Audio delay automatic calibration method and device based on anomaly detection, equipment and storage medium

Abstract

The invention discloses an automatic audio delay calibration method, device and equipment based on anomaly detection and a storage medium, which are applied to a multi-equipment audio system and are used for collecting audio signals for preprocessing, collecting delay time measurement values, environment data and the audio signals for abnormal data detection. Calculating a delay compensation based on the audio signal and the delay time measurement, calculating an environmental factor compensation based on the environmental data; based on the delay compensation and the environmental factor compensation, audio delay automatic calibration is carried out through a real-time feedback mechanism; and evaluating the system performance based on the audio signal acquired in real time and the delay time measurement value, and optimizing the real-time feedback mechanism in real time. Interference data are accurately identified and filtered through intelligent data analysis, and a real-time analysis and automatic processing mechanism is adopted, so that the limitation of traditional manual calibration is broken through. The system can dynamically sense environment changes and adaptively adjust calibration parameters, and millisecond-level delay calibration precision is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of multi-device audio playback, and in particular to an audio delay automatic calibration method, device, equipment and storage medium based on abnormality detection. Background Art

[0002] In the field of modern multi-device audio systems, the problem of audio delay is becoming increasingly prominent. Whether it is a home theater system, professional audio equipment or smart speakers, the delay differences between multiple devices will significantly affect the sound restoration effect. Traditional calibration methods mainly rely on manual operation or preset parameters, which is not only time-consuming and labor-intensive, but also easily affected by subjective factors. At the same time, due to the lack of consideration of environmental factors (temperature, humidity, etc.), the calibration results are often not stable enough. Existing technologies cannot effectively identify and filter abnormal data, making it difficult to ensure calibration accuracy. In addition, traditional methods lack adaptive capabilities, cannot cope with the impact of environmental changes such as temperature and humidity, and cannot achieve real-time dynamic calibration. These problems seriously restrict the performance of multi-device audio systems, and an innovative solution is urgently needed. Summary of the invention

[0003] The present invention provides an automatic audio delay calibration method, device, equipment and storage medium based on anomaly detection, innovatively introduces anomaly detection algorithm, realizes accurate identification and filtering of interference data through intelligent data analysis, and adopts real-time analysis and automatic processing mechanism to break through the limitations of traditional manual calibration. The system can dynamically perceive environmental changes and adaptively adjust calibration parameters to achieve millisecond-level delay calibration accuracy. In addition, the calibration model is optimized through machine learning algorithm to ensure the continuous and stable operation of multi-device audio systems, greatly improving the calibration effect.

[0004] A first aspect of the present invention provides an audio delay automatic calibration method based on anomaly detection, which is applied to a multi-device audio system and includes the following steps:

[0005] Collecting audio signals for preprocessing, collecting delay time measurement values, environmental data and the audio signals for abnormal data detection;

[0006] Calculating delay compensation based on the audio signal and the delay time measurement value, and calculating environmental factor compensation based on the environmental data;

[0007] Automatically calibrate audio delay based on the delay compensation and the environmental factor compensation through a real-time feedback mechanism;

[0008] The system performance is evaluated based on the real-time collected audio signal and the delay time measurement value, and the real-time feedback mechanism is optimized in real time.

[0009] Preferably, collecting audio signals for preprocessing further includes:

[0010] applying a Gaussian filter to the audio signal to smooth the signal and remove high frequency noise;

[0011] The audio signal is decomposed at multiple scales using the selected wavelet basis function to obtain wavelet coefficients at different scales. The decomposed wavelet coefficients are threshold processed to remove noise components and reconstruct the denoised audio signal.

[0012] Preferably, collecting the delay time measurement value, the environmental data and the audio signal for abnormal data detection further comprises:

[0013] The Z-score anomaly detection method is used to quickly screen and preliminarily determine the scope of anomalies;

[0014] Abnormal data is locked by using the Mahalanobis distance anomaly detection method.

