53 results about "Noise reduction algorithm" patented technology

The invention discloses an elevator steel belt damage detection and quantitative analysis system based on eddy current and magnetic flux leakage dual-mode detection, and aims to solve the problems of single-mode information loss and serious industrial field strong noise interference in the existing steel belt detection. The system synchronously integrates an eddy current sensor, a magnetic flux leakage sensor and an encoder through a multi-probe array adapter; and multi-dimensional damage physical information in the steel strip is obtained. An improved wavelet packet transform-empirical mode decomposition (WPT-EMD) collaborative noise reduction algorithm is adopted, and in combination with a sub-band energy entropy and a self-attention mechanism, non-stationary mechanical noise is effectively filtered out. A multi-rule feature extraction engine is used for extracting smooth residual errors, derivative mutation and other features, a support vector machine (DE-SVM) model introducing physical priori knowledge weights is constructed, and the small sample recognition problem is solved in combination with a virtual sample generation technology. The method can realize high-precision positioning and quantitative evaluation of steel strip damage under complex working conditions, and has the characteristics of strong anti-interference capability, high identification accuracy and good generalization performance.

The invention relates to the technical field of time length detection, and discloses a news simulcasting time length detection alarm method based on voice recognition, which comprises the following steps: S1, noise reduction: integrating an advanced digital signal processing technology and a professional noise reduction algorithm to form a refined processing system adaptive to'news simulcasting 'audio, according to the system, aiming at collected useless components such as environment noise and equipment noise, noise characteristics are captured through a multi-dimensional signal analysis model, an effective information core identifier is defined, a differentiated characteristic database of signals and noise is constructed, and a technician sets scientific noise reduction parameters according to the differentiated characteristic database. And accurate noise identification and stripping: integrating an advanced digital signal processing technology and a professional noise reduction algorithm, capturing noise characteristics through a multi-dimensional signal analysis model, accurately stripping environmental noise (such as studio echo and external interference sound) and equipment noise (such as sound recording equipment floor noise and transmission link electromagnetic interference), and simultaneously retaining the original texture of effective audio.

The invention discloses an off-line estimation method for an automobile active noise reduction nonlinear transfer function based on RNN (Recurrent Neural Network). Specific used models are LSTM (Long Short Term Memory) and GRU (Generalized Range Unit). For a specific vehicle model, offline acquisition and preprocessing of data, model training and deployment of the model to a specific audio DSP are carried out, a traditional vehicle active noise reduction algorithm (LMS, APA, LS and the like) assumes an acoustic path as a linear system (MA / ARMA model) which cannot adapt to the nonlinear characteristics of an actual acoustic path, and two RNN models of LSTM / GRU are adopted to carry out nonlinear transfer function estimation, so that the nonlinear characteristics of the acoustic path cannot be adapted to the nonlinear characteristics of the actual acoustic path. The nonlinear features of the acoustic path can be accurately represented, the in-vehicle noise suppression effect is effectively improved, and the acoustic experience of a driver and passengers is improved.

The present application relates to carbon emission source inversion calculation technical field, especially to a kind of construction site carbon emission source inversion calculation method based on atmospheric diffusion model.The technical scheme includes the following steps: constructing space diffusion model: the meteorological parameter of construction site is obtained by meteorological monitoring equipment, pollutant concentration distribution is calculated based on atmospheric diffusion model, the model is corrected vertical diffusion by introducing mirror source term;Data dynamic noise reduction: the original monitoring data are filtered, and the balance between noise suppression and real fluctuation reservation is balanced by dynamic adjustment algorithm;Iterative inversion calculation;Comprehensive verification: by theory simulation and actual detection combination.The present application realizes the accurate, efficient and low-cost inversion of construction site carbon emission source by dynamically coupling meteorological-emission model, adaptive noise reduction algorithm and multi-source verification mechanism, which provides reliable technical support for real-time carbon management, carbon trading and green construction.

The invention discloses a wireless remote control and data return device of a coal bunker cleaning machine, relates to the technical field of wireless remote control of coal bunker cleaning machines, aims to solve the technical problem that the type and residual quantity of coal accumulated in a traditional bunker cannot be accurately recognized, and comprises a field sensing module, a data processing module, a wireless transmission module and a remote control module. In a noise reduction unit of a data processing module, a wavelet noise reduction algorithm is used for processing image data acquired by an AI visual camera. Mist noise generated by dust interference can be effectively filtered out, key features such as edges and textures of coal deposits can be clearly reserved, the problem that viscous coal and wet powdery coal as well as blocky coal and viscous coal are difficult to distinguish manually is solved, the type difference and distribution condition of the coal deposits in the bin can be clearly captured, a high-quality image basis is provided for subsequent accurate recognition of the types of the coal deposits, and the coal deposits in the bin can be accurately recognized. And the coal deposit characteristics are judged no longer depending on subjective experience of operators. The problem that the type and residual quantity of accumulated coal in a bin cannot be accurately recognized is solved.

