Audio control methods and systems for stage performances

Abstract

This application relates to the fields of artificial intelligence and stage technology, and provides an audio control method and system for stage performances. The method includes: collecting real-time environmental parameters of an open-air stage, including at least two of rainfall, wind speed, ambient noise, temperature and humidity, and audience noise; inputting the real-time environmental parameters into a preset dynamic interaction model, and outputting the disturbance amount of each frequency band; the dynamic interaction model is a nonlinear model trained through multi-factor combination samples, and the multi-factor combination includes the actual disturbance amount of each frequency band under different combinations of environmental parameters; calculating the compensation gain of each frequency band based on the disturbance amount of each frequency band; and compensating each frequency band of the stage performance audio signal to be output based on the compensation gain to obtain a compensated audio signal. This invention enables the system to adapt to environmental changes through learning and feedback, and to more accurately model complex interaction relationships, ensuring that key audio content remains clearly identifiable regardless of how environmental factors are superimposed.

Description

Technical Field

[0001] This application relates to the fields of artificial intelligence and stage technology, and in particular to an audio control method and system for stage performances. Background Technology

[0002] In open-air stage performances, environmental factors can mask crucial audio content such as vocals and instrument details. To mitigate the impact of environmental factors, existing methods calculate the total gain for each frequency band based on preset gains and weights for each environmental factor, and then use this total gain to compensate for the volume of each frequency band. However, in real-world scenarios, the effects of different environmental factors on different frequency bands can interfere with each other, and existing methods cannot accurately model this complex interaction, resulting in poor compensation effects. Furthermore, increased humidity during rainy days alters sound wave propagation, and the increased absorption of high-frequency sound waves by moisture shifts the frequency response characteristics of the audio system, leading to a deterioration in performance quality. Summary of the Invention

[0003] In view of the above-mentioned technical problems, the purpose of this application is to provide an audio control method and system for stage performances, which aims to solve at least one of the above-mentioned technical problems.

[0004] In a first aspect, embodiments of this application provide an audio control method for stage performances, the method comprising:

[0005] Real-time environmental parameters of the open-air stage are collected, including at least two of the following: rainfall, wind speed, ambient noise, temperature and humidity, and audience noise.

[0006] The real-time environmental parameters are input into a preset dynamic interaction model, which outputs the disturbance amount of each frequency band. The dynamic interaction model is a nonlinear model trained by multi-factor combination samples, and the multi-factor combination includes the actual disturbance amount of each frequency band under different combinations of environmental parameters.

[0007] The compensation gain for each frequency band is calculated based on the amount of disturbance in each frequency band.

[0008] The compensated audio signal is obtained by compensating each frequency band of the stage performance audio signal to be output based on the compensation gain.

[0009] Furthermore, the disturbed quantities include amplitude attenuation and signal-to-noise ratio degradation, and the training process of the dynamic interaction model includes:

[0010] Collect N environmental parameter combination samples. Each sample includes the specific values ​​of M environmental parameters and the actual disturbance amount of each frequency band in the corresponding scenario.

[0011] The environmental parameter combination samples are divided into a training set and a validation set;

[0012] A neural network model is used, with environmental parameters from the training set as input, the disturbance amount in each frequency band as output, and a preset loss function to train the neural network model;

[0013] The trained model is validated using a validation set, and when the validation accuracy is greater than a preset threshold, it is determined to be the dynamic interaction model.

[0014] Furthermore, the loss function for training the dynamic interaction model is:

[0015] ;

[0016] in, ;

[0017] ;

[0018] ;

[0019] ;