[0015] Preferably, calculating the delay compensation based on the audio signal and the delay time measurement value further comprises:

[0016] The delay range is estimated by a cross-correlation analysis algorithm;

[0017] A fast Fourier transform is performed through a phase difference algorithm to obtain a frequency domain representation, the phase difference is calculated based on the frequency domain representation, the relative delay is estimated according to the relationship between the phase difference and the time delay, and the delay compensation is calculated.

[0018] Preferably, calculating the environmental factor compensation based on the environmental data further comprises:

[0019] The temperature data is collected in real time through the temperature and humidity sensor, and the sound speed parameters are corrected based on the temperature and sound speed mathematical model;

[0020] The humidity data is collected in real time through the temperature and humidity sensors, and the sound speed parameters are corrected based on the mathematical model of humidity and sound speed.

[0021] Preferably, the automatic calibration of audio delay based on the delay compensation and the environmental factor compensation through a real-time feedback mechanism further includes:

[0022] The delay compensation and the environmental factor compensation acquired in real time are input into a preset PID control model, and the PID control model outputs a dependent variable audio delay time to achieve automatic calibration of the audio delay;

[0023] The parameters of the proportional, integral and differential links of the PID control model are adaptively adjusted through a machine learning model.

[0024] Preferably, evaluating system performance based on the real-time collected audio signal and delay time measurement value, and optimizing the real-time feedback mechanism in real time further includes:

[0025] Inputting data including at least historical calibration data, environmental parameters, and equipment status into the trained support vector machine model;

[0026] The support vector machine model outputs optimization data including at least parameters of the three links of proportion, integration and differentiation of the PID control model.

[0027] Preferably, evaluating system performance based on the real-time collected audio signal and delay time measurement value, and optimizing the real-time feedback mechanism in real time further includes:

[0028] During the operation of the system, audio signals, delay time measurements, and environmental data are recorded in real time, and statistical analysis is performed on the recorded data to calculate system performance indicators.

[0029] A second aspect of the present invention provides an audio delay automatic calibration device based on abnormality detection, comprising:

[0030] A data acquisition module, used to collect audio signals for preprocessing, collect delay time measurement values, environmental data and the audio signals for abnormal data detection;

[0031] a compensation calculation module, configured to calculate delay compensation based on the audio signal and the delay time measurement value, and calculate environmental factor compensation based on the environmental data;

[0032] An automatic calibration module, used for automatically calibrating audio delay through a real-time feedback mechanism based on the delay compensation and the environmental factor compensation;

[0033] The adaptive adjustment module is used to evaluate the system performance based on the real-time collected audio signal and the delay time measurement value, and optimize the real-time feedback mechanism in real time.

[0034] A third aspect of the present invention provides an audio delay automatic calibration device based on anomaly detection, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the above-mentioned audio delay automatic calibration method based on anomaly detection when executed by the processor.

[0035] A fourth aspect of the present invention provides a computer-readable storage medium having instructions stored thereon, wherein when the instructions are executed by a processor, the method for automatic audio delay calibration based on anomaly detection as described in any one of claims 1 to 8 is implemented.

[0036] In the technical solution provided by the present invention, a delay compensation value is calculated based on an audio signal and a delay time measurement value. According to environmental data, the influence of environmental factors on the audio signal is calculated, and corresponding compensation is performed. For example, changes in temperature and humidity will affect the speed of sound, thereby affecting the propagation time of the audio signal. The calculated delay compensation and environmental factor compensation values ​​are applied to the audio system through a real-time feedback mechanism, and the delay of the audio signal is dynamically adjusted to achieve synchronization between multiple devices. In addition, the internal parameters of the model of the real-time feedback mechanism are adaptively adjusted based on the real-time performance evaluation results of the system, such as adjusting the parameters of the PID control model, thereby improving the delay accuracy and stability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a flow chart of the method for automatic calibration of audio delay based on anomaly detection of the present invention;

[0038] Figure 2 It is a schematic diagram of a process of automatically calibrating audio delay through a real-time feedback mechanism based on the delay compensation and the environmental factor compensation in an embodiment;

[0039] Figure 3 FIG. 4 is a schematic diagram of an embodiment of a computer device in this embodiment. DETAILED DESCRIPTION

[0040] The present invention provides an audio delay automatic calibration method, system, device and storage medium based on anomaly detection, which effectively solves the problem of reopening capture when the audio input player switches modes through a persistent audio capture session and a dynamic audio processing pipeline.

