: Obtain first incident angle information, first incident height information and first incident distance information of the target sound; Obtain the first position information according to the first incident angle information, first incident height information and first incident distance information; Obtain second incident angle information, second incident height information, and second incident distance information of the masking sound; The second position information is obtained according to the second incident angle information, second incident height information and second incident distance information. 5. The method of claim 1, wherein the method includes: Obtain the first time information when the target sound reaches both ears; Obtain the second time information when the masking sound reaches both ears; Obtain time difference information between the first time information and the second time information; Obtain the first intensity information of the target sound reaching both ears; Obtain the second intensity information of the masking sound reaching both ears; Obtain intensity difference information between the first intensity information and the second intensity information; According to the intensity difference information, a first intensity difference influence parameter is obtained; According to the first intensity difference influence parameter, the first information-masked speech perception ability evaluation result is modified to obtain a third information-masked speech perception ability evaluation result. 6. The method of claim 1, wherein the method includes: Obtain the quantity information of the masking sound; Perform vector conversion on the quantity information of the masking sound to obtain the vector module corresponding to the quantity information; According to the vector module, a first quantity influencing parameter is obtained; According to the first quantitative influence parameter, the first information-masked speech perception ability evaluation result is modified to obtain a fourth information-masked speech perception ability evaluation result. 7. The method of claim 1, wherein said inputting the energy masking effect into an energy masked speech perception ability evaluation model to obtain a first energy masking speech perception ability evaluation result includes: Use the energy masking effect in historical data as a training data set to train the neural network model until the model reaches a convergence state, and construct the energy masked speech perception ability evaluation model; Enter the energy masking effect as input information into the energy masking speech perception ability assessment model; Output information of the energy-masked speech perception ability evaluation model is obtained, and the output information includes the first energy-masked speech perception ability evaluation result. 8. A speech perception ability testing system for children using cochlear implants, wherein the system includes: a first obtaining unit, the first obtaining unit is used to obtain a first type of masking sound and a second type of masking sound, wherein the first type of masking sound and the second type of masking sound are different; a second obtaining unit, the second obtaining unit being used to obtain the first masking effect of the first type of masking sound; a third obtaining unit, the third obtaining unit is used to obtain the second masking effect of the second type of masking sound; A fourth obtaining unit, the fourth obtaining unit is used to input the first masking effect and the second masking effect into the masking separation model to obtain the energy masking effect and the information masking effect; A fifth obtaining unit, the fifth obtaining unit is used to input the energy masking effect into the energy masking speech perception ability evaluation model, and obtain the first energy masking speech perception ability evaluation result; A sixth obtaining unit, the sixth obtaining unit is used to input the information masking effect into the information masking speech perception ability evaluation model, and obtain the first information masking speech perception ability evaluation result; A seventh obtaining unit, the seventh obtaining unit obtains a first level of the first energy masking speech perception ability evaluation result, the first level refers to the first type of masking sound and the second type of masking The level of the energy masking effect of the sound on the target sound is obtained from the evaluation result of the first energy masking speech perception ability; An eighth obtaining unit, the eighth obtaining unit obtains a second level of the first information masking speech perception ability evaluation result, the second level refers to the first type of masking sound and the second type of masking The level of the information masking effect of the sound on the target sound is obtained from the evaluation results of the first information masking speech perception ability; A ninth obtaining unit, the ninth obtaining unit obtains a first weight ratio based on the ratio of the first level and the second level; A tenth obtaining unit, the tenth obtaining unit obtains the speech perception of the first child based on the first weight ratio, the first energy masked speech perception ability evaluation result and the first information masking speech perception ability evaluation result. Competency assessment results. 9. A smart pharmacy service evaluation system, comprising: a processor, the processor is coupled to a memory, the memory is used to store a program, and when the program is executed by the processor, the system is configured to execute as claimed in the claim The method described in any one of 1 to 7.