[0020] in, For the total loss, The amplitude attenuation L1 loss for each frequency band, The MSE loss is the amount of signal-to-noise ratio degradation in each frequency band. This is a penalty term for prediction bias in high-priority frequency bands. , , These are the weighting coefficients, and K represents the number of frequency bands, and k represents the frequency band index. This represents the weighting coefficient for the k-th frequency band. The weighting coefficient for higher-priority frequency bands is greater than that for lower-priority frequency bands. This represents the actual signal-to-noise ratio degradation in the k-th frequency band for the i-th sample. The model predicts the signal-to-noise ratio degradation for the k-th frequency band in the i-th sample; This represents the actual amplitude attenuation of the i-th sample in the k-th frequency band. This is the predicted amplitude attenuation value of the model for the k-th frequency band of the i-th sample; The deviation threshold, Let be the overall prediction bias of the i-th sample in the m-th high-priority frequency band, where m is the index of the high-priority frequency band. This represents the actual amplitude attenuation of the m-th high-priority frequency band for the i-th sample. This is the predicted amplitude attenuation value of the model for the m-th high-priority frequency band of the i-th sample; This represents the actual signal-to-noise ratio degradation of the m-th high-priority frequency band for the i-th sample. The predicted signal-to-noise ratio degradation of the m-th high-priority frequency band for the i-th sample; This is the penalty coefficient.

[0021] Furthermore, after the step of compensating each frequency band of the stage performance audio signal to be output based on the compensation gain to obtain the compensated audio signal, the method further includes:

[0022] Collect air humidity and air temperature;

[0023] Calculate the time compensation value of each speaker in the multi-speaker system based on the air humidity and air temperature;

[0024] The compensated audio signal is controlled to be played on each speaker based on the time compensation value of each speaker.

[0025] Furthermore, the step of calculating the time compensation value of each speaker in the multi-speaker system based on the air humidity and air temperature includes:

[0026] Calculate the current speed of sound based on the air humidity and air temperature;

[0027] Calculate the time compensation value for each speaker in a multi-speaker system based on the speed of sound when the air is dry and the current speed of sound.

[0028] Furthermore, the step of calculating the current speed of sound based on the air humidity and air temperature includes:

[0029] According to the formula Calculate the current speed of sound; where v is the current speed of sound, T is the air temperature in degrees Celsius, and h is the relative humidity percentage.

[0030] Furthermore, the step of calculating the time compensation value of each speaker in the multi-speaker system based on the air humidity and air temperature includes:

[0031] According to the formula Calculate the time compensation value for each speaker in the multi-speaker system; where Δt is the time compensation value of the target speaker in the multi-speaker system, d is the distance between the target speaker and the audience reference point, and v is the current speed of sound. The speed of sound when the air is dry.

[0032] Secondly, embodiments of this application provide an audio control system for stage performances, the system comprising:

[0033] The data acquisition module is used to acquire real-time environmental parameters of the open-air stage, including at least two of the following: rainfall, wind speed, ambient noise, temperature and humidity, and audience noise.

[0034] The input module is used to input the real-time environmental parameters into a preset dynamic interaction model and output the disturbance amount of each frequency band; the dynamic interaction model is a nonlinear model obtained by training through multi-factor combination samples, and the multi-factor combination includes the actual disturbance amount of each frequency band under different combinations of environmental parameters.

[0035] The calculation module is used to calculate the compensation gain of each frequency band based on the disturbance amount of each frequency band;

[0036] The compensation module is used to compensate each frequency band of the stage performance audio signal to be output based on the compensation gain, so as to obtain a compensated audio signal.

[0037] Furthermore, the disturbed quantities include amplitude attenuation and signal-to-noise ratio degradation, and the training process of the dynamic interaction model includes:

[0038] Collect N environmental parameter combination samples. Each sample includes the specific values ​​of M environmental parameters and the actual disturbance amount of each frequency band in the corresponding scenario.

[0039] The environmental parameter combination samples are divided into a training set and a validation set;

[0040] A neural network model is used, with environmental parameters from the training set as input, the disturbance amount in each frequency band as output, and a preset loss function to train the neural network model;

[0041] The trained model is validated using a validation set, and when the validation accuracy is greater than a preset threshold, it is determined to be the dynamic interaction model.