[0041] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0042] Embodiment 1

[0043] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 , provides an audio delay automatic calibration method based on anomaly detection, which is applied to a multi-device audio system, comprising the following steps:

[0044] S100: collecting audio signals for preprocessing, collecting delay time measurement values, environmental data and the audio signals for abnormal data detection;

[0045] S200: Calculating delay compensation based on the audio signal and the delay time measurement value, and calculating environmental factor compensation based on the environmental data;

[0046] S300: Automatically calibrating audio delay through a real-time feedback mechanism based on the delay compensation and the environmental factor compensation;

[0047] S400: Evaluate system performance based on the real-time collected audio signal and delay time measurement value, and optimize the real-time feedback mechanism in real time.

[0048] The technical solution of this embodiment calculates the delay compensation value based on the audio signal and the delay time measurement value. According to the environmental data, the influence of environmental factors on the audio signal is calculated and corresponding compensation is performed. For example, changes in temperature and humidity will affect the speed of sound, thereby affecting the propagation time of the audio signal. The calculated delay compensation and environmental factor compensation values ​​are applied to the audio system through a real-time feedback mechanism, and the delay of the audio signal is dynamically adjusted to achieve synchronization between multiple devices. In addition, the internal parameters of the model of the real-time feedback mechanism are adaptively adjusted based on the real-time performance evaluation results of the system, such as adjusting the parameters of the PID control model, thereby improving the delay accuracy and stability of the system.

[0049] It should be noted that the multi-device audio system of the present invention adopts a distributed structure and includes at least the following hardware components:

[0050] Main controller: responsible for data processing and algorithm operation;

[0051] High-precision microphone array: Each speaker is equipped with at least 3 microphones;

[0052] Environmental sensors: used to collect data such as temperature, humidity, and air pressure;

[0053] Clock synchronization module: provides microsecond-level time synchronization.

[0054] For example, in a typical 5.1 channel system, the configuration is as follows: 6 speakers are each equipped with 3 microphones distributed at 120 degrees, the environmental sensor sampling rate is 10Hz, the clock synchronization accuracy is: ±1 microsecond. The audio signal sampling rate is 48kHz, the bit depth is 24bit, and the acquisition window is 20ms.

[0055] Preferably, collecting audio signals for preprocessing further includes:

[0056] applying a Gaussian filter to the audio signal to smooth the signal and remove high frequency noise;

[0057] The audio signal is decomposed at multiple scales using the selected wavelet basis function to obtain wavelet coefficients at different scales. The decomposed wavelet coefficients are threshold processed to remove noise components and reconstruct the denoised audio signal.

[0058] The technical solution of this embodiment uses a Gaussian function to perform weighted averaging on the signal, which can effectively smooth the audio signal and reduce mutations and noise in the signal. The Gaussian filter has a good inhibitory effect on high-frequency components, can effectively remove high-frequency noise in the audio signal, and improve the signal-to-noise ratio. While smoothing the signal, it can better maintain the original characteristics of the signal and avoid signal distortion caused by excessive smoothing. Gaussian filtering removes high-frequency noise, and the formula is: G(x, y) = (1 / 2πσ 2 )e^(-(x 2 +y 2 ) / 2σ 2 ), where σ is the standard deviation, usually 1.5. At the same time, the selected wavelet basis function is used to perform multi-scale decomposition of the audio signal, which can capture the local characteristics of the signal and is suitable for the analysis of non-stationary signals. After removing the noise component, the processed wavelet coefficients are reconstructed through inverse wavelet transform to obtain the denoised audio signal. During the reconstruction process, attention should be paid to the processing of boundary effects to avoid introducing additional noise. Specifically, the wavelet transform performs multi-scale analysis, and the formula is: ψa,b(t)=(1 / √a)ψ((tb) / a), where a is the scale parameter and b is the translation parameter.