The application relates to the technical field of data noise reduction, and discloses a security alarm noise reduction method and system based on a data weaving technology, which comprises the following steps: based on a data weaving architecture, a unified logical data view is constructed; an AI-driven data intelligent agent component system is deployed, API and new data sources that change automatically are recognized and adapted, metadata, threat intelligence and infrastructure operation state information are fused; an attack chain panoramic graph and a behavior causal chain model are constructed; a semantic noise reduction algorithm, time series clustering analysis and a confidence score mechanism are used to remove duplicate alarms, identify false alarms and filter low-risk events for security alarms; and alarm deduplication, priority adjustment and linkage disposal strategy generation are carried out. The application solves the problems of alarm flooding, high false alarm rate and low processing efficiency in the existing security alarm system.

The application discloses a kind of based on improved SVD's dry-type air-core reactor optical fiber sensing noise reduction method, and improved SVD is proposed to be applied to distributed optical fiber sensing detection dry-type air-core reactor fault alarm system.Establish the backscattering model of temperature measurement system, add Gaussian white noise and utilize traditional threshold denoising and improved SVD denoising analysis signal-to-noise ratio, provide theoretical basis for experiment.Under existing conditions in laboratory, collect original anti-Stokes light with temperature information and Stokes light and obtain ratio data matrix by ratio, after remodeling data matrix, singular value decomposition reconstruction is carried out, then after remodeling matrix, the ratio signal with temperature information after denoising is obtained, into two-way demodulation formula to obtain demodulation temperature information, finally according to demodulation error, compare denoising effect, the present application can effectively reduce demodulation temperature error by noise reduction algorithm, improve system temperature measurement precision, compared with traditional wavelet denoising, improve system signal-to-noise ratio, avoid threshold selection uncertainty and other problems.

The present application discloses an array-based sound pickup method and device having continuously variable polar patterns. The method comprises: receiving a first audio from a unidirectional microphone and a second audio from an omnidirectional microphone, and calculating a gain coefficient; performing gain processing on the first audio on the basis of the gain coefficient to obtain a first gain-processed audio; performing delay alignment on the second audio to obtain an auxiliary audio; mixing the first gain-processed audio and the auxiliary audio according to a proportional value to obtain a mixed audio; and performing noise reduction on the mixed audio by means of a noise reduction strategy and the gain coefficient to obtain a corresponding target audio. The above method is used in conjunction with an array-based sound pickup device capable of continuously variable polar pattern adjustment; two or more microphones having different polar patterns are used to form a sound pickup array, and a specific microphone array algorithm is used to achieve wide-range continuously variable adjustment of pickup directivity; moreover, by means of an array-based post-processing noise reduction algorithm, a stronger noise reduction function than a conventional single microphone or simple array-based sound pickup is achieved.

The application discloses a depth map denoising method and system based on gradient correction, and belongs to the field of image denoising. A complete section of a foreground in a local image is selected, a control point set is selected on the complete section, a section model is constructed, and section gradient information is further calculated; then, the rest of the sections are traversed, the section gradient information of the last section and a dynamic programming algorithm are used to gradually correct the section of the current image, and the current interface gradient information is calculated for the calculation of the next section. The application is used for repairing error areas, and does not process non-error areas. The application can fill the holes in the image, and can also find abnormal points in the image caused by noise, and the abnormal points are repaired according to the gradient information. The section model is calculated only once, and is used for generating initial gradient information. In the process of traversing the image, the gradient information is continuously updated according to the minimum principle of corresponding items of adjacent sections of errors. The local image is only traversed once, and the effect can be achieved, so that the application is a high-efficiency denoising algorithm.

The application provides a sound source detection and positioning method, mainly comprising the following steps: splitting a multi-channel signal into a single-channel signal; using a CEEMDAN noise reduction algorithm for noise reduction processing; extracting FBANK features and GCC features from the single-channel signal after noise reduction respectively; training a CRNN network combined with category labels and position labels to obtain a sound source positioning detection model; splitting the online extracted samples according to channels; extracting FBANK features and GCC features from the single-channel signal after splitting respectively, and jointly inputting the comprehensive features into the sound source positioning detection model to obtain the estimation results of the sound source category and the estimation results of the position. The application reduces the influence of unknown noise on the sound source signal by carrying out noise reduction processing on the sound source signal with unknown noise distribution, and simultaneously uses a multi-task learning method for the sound source category and position, which can significantly improve the precision and reduce the complexity of the online prediction process.