[0042] Furthermore, the loss function for training the dynamic interaction model is:

[0043] ;

[0044] in, ;

[0045] ;

[0046] ;

[0047] ;

[0048] in, For the total loss, The amplitude attenuation L1 loss for each frequency band, The MSE loss is the amount of signal-to-noise ratio degradation in each frequency band. This is a penalty term for prediction bias in high-priority frequency bands. , , These are the weighting coefficients, and K represents the number of frequency bands, and k represents the frequency band index. This represents the weighting coefficient for the k-th frequency band. The weighting coefficient for higher-priority frequency bands is greater than that for lower-priority frequency bands. This represents the actual signal-to-noise ratio degradation in the k-th frequency band for the i-th sample. The model predicts the signal-to-noise ratio degradation for the k-th frequency band in the i-th sample; This represents the actual amplitude attenuation of the i-th sample in the k-th frequency band. This is the predicted amplitude attenuation value of the model for the k-th frequency band of the i-th sample; The deviation threshold, Let be the overall prediction bias of the i-th sample in the m-th high-priority frequency band, where m is the index of the high-priority frequency band. This represents the actual amplitude attenuation of the m-th high-priority frequency band for the i-th sample. This is the predicted amplitude attenuation value of the model for the m-th high-priority frequency band of the i-th sample; This represents the actual signal-to-noise ratio degradation of the m-th high-priority frequency band for the i-th sample. The predicted signal-to-noise ratio degradation of the m-th high-priority frequency band for the i-th sample; This is the penalty coefficient.

[0049] This application has the following technical effects:

[0050] (1) The audio control method for stage performance provided in this application includes: collecting real-time environmental parameters of an open-air stage, wherein the environmental parameters include at least two of rainfall, wind speed, environmental noise, temperature and humidity, and audience noise; inputting the real-time environmental parameters into a preset dynamic interaction model and outputting the disturbance amount of each frequency band; wherein the dynamic interaction model is a nonlinear model trained by multi-factor combination samples, and the multi-factor combination includes the actual disturbance amount of each frequency band under different combinations of environmental parameters; calculating the compensation gain of each frequency band based on the disturbance amount of each frequency band; and compensating each frequency band of the stage performance audio signal to be output based on the compensation gain to obtain a compensated audio signal. Compared with existing methods, this invention replaces the fixed overlap of preset gain and preset weight with a data-driven dynamic interaction model, no longer using manual rules to hard-decode complex interactions, but allowing the system to adapt to environmental changes through learning and feedback, and is more capable of accurately modeling complex interaction relationships, so that key audio content is always clearly distinguishable no matter how environmental factors are superimposed.

[0051] (2) Since air humidity and temperature change the speed of sound in the air during rainfall, calculating the time compensation value of each speaker in a multi-speaker system based on air humidity and air temperature can better control the synchronization of audio with other stage elements (such as movements) and ensure the stage performance effect. At the same time, it ensures that the sound signals of speakers in different positions reach the audience positions synchronously, eliminates the phase difference caused by changes in the speed of sound, and avoids the phenomenon of sound "trailing" or "overlapping". Attached Figure Description

[0052] To more clearly illustrate the technical solution of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0053] Figure 1 This is a flowchart illustrating an audio control method for stage performances provided in an embodiment of this application. Detailed Implementation

[0054] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0055] Those skilled in the art will understand that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have the same meaning as in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless specifically defined as herein.

[0056] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, apparatus, article, or method. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, apparatus, article, or method that includes that element.

[0057] like Figure 1 As shown in the figure, this application provides an audio control method for stage performances, the method comprising:

[0058] S1. Collect real-time environmental parameters of the open-air stage, including at least two of the following: rainfall, wind speed, ambient noise, temperature and humidity, and audience noise;

[0059] S2. Input the real-time environmental parameters into a preset dynamic interaction model and output the disturbance amount of each frequency band; the dynamic interaction model is a nonlinear model obtained by training through multi-factor combination samples, and the multi-factor combination includes the actual disturbance amount of each frequency band under different combinations of environmental parameters.

[0060] S3. Calculate the compensation gain for each frequency band based on the amount of disturbance in each frequency band;

[0061] S4. Based on the compensation gain, compensate for each frequency band of the stage performance audio signal to be output to obtain the compensated audio signal.

[0062] Compared to existing methods, this invention replaces the fixed overlap of preset gain and preset weight with a data-driven dynamic interaction model. Instead of using manual rules to hard-decode complex interactions, it allows the system to learn and adapt to environmental changes through feedback, enabling it to more accurately model complex interaction relationships and ensure that key audio content remains clear and identifiable regardless of how environmental factors are superimposed.