[0059] Preferably, collecting the delay time measurement value, the environmental data and the audio signal for abnormal data detection further comprises:

[0060] The Z-score anomaly detection method is used to quickly screen and preliminarily determine the scope of anomalies;

[0061] Abnormal data is locked by using the Mahalanobis distance anomaly detection method.

[0062] In the technical solution of this embodiment, the Z-score anomaly detection method identifies outliers by calculating the standard deviation of the data point and the mean of the data set. It is simple and fast, suitable for preliminarily determining the range of anomalies, and standardizing the data so that data of different dimensions can be compared, which helps to improve the accuracy of anomaly detection. In addition, the Mahalanobis distance takes into account the correlation of the data, is suitable for anomaly detection of multivariate data, can effectively identify data points that deviate from the normal pattern in multiple dimensions, is insensitive to the scale of the data, has strong robustness, and can accurately detect abnormal data even in the presence of outliers.

[0063] Specifically, in the Z-score anomaly detection method, Z = (x-μ) / σ, where x is the observed value, μ is the average value, and σ is the standard deviation. When |Z|>3, it is judged to be abnormal. For different detection data objects, the x data can be: audio sampling data, delay time measurement value, environmental parameters (temperature, humidity, etc.). The Z-score anomaly detection method marks and temporarily stores the data points judged to be abnormal, and uses the historical valid data of the sliding window for interpolation compensation. If abnormal data appears continuously, the system alarm is triggered and the fault-tolerant processing mechanism is entered. In the Mahalanobis distance detection anomaly detection method, D = √((x-μ)^TΣ^(-1)(x-μ)), where Σ is the covariance matrix and x is the observation vector. The Z-score method is mainly used for anomaly detection of single-dimensional data, such as the delay time series of a single sensor. The Mahalanobis distance detection is used for joint anomaly detection of multi-dimensional data, such as the collaborative analysis of multiple sensor data. The two methods are used in combination, first using the Z-score method for rapid screening, and then using the Mahalanobis distance for accurate judgment, forming a double verification mechanism.

[0064] Preferably, calculating the delay compensation based on the audio signal and the delay time measurement value further comprises:

[0065] The delay range is estimated by a cross-correlation analysis algorithm;

[0066] A fast Fourier transform is performed through a phase difference algorithm to obtain a frequency domain representation, the phase difference is calculated based on the frequency domain representation, the relative delay is estimated according to the relationship between the phase difference and the time delay, and the delay compensation is calculated.

[0067] The cross-correlation analysis algorithm in the technical solution of this embodiment can estimate the time delay between signals by calculating the cross-correlation function between two signals. It is suitable for situations where the signal waveforms are similar and can provide preliminary delay estimates. Since the calculation is relatively simple, it is suitable for real-time processing. At the same time, the cross-correlation analysis has a certain robustness to noise and can effectively estimate the delay in a noisy environment. The phase difference algorithm can provide high-precision delay estimation, but the amount of calculation for calculating FFT and phase difference is large, which may affect real-time performance. Therefore, this embodiment first uses the cross-correlation analysis algorithm to roughly estimate the delay range, and then uses the phase difference method to accurately calculate, forming a coarse adjustment + fine adjustment process. Rapid screening through cross-correlation analysis can reduce the amount of data for subsequent phase difference calculations, thereby improving overall calculation efficiency. The complementarity of the two can effectively improve the real-time and accuracy of delay compensation.

[0068] Specifically, the cross-correlation analysis algorithm is: R(τ)=∑(x(t)y(t+τ)), where τ is the time delay, x(t) and y(t) are two audio signals. Delay estimation based on phase difference is: Δφ=2πfΔt, where f is the signal frequency and Δt is the time delay.