The invention relates to the field of microphone noise reduction, and discloses a call noise reduction method and device based on an earphone, and a storage medium. The method comprises the following steps: acquiring an audio signal based on a noise reduction microphone; based on a preset noise reduction algorithm, performing noise reduction calculation on the audio signal to obtain an offset signal, and playing the offset signal based on a noise reduction loudspeaker; when an incoming call is received, a call microphone is triggered to acquire a call audio signal; judging whether a difference value between the call audio signal and the audio signal is greater than a preset disturbance threshold value or not; when the disturbance value is larger than the preset disturbance threshold value, a preset offset attenuation table is inquired according to the size of the offset signal, and an attenuation parameter corresponding to the offset signal is obtained; performing noise deduction on the call audio signal based on the attenuation parameter to obtain a human voice signal; and playing the human voice signal based on the call loudspeaker. In the embodiment of the invention, the call quality is not interfered while the noise reduction effect of the external noise is ensured, and the noise reduction of the call audio is realized at the same time.

The invention relates to the field of GIS equipment partial discharge detection, and particularly provides a hardware and algorithm combined GIS equipment partial discharge signal noise reduction processing method. The method comprises the following steps: innovatively building a hardware module; an intelligent noise reduction algorithm is optimally designed, and efficient noise reduction processing on the ultrahigh-frequency signals is achieved; wherein the hardware module comprises an EMI filter and is used for improving the anti-interference capability of the system and improving the anti-interference capability and accuracy of partial discharge signal processing through cooperative processing of hardware preprocessing and algorithm optimization analysis. The problem of difficulty in signal acquisition in a traditional signal processing method is solved, noise reduction processing of partial discharge signals is effectively realized, and reliable data support is provided for partial discharge fault analysis of GIS equipment.

This invention discloses an active noise reduction algorithm based on a convolutional-fuzzy neural network without secondary path sensors. The algorithm establishes a correlation model between noise sources at different locations within a vehicle and the noise in the target noise reduction area using a convolutional-fuzzy neural network. It calculates and fits a virtual error noise signal for the target noise reduction area, replacing the error signal obtained through secondary path sensors in traditional methods. This reduces the dependence of active noise reduction in large vehicle interior spaces on multiple secondary path sensors. Furthermore, the invention uses the virtual error noise signal as input to the fuzzy layer, iteratively calculating and identifying secondary paths, and outputting the optimal noise cancellation signal in real time, improving computational efficiency and enhancing the ability to handle nonlinear noise.

The application discloses an active noise reduction algorithm based on deep learning, which identifies and establishes primary and secondary physical paths through a path modeling module: an input tensor is constructed through a frequency domain feature extraction module, and a deep neural network is used for noise reduction processing. The network architecture adopts a multi-resolution coding structure, extracts fine frequency band features through parallel multi-scale convolution and SE channel attention mechanism, captures the time sequence dependence of noise signals in combination with an LSTM network, and realizes high-precision frequency domain reconstruction by using a frequency alignment cropping jump connection decoding structure. In addition, the algorithm introduces a physical constraint optimization module, which restores the network output to a time domain signal in the training stage, and constructs a physical acoustic loss function in combination with the acoustic response of the secondary path. The application can effectively model a complex sound field environment and improve the noise reduction performance of an active noise reduction system.

The invention discloses a low-delay AI noise reduction optimization algorithm based on a multi-core microprocessor. The low-delay AI noise reduction optimization algorithm comprises the following steps of 1, performing framing windowing and feature extraction on a voice signal; step 2, sending the characteristic value into a trained neural network to obtain a gain value; step 3, performing gain interpolation calculation on the gain and the frequency spectrum of the original signal after comb filtering, and outputting a frame of signal on a time domain by using inverse Fourier transform and speech synthesis; the method has the advantages that a neural network method in deep learning is combined, and a lightweight neural network is fused to only predict the gain and a small amount of control quantity of each frequency band; various deep optimization modes are used, the algorithm delay is reduced to 9ms, the noise reduction effect is good, and distortion is avoided; meanwhile, some defects of transplantation optimization of an end-to-end depth AI noise reduction algorithm at the present stage are overcome, the problems of high computing power and high time delay of an end-to-end large model on a resource / power consumption limited platform are avoided, and better deployability and robustness are achieved.