[0063] In one embodiment, the disturbance includes amplitude attenuation and signal-to-noise ratio degradation, and the training process of the dynamic interaction model includes:

[0064] Collect N environmental parameter combination samples. Each sample includes the specific values ​​of M environmental parameters and the actual disturbance amount of each frequency band in the corresponding scenario.

[0065] The environmental parameter combination samples are divided into a training set and a validation set;

[0066] A neural network model is used, with environmental parameters from the training set as input, the disturbance amount in each frequency band as output, and a preset loss function to train the neural network model;

[0067] The trained model is validated using a validation set, and when the validation accuracy is greater than a preset threshold, it is determined to be the dynamic interaction model.

[0068] In this embodiment, the environmental parameters may include rainfall, wind speed, ambient noise, temperature and humidity, and audience noise. The neural network model may employ a multilayer perceptron, recurrent neural network, etc. Amplitude attenuation refers to the difference between the ideal output amplitude and the actual output amplitude of a certain frequency band. Signal-to-noise ratio degradation refers to the difference between the ideal signal-to-noise ratio and the signal-to-noise ratio after disturbance in a certain frequency band.

[0069] To enable the trained model to more accurately predict the level of disturbance in key audio, in one embodiment, the loss function for training the dynamic interaction model is:

[0070] ;

[0071] in, ;

[0072] ;

[0073] ;

[0074] ;

[0075] in, For the total loss, The amplitude attenuation L1 loss for each frequency band, The MSE loss is the amount of signal-to-noise ratio degradation in each frequency band. This is a penalty term for prediction bias in high-priority frequency bands. , , These are the weighting coefficients, and K represents the number of frequency bands, and k represents the frequency band index. This represents the weighting coefficient for the k-th frequency band. The weighting coefficient for higher-priority frequency bands is greater than that for lower-priority frequency bands. This represents the actual signal-to-noise ratio degradation in the k-th frequency band for the i-th sample. The model predicts the signal-to-noise ratio degradation for the k-th frequency band in the i-th sample; This represents the actual amplitude attenuation of the i-th sample in the k-th frequency band. This is the predicted amplitude attenuation value of the model for the k-th frequency band of the i-th sample; The deviation threshold, Let be the overall prediction bias of the i-th sample in the m-th high-priority frequency band, where m is the index of the high-priority frequency band. This represents the actual amplitude attenuation of the m-th high-priority frequency band for the i-th sample. This is the predicted amplitude attenuation value of the model for the m-th high-priority frequency band of the i-th sample; This represents the actual signal-to-noise ratio degradation of the m-th high-priority frequency band for the i-th sample. The predicted signal-to-noise ratio degradation of the m-th high-priority frequency band for the i-th sample; This is the penalty coefficient.

[0076] In one embodiment, the disturbance quantity includes amplitude attenuation and signal-to-noise ratio degradation, and the step of calculating the compensation gain for each frequency band based on the disturbance quantity of each frequency band includes:

[0077] The compensation gain for each frequency band is calculated using the following formula:

[0078] ;

[0079] ;

[0080] ;

[0081] in, For the compensation gain of a certain frequency band, The weighting coefficients for amplitude compensation gain. These are the weighting coefficients for the signal-to-noise ratio compensation gain. Amplitude compensation gain, This represents the amplitude attenuation in a certain frequency band. This is the amplitude compensation coefficient, typically ranging from 1.0 to 1.3, and needs to be adjusted according to the acoustic characteristics of the outdoor stage. For example, when the outdoor stage has many reflective objects and the acoustic environment is complex, A can be set to 1.0-1.1 to avoid overcompensation; while in open squares or other environments where sound waves easily diffuse, A can be set to 1.2-1.3 to compensate for additional signal attenuation. This is for signal-to-noise ratio compensation gain. This represents the signal-to-noise ratio degradation in a certain frequency band. This is the signal-to-noise ratio threshold, typically ranging from 3 to 5 dB. When the signal is relatively weak, it indicates that the noise interference has little impact on signal clarity and no additional compensation is needed to avoid unnecessary compensation fluctuations caused by minor interference. B is the signal-to-noise ratio (SNR) compensation coefficient, ranging from 0.8 to 1.2, and needs to be adjusted according to the signal type. For the human voice frequency band (1-4kHz), since the human ear is more sensitive to speech clarity, B can be set to 1.1-1.2 to prioritize ensuring clear and intelligible speech. For the low-frequency range of instrumental music (20-200Hz), low-frequency signals are relatively less sensitive to SNR, and to avoid overcompensation leading to muddy audio, a value of 0.8-0.9 can be used.