[0069] Preferably, calculating the environmental factor compensation based on the environmental data further comprises:

[0070] The temperature data is collected in real time through the temperature and humidity sensor, and the sound speed parameters are corrected based on the temperature and sound speed mathematical model;

[0071] The humidity data is collected in real time through the temperature and humidity sensors, and the sound speed parameters are corrected based on the mathematical model of humidity and sound speed.

[0072] This embodiment deploys a high-precision temperature sensor in the audio processing environment to ensure that environmental temperature changes can be monitored in real time. Combining temperature and humidity data for sound velocity correction can significantly improve the accuracy of delay compensation and reduce errors. Real-time environmental data collection and sound velocity correction enable the system to quickly adapt to environmental changes and optimize response time. In the temperature and sound velocity mathematical model, the sound velocity correction formula is: c = 331.3 + 0.606t, where t is temperature (°C). In the humidity and sound velocity mathematical model, the humidity effect correction formula is: Δc = c 0 (1+αH), where c 0 is the speed of sound under standard conditions, H is the relative humidity, and α is the correction factor.

[0073] Furthermore, the synchronization of multiple devices in the audio system is optimized using the following methods:

[0074] Least squares optimization: min∑(di-d ～ i) 2 , where di is the measurement delay, d ～ i is the target delay. Through least squares optimization, the synchronization accuracy of multi-device audio systems can be significantly improved and audio asynchrony can be reduced. Real-time delay compensation calculation and feedback mechanism enable the system to quickly adapt to environmental changes and device status fluctuations, and improve response speed. Accurate synchronization and fast response speed enhance the user's auditory experience and satisfaction.

[0075] Gradient Descent Optimization: Among them, α is the learning rate and J(θ) is the cost function. The calculated delay compensation value is applied to each device through a real-time feedback mechanism, and the audio processing parameters of the device are dynamically adjusted to achieve synchronization. Through gradient descent optimization, the synchronization accuracy of multi-device audio systems can be significantly improved, and the phenomenon of audio and video asynchrony can be reduced. Real-time delay compensation calculation and feedback mechanism enable the system to quickly adapt to environmental changes and device status fluctuations, and improve response speed.

[0076] Preferably, the automatic calibration of audio delay based on the delay compensation and the environmental factor compensation through a real-time feedback mechanism further includes:

[0077] The delay compensation and the environmental factor compensation acquired in real time are input into a preset PID control model, and the PID control model outputs a dependent variable audio delay time to achieve automatic calibration of the audio delay;

[0078] The parameters of the proportional, integral and differential links of the PID control model are adaptively adjusted through a machine learning model.

[0079] This embodiment can achieve accurate automatic calibration of audio delay through adaptive adjustment of the PID control model and the machine learning model, thereby improving the synchronization accuracy of the multi-device audio system. The PID control model is responsible for real-time closed-loop control to ensure rapid response of the system. The machine learning model adaptively and dynamically adjusts the PID control model parameters to adapt to environmental changes. Specifically, in the PID control model, u(t) = Kpe(t) + Ki∫e(t)dt + Kd(de / dt), where Kp, Ki, and Kd are the parameters of the three links of proportion, integration, and differentiation. In the adaptive adjustment control, K(t) = K 0 +ΔK(t), where K 0 is the initial gain, and ΔK(t) is the dynamic adjustment amount.

[0080] As a preferred embodiment, the machine learning model adopts support vector machine (SVM) regression: f(x) = ∑(αi-αi*)K(xi,x)+b, where K is the kernel function, and αi and αi* are Lagrange multipliers. The input of the support vector machine is multidimensional features such as historical calibration data, environmental parameters, and equipment status, and the output is optimization suggestions for calibration parameters. The optimization content is to predict the optimal PID parameters, environmental compensation coefficients, sampling window size, etc. The use of the support vector machine regression model can improve calibration accuracy, shorten convergence time, and enhance anti-interference ability.