The invention provides a real-time self-adaptive noise reduction Bluetooth headset, which is characterized in that environment noise and ear canal residual noise are respectively acquired by a dual-microphone array at an included angle of 45 degrees, four scenes of traffic noise, human voice, wind noise and a quiet environment are identified in real time by an embedded lightweight convolutional neural network (parameter quantity is less than or equal to 5KB), and matched noise reduction parameters are dynamically loaded; an anti-phase sound wave is generated in combination with a self-adaptive feedback controller, system delay is compressed to 0.08 ms level by using an LMS filter with an adjustable step length mu, and a sound wave anti-phase physical limit is broken through; the noise reduction depth (static 40dB / walking 25dB) is dynamically adjusted according to the motion state through the six-axis sensor, and noise reduction is stopped within 0.5 second when the barometer detects that the earphone is taken off; the binaural exchanges noise data based on BLE 5.0, and executes a hybrid noise reduction strategy in an asymmetric scene. According to the scheme, the noise suppression depth is improved by 40% (the subway environment reaches 38dB), and the high-frequency phase deviation is lt; and the PESQ score of the binaural voice definition is 4.8 / 5.0, the power consumption of a motion scene is reduced by 35%, and the method is suitable for acoustic equipment such as TWS earphones and the like.

The invention discloses a voiceprint recognition and noise reduction system based on multi-array vibration sensors with different frequencies. The voiceprint recognition and noise reduction system comprises a multi-array vibration sensor module, an acoustic sensor module, an integrated controller and an algorithm module. Wherein the vibration sensor captures mechanical vibration characteristics of voiceprints, the acoustic sensor acquires voice signals, and the integrated controller adopts an STM32H747 microcontroller and supports multi-channel synchronous acquisition. The algorithm module comprises a vibration-acoustics double-channel feature extraction algorithm, a vibration-guided EFsLMS adaptive noise reduction algorithm, a dynamic multi-modal feature fusion mechanism and a double-judgment anti-counterfeiting mechanism, and the noise reduction process is guided through the vibration-guided EFsLMS adaptive noise reduction algorithm by using vibration signal features; the weight is automatically adjusted according to the signal energy ratio through a dynamic multi-modal feature fusion mechanism, identity verification is carried out through a double-judgment anti-counterfeiting mechanism in combination with the voiceprint similarity, the vibration mode matching degree and the semantic content difference degree, the voiceprint recognition precision in the noise environment is remarkably improved, and the system safety is enhanced.

The invention discloses a third harmonic microscopic imaging device with a three-dimensional rapid intelligent noise reduction function, which omits a complex and tedious processing process of an imaging sample by means of the imaging advantage of third harmonic, avoids photobleaching and light damage to the greatest extent, can rapidly image for a long time, and has the advantages of simple structure and high efficiency. Meanwhile, the optical slicing capability is crucial to acquisition of a three-dimensional image, and millimeter-level depth subcellular resolution microscopic imaging can be realized; according to the zero-sample unsupervised intelligent noise reduction algorithm, the obtained high-noise third harmonic microscopic image can be quickly subjected to noise reduction, the signal-to-noise ratio of the image is improved, and subsequent cell segmentation and counting tasks are facilitated.

The invention discloses a flight stage adaptive cockpit speech enhancement system based on multi-parameter fusion, and the system comprises a data collection module which collects key flight parameters in real time from an airborne data network of an aircraft; the flight stage recognition module is used for analyzing the input parameters of the data acquisition module, deducing the current flight stage in real time and judging whether a special situation is entered or not; outputting the stage code and the confidence coefficient to an adaptive speech enhancement module; and the adaptive speech enhancement module is used for selecting a proper noise reduction model to suppress the current noise according to the stage code and the confidence coefficient, and carrying out optimal scheduling through model hot switching and double-model mixed execution. According to the flight stage self-adaptive cockpit voice enhancement system based on multi-parameter fusion, the flight stage is automatically recognized by analyzing the flight parameters in real time, and a targeted noise reduction algorithm is dynamically called, so that the voice recording quality can be remarkably improved, and noise environments of different stages in the flight process can be well adapted.

The application discloses an image recognition system applied to condensate water fine treatment of a power plant, and particularly relates to the field of image recognition, and comprises an initialization module, a noise reduction module, an analysis module, a standardization module, a classification module, an evaluation module, a suggestion module