[0082] In one embodiment, after the step of compensating each frequency band of the stage performance audio signal to be output based on the compensation gain to obtain the compensated audio signal, the method further includes:

[0083] S51. Collect air humidity and air temperature;

[0084] S52. Calculate the time compensation value of each speaker in the multi-speaker system based on the air humidity and air temperature.

[0085] S53. Control the playback of the compensated audio signal on each speaker based on the time compensation value of each speaker.

[0086] In step S52, the step of calculating the time compensation value of each speaker in the multi-speaker system based on the air humidity and air temperature includes:

[0087] S521. Calculate the current speed of sound based on the air humidity and air temperature;

[0088] S522. Calculate the time compensation value of each speaker in the multi-speaker system based on the sound velocity when the air is dry and the current sound velocity.

[0089] In step S521, the step of calculating the current speed of sound based on the air humidity and air temperature includes:

[0090] According to the formula Calculate the current speed of sound; where v is the current speed of sound, T is the air temperature in degrees Celsius, and h is the relative humidity percentage.

[0091] In step S522, the step of calculating the time compensation value of each speaker in the multi-speaker system based on the air humidity and air temperature includes:

[0092] According to the formula Calculate the time compensation value for each speaker in the multi-speaker system; where Δt is the time compensation value of the target speaker in the multi-speaker system, d is the distance between the target speaker and the audience reference point, and v is the current speed of sound. The speed of sound when the air is dry.

[0093] In this embodiment, since air humidity and temperature change the speed of sound in the air during rainfall, calculating the time compensation value of each speaker in the multi-speaker system based on air humidity and temperature can better control the synchronization of audio with other stage elements (such as movements), ensuring the stage performance effect. Simultaneously, it ensures that the sound signals from speakers in different locations arrive at the audience's location synchronously, eliminating phase differences caused by changes in sound speed and avoiding sound "trailing" or "overlapping" phenomena.

[0094] This application also provides an audio control system for stage performances, the system comprising:

[0095] The acquisition module 1 is used to acquire real-time environmental parameters of the open-air stage, including at least two of the following: rainfall, wind speed, ambient noise, temperature and humidity, and audience noise.

[0096] Input module 2 is used to input the real-time environmental parameters into a preset dynamic interaction model and output the disturbance amount of each frequency band; the dynamic interaction model is a nonlinear model obtained by training through multi-factor combination samples, and the multi-factor combination includes the actual disturbance amount of each frequency band under different combinations of environmental parameters.

[0097] Calculation module 3 is used to calculate the compensation gain of each frequency band based on the disturbance amount of each frequency band;

[0098] The compensation module 4 is used to compensate each frequency band of the stage performance audio signal to be output based on the compensation gain, so as to obtain a compensated audio signal.

[0099] In one embodiment, the disturbance includes amplitude attenuation and signal-to-noise ratio degradation, and the training process of the dynamic interaction model includes:

[0100] Collect N environmental parameter combination samples. Each sample includes the specific values ​​of M environmental parameters and the actual disturbance amount of each frequency band in the corresponding scenario.

[0101] The environmental parameter combination samples are divided into a training set and a validation set;

[0102] A neural network model is used, with environmental parameters from the training set as input, the disturbance amount in each frequency band as output, and a preset loss function to train the neural network model;

[0103] The trained model is validated using a validation set, and when the validation accuracy is greater than a preset threshold, it is determined to be the dynamic interaction model.