[0081] As a preferred embodiment, the machine learning model adopts a feedforward neural network structure, the input layer is delay data (6-8 dimensions) and environmental data (3-4 dimensions), the hidden layer adopts 2 layers, each layer has 64 nodes, the activation function ReLU: f(x) = max(0, x), the output layer is the calibration compensation value and PID parameter adjustment amount, and the network weights are continuously optimized through online learning to achieve adaptive improvement of system performance, thereby reducing calibration time, improving accuracy stability, and enhancing environmental adaptability.

[0082] Preferably, evaluating system performance based on the real-time collected audio signal and delay time measurement value, and optimizing the real-time feedback mechanism in real time further includes:

[0083] Inputting data including at least historical calibration data, environmental parameters, and equipment status into the trained support vector machine model;

[0084] The support vector machine model outputs optimization data including at least parameters of the three links of proportion, integration and differentiation of the PID control model.

[0085] Preferably, evaluating system performance based on the real-time collected audio signal and delay time measurement value, and optimizing the real-time feedback mechanism in real time further includes:

[0086] During the operation of the system, audio signals, delay time measurements, and environmental data are recorded in real time, and statistical analysis is performed on the recorded data to calculate system performance indicators.

[0087] For example, delay accuracy evaluation: Among them, yi is the actual value, i is the predicted value. Stability assessment: σ 2 =∑(xi-μ) 2 / n, where σ 2 is the variance and μ is the mean value.

[0088] As a preferred embodiment, during operation, the system performs:

[0089] Adaptive threshold adjustment: T(t) = T 0 +β·σ(t), where T 0 is the basic threshold, and β is the adjustment coefficient.

[0090] Automatic parameter tuning: Genetic algorithm optimization is used with a population size of 100, a crossover rate of 0.8, and a mutation rate of 0.1.

[0091] As a preferred option, the system implements the following exception handling and fault tolerance mechanisms:

[0092] Exception handling strategy:

[0093] 1) Fault detection algorithm: F(t) = ∑wi·fi(t), where wi is the weight coefficient and fi is the fault feature.

[0094] 2) Fault-tolerant processing: backup switching time: <10ms, data recovery mechanism: using circular buffer.

[0095] System monitoring and maintenance:

[0096] 1) Performance monitoring indicators: CPU usage threshold: 80%, memory usage threshold: 75%, network delay threshold: 5ms.

[0097] 2) Automatic maintenance strategy: log recording cycle: 10 minutes, system self-check cycle: 1 hour, data backup cycle: 24 hours.

[0098] The above technical scheme ensures the high accuracy and stability of multi-device audio delay automatic calibration through systematic step design and detailed algorithm implementation. Each step is equipped with specific implementation examples and algorithm formulas to facilitate technical implementation and subsequent optimization. The present invention significantly improves the synchronization accuracy and stability of the multi-device audio system by innovatively introducing a multi-level anomaly detection method and an adaptive algorithm, and achieves millisecond-level delay calibration accuracy. The multi-level anomaly detection mechanism is introduced. At the data processing level, combined with pre-processing algorithms such as Gaussian filtering and wavelet transform, accurate identification and filtering of interference data are achieved. With multi-dimensional anomaly detection methods such as Z-score and Mahalanobis distance, the abnormal range is first determined, and then the abnormal data is accurately determined, which not only reduces the amount of calculation but also significantly improves the data reliability. At the same time, through the distributed architecture design and environmental factor adaptive compensation mechanism, the problem of unstable calibration accuracy of traditional solutions in complex environments is successfully solved. At the optimization level, the dynamic compensation algorithm based on the influence of sound speed and humidity, and the intelligent optimization system integrating PID control model and machine learning, are organically combined to enable the system to process 5000+ data points at the same time and achieve millisecond-level delay calibration accuracy. Moreover, through intelligent fault detection and fault tolerance mechanisms, the stable operation of the system is guaranteed, and it has environmental adaptability and automatic fault detection functions, which significantly surpasses the existing technical level. Compared with traditional solutions, the present invention has achieved significant improvements in calibration accuracy, system stability and environmental adaptability, and provides an efficient and reliable technical solution for the synchronous control of multi-device audio systems.

[0099] Second embodiment

[0100] Based on the same inventive concept, this embodiment provides an audio delay automatic calibration device based on abnormality detection, comprising:

[0101] A data acquisition module, used to collect audio signals for preprocessing, collect delay time measurement values, environmental data and the audio signals for abnormal data detection;

[0102] a compensation calculation module, configured to calculate delay compensation based on the audio signal and the delay time measurement value, and calculate environmental factor compensation based on the environmental data;

[0103] An automatic calibration module, used for automatically calibrating audio delay through a real-time feedback mechanism based on the delay compensation and the environmental factor compensation;

[0104] The adaptive adjustment module is used to evaluate the system performance based on the real-time collected audio signal and the delay time measurement value, and optimize the real-time feedback mechanism in real time.

[0105] The technical solution of this embodiment calculates the delay compensation value based on the audio signal and the delay time measurement value. According to the environmental data, the influence of environmental factors on the audio signal is calculated and corresponding compensation is performed. For example, changes in temperature and humidity will affect the speed of sound, thereby affecting the propagation time of the audio signal. The calculated delay compensation and environmental factor compensation values ​​are applied to the audio system through a real-time feedback mechanism, and the delay of the audio signal is dynamically adjusted to achieve synchronization between multiple devices. In addition, the internal parameters of the model of the real-time feedback mechanism are adaptively adjusted based on the real-time performance evaluation results of the system, such as adjusting the parameters of the PID control model, thereby improving the delay accuracy and stability of the system.

[0106] This embodiment also provides an audio delay automatic calibration device based on anomaly detection, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the above-mentioned audio delay automatic calibration method based on anomaly detection when executed by the processor.

[0107] Based on the same inventive concept, this embodiment also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned methods for automatic audio delay calibration based on abnormality detection are implemented.

[0108] The following is a detailed description of the computer device for automatic calibration of audio delay based on anomaly detection in this embodiment from the perspective of hardware processing.

[0109] See also Figure 3 As shown, the computer device includes a processor 300 and a memory 301 , wherein the memory 301 stores machine executable instructions that can be executed by the processor 300 , and the processor 300 executes the machine executable instructions to implement the above-mentioned audio delay automatic calibration method based on abnormality detection.

[0110] further, Figure 3 The computer device shown further includes a bus 302 and a communication interface 303 , and the processor 300 , the communication interface 303 and the memory 301 are connected via the bus 302 .

[0111] The memory 301 may include a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), for example, at least one disk storage. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 303 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used. The bus 302 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0112] The processor 300 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 300. The above processor 300 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The disclosed methods, steps and logic block diagrams in the embodiments of the present disclosure can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in conjunction with the embodiments of the present disclosure can be directly embodied as a hardware decoding processor to be executed, or a combination of hardware and software modules in the decoding processor can be executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 301 , and the processor 300 reads the information in the memory 301 and completes the method steps of the above-mentioned embodiment in combination with its hardware.

[0113] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are executed on a computer, the computer executes the steps of an automatic audio delay calibration method based on anomaly detection.

[0114] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0115] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0116] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An audio delay automatic calibration method based on anomaly detection, applied to a multi-device audio system, characterized in that: The steps include: Collecting audio signals for preprocessing, collecting delay time measurement values, environmental data and the audio signals for abnormal data detection; Calculate delay compensation based on the audio signal and the delay time measurement value, and calculate environmental factor compensation based on the environmental data; Automatically calibrate audio delay based on the delay compensation and the environmental factor compensation through a real-time feedback mechanism; The system performance is evaluated based on the real-time collected audio signal and the delay time measurement value, and the real-time feedback mechanism is optimized in real time.