[0104] In one embodiment, the loss function for training the dynamic interaction model is:

[0105] ;

[0106] in, ;

[0107] ;

[0108] ;

[0109] ;

[0110] in, For the total loss, The amplitude attenuation L1 loss for each frequency band, The MSE loss is the amount of signal-to-noise ratio degradation in each frequency band. This is a penalty term for prediction bias in high-priority frequency bands. , , These are the weighting coefficients, and K represents the number of frequency bands, and k represents the frequency band index. This represents the weighting coefficient for the k-th frequency band. The weighting coefficient for higher-priority frequency bands is greater than that for lower-priority frequency bands. This represents the actual signal-to-noise ratio degradation in the k-th frequency band for the i-th sample. The model predicts the signal-to-noise ratio degradation for the k-th frequency band in the i-th sample; This represents the actual amplitude attenuation of the i-th sample in the k-th frequency band. This is the predicted amplitude attenuation value of the model for the k-th frequency band of the i-th sample; The deviation threshold, Let be the overall prediction bias of the i-th sample in the m-th high-priority frequency band, where m is the index of the high-priority frequency band. This represents the actual amplitude attenuation of the m-th high-priority frequency band for the i-th sample. This is the predicted amplitude attenuation value of the model for the m-th high-priority frequency band of the i-th sample; This represents the actual signal-to-noise ratio degradation of the m-th high-priority frequency band for the i-th sample. The predicted signal-to-noise ratio degradation of the m-th high-priority frequency band for the i-th sample; This is the penalty coefficient.

[0111] The above description is only a preferred embodiment of this application and does not limit the patent scope of this application. Any equivalent structural or procedural changes made based on the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. An audio control method for stage performances, characterized by, The method includes: Real-time environmental parameters of the open-air stage are collected, including at least two of the following: rainfall, wind speed, ambient noise, temperature and humidity, and audience noise. The real-time environmental parameters are input into a preset dynamic interaction model, which outputs the disturbance amount of each frequency band. The dynamic interaction model is a nonlinear model trained by multi-factor combination samples, and the multi-factor combination includes the actual disturbance amount of each frequency band under different combinations of environmental parameters. The compensation gain for each frequency band is calculated based on the amount of disturbance in each frequency band. Based on the aforementioned compensation gain, each frequency band of the stage performance audio signal to be output is compensated to obtain a compensated audio signal; The disturbance includes amplitude attenuation and signal-to-noise ratio degradation. The training process of the dynamic interaction model includes: Collect N environmental parameter combination samples. Each sample includes the specific values ​​of M environmental parameters and the actual disturbance amount of each frequency band in the corresponding scenario. The environmental parameter combination samples are divided into a training set and a validation set; A neural network model is used, with environmental parameters from the training set as input, the disturbance amount in each frequency band as output, and a preset loss function to train the neural network model; The trained model is validated using a validation set. When the validation accuracy is greater than a preset threshold, it is determined to be the dynamic interaction model. The loss function for training the dynamic interaction model is: ； wherein ; ； ； ； in, For the total loss, The amplitude attenuation L1 loss for each frequency band, The MSE loss is the amount of signal-to-noise ratio degradation in each frequency band. This is a penalty term for prediction bias in high-priority frequency bands. , , These are the weighting coefficients, and K represents the number of frequency bands, and k represents the frequency band index. This represents the weighting coefficient for the k-th frequency band. The weighting coefficient for higher-priority frequency bands is greater than that for lower-priority frequency bands. This represents the actual signal-to-noise ratio degradation in the k-th frequency band for the i-th sample. The model predicts the signal-to-noise ratio degradation for the k-th frequency band in the i-th sample; This represents the actual amplitude attenuation of the i-th sample in the k-th frequency band. This is the predicted amplitude attenuation value of the model for the k-th frequency band of the i-th sample; The deviation threshold, Let be the overall prediction bias of the i-th sample in the m-th high-priority frequency band, where m is the index of the high-priority frequency band. This represents the actual amplitude attenuation of the m-th high-priority frequency band for the i-th sample. This is the predicted amplitude attenuation value of the model for the m-th high-priority frequency band of the i-th sample; This represents the actual signal-to-noise ratio degradation of the m-th high-priority frequency band for the i-th sample. The predicted signal-to-noise ratio degradation of the m-th high-priority frequency band for the i-th sample; This is the penalty coefficient.