2. The method for automatic audio delay calibration based on anomaly detection according to claim 1, characterized in that: Collecting audio signals for preprocessing further includes: applying a Gaussian filter to the audio signal to smooth the signal and remove high frequency noise; The audio signal is decomposed at multiple scales using the selected wavelet basis function to obtain wavelet coefficients at different scales. The decomposed wavelet coefficients are threshold processed to remove noise components and reconstruct the denoised audio signal.

3. The method for automatic audio delay calibration based on anomaly detection according to claim 1, characterized in that: Collecting the delay time measurement value, the environmental data and the audio signal for abnormal data detection further includes: The Z-score anomaly detection method is used to quickly screen and preliminarily determine the scope of anomalies; Abnormal data is locked by using the Mahalanobis distance anomaly detection method.

4. The method for automatic audio delay calibration based on anomaly detection according to claim 1, characterized in that: Calculating delay compensation based on the audio signal and the delay time measurement further comprises: The delay range is estimated by a cross-correlation analysis algorithm; A fast Fourier transform is performed through a phase difference algorithm to obtain a frequency domain representation, the phase difference is calculated based on the frequency domain representation, the relative delay is estimated according to the relationship between the phase difference and the time delay, and the delay compensation is calculated.

5. The method for automatic audio delay calibration based on anomaly detection according to claim 1, characterized in that: Calculating environmental factor compensation based on the environmental data further includes: The temperature data is collected in real time through the temperature and humidity sensor, and the sound speed parameters are corrected based on the temperature and sound speed mathematical model; The humidity data is collected in real time through the temperature and humidity sensors, and the sound speed parameters are corrected based on the mathematical model of humidity and sound speed.

6. The method for automatic audio delay calibration based on anomaly detection according to claim 1, characterized in that: Automatically calibrating audio delay based on the delay compensation and the environmental factor compensation through a real-time feedback mechanism further includes: The delay compensation and the environmental factor compensation acquired in real time are input into a preset PID control model, and the PID control model outputs a dependent variable audio delay time to achieve automatic calibration of the audio delay; The parameters of the proportional, integral and differential links of the PID control model are adaptively adjusted through a machine learning model.

7. The method for automatic audio delay calibration based on anomaly detection according to claim 1, characterized in that: Evaluating system performance based on real-time collected audio signals and delay time measurements, and optimizing the real-time feedback mechanism in real time further includes: Inputting data including at least historical calibration data, environmental parameters, and equipment status into the trained support vector machine model; The support vector machine model outputs optimization data including at least parameters of the three links of proportion, integration and differentiation of the PID control model.

8. The method for automatic audio delay calibration based on anomaly detection according to claim 1, characterized in that: Evaluating system performance based on real-time collected audio signals and delay time measurements, and optimizing the real-time feedback mechanism in real time further includes: During the operation of the system, audio signals, delay time measurements, and environmental data are recorded in real time, and statistical analysis is performed on the recorded data to calculate system performance indicators.

9. An audio delay automatic calibration device based on anomaly detection, characterized in that: include: A data acquisition module, used to collect audio signals for preprocessing, collect delay time measurement values, environmental data and the audio signals for abnormal data detection; a compensation calculation module, configured to calculate delay compensation based on the audio signal and the delay time measurement value, and calculate environmental factor compensation based on the environmental data; An automatic calibration module, used for automatically calibrating audio delay through a real-time feedback mechanism based on the delay compensation and the environmental factor compensation; The adaptive adjustment module is used to evaluate the system performance based on the real-time collected audio signal and the delay time measurement value, and optimize the real-time feedback mechanism in real time.

10. An audio delay automatic calibration device based on anomaly detection, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the computer program is executed by a processor, the steps of the method for automatic audio delay calibration based on anomaly detection as described in any one of claims 1 to 8 are implemented.

11. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by the processor, the method for automatic audio delay calibration based on abnormality detection as described in any one of claims 1 to 8 is implemented.

Images