2. The audio control method for stage performance according to claim 1, characterized in that, After the step of compensating each frequency band of the stage performance audio signal to be output based on the compensation gain to obtain the compensated audio signal, the method further includes: Collect air humidity and air temperature; Calculate the time compensation value of each speaker in the multi-speaker system based on the air humidity and air temperature; The compensated audio signal is controlled to be played on each speaker based on the time compensation value of each speaker.

3. The audio control method for stage performance according to claim 2, characterized in that, The step of calculating the time compensation value of each speaker in the multi-speaker system based on the air humidity and air temperature includes: Calculate the current speed of sound based on the air humidity and air temperature; Calculate the time compensation value for each speaker in a multi-speaker system based on the speed of sound when the air is dry and the current speed of sound.

4. The audio control method for stage performance according to claim 3, characterized in that, The step of calculating the current speed of sound based on the air humidity and air temperature includes: According to the formula Calculate the current speed of sound; where v is the current speed of sound, T is the air temperature in degrees Celsius, and h is the relative humidity percentage.

5. The audio control method for stage performance according to claim 3, characterized in that, The step of calculating the time compensation value of each speaker in the multi-speaker system based on the air humidity and air temperature includes: According to the formula Calculate the time compensation value for each speaker in the multi-speaker system; where Δt is the time compensation value of the target speaker in the multi-speaker system, d is the distance between the target speaker and the audience reference point, and v is the current speed of sound. The speed of sound when the air is dry.

6. An audio control system for stage performances, characterized in that, The system includes: The data acquisition module is used to acquire real-time environmental parameters of the open-air stage, including at least two of the following: rainfall, wind speed, ambient noise, temperature and humidity, and audience noise. The input module is used to input the real-time environmental parameters into a preset dynamic interaction model and output the disturbance amount of each frequency band; the dynamic interaction model is a nonlinear model obtained by training through multi-factor combination samples, and the multi-factor combination includes the actual disturbance amount of each frequency band under different combinations of environmental parameters. The calculation module is used to calculate the compensation gain of each frequency band based on the disturbance amount of each frequency band; The compensation module is used to compensate each frequency band of the stage performance audio signal to be output based on the compensation gain, so as to obtain a compensated audio signal. The disturbance includes amplitude attenuation and signal-to-noise ratio degradation. The training process of the dynamic interaction model includes: Collect N environmental parameter combination samples. Each sample includes the specific values ​​of M environmental parameters and the actual disturbance amount of each frequency band in the corresponding scenario. The environmental parameter combination samples are divided into a training set and a validation set; A neural network model is used, with environmental parameters from the training set as input, the disturbance amount in each frequency band as output, and a preset loss function to train the neural network model; The trained model is validated using a validation set. When the validation accuracy is greater than a preset threshold, it is determined to be the dynamic interaction model. The loss function for training the dynamic interaction model is: ； in, ; ； ； ； in, For the total loss, The amplitude attenuation L1 loss for each frequency band, The MSE loss is the amount of signal-to-noise ratio degradation in each frequency band. This is a penalty term for prediction bias in high-priority frequency bands. , , These are the weighting coefficients, and K represents the number of frequency bands, and k represents the frequency band index. This represents the weighting coefficient for the k-th frequency band. The weighting coefficient for higher-priority frequency bands is greater than that for lower-priority frequency bands. This represents the actual signal-to-noise ratio degradation in the k-th frequency band for the i-th sample. The model predicts the signal-to-noise ratio degradation for the k-th frequency band in the i-th sample; This represents the actual amplitude attenuation of the i-th sample in the k-th frequency band. This is the predicted amplitude attenuation value of the model for the k-th frequency band of the i-th sample; The deviation threshold, Let be the overall prediction bias of the i-th sample in the m-th high-priority frequency band, where m is the index of the high-priority frequency band. This represents the actual amplitude attenuation of the m-th high-priority frequency band for the i-th sample. This is the predicted amplitude attenuation value of the model for the m-th high-priority frequency band of the i-th sample; This represents the actual signal-to-noise ratio degradation of the m-th high-priority frequency band for the i-th sample. The predicted signal-to-noise ratio degradation of the m-th high-priority frequency band for the i-th sample; This is the penalty coefficient.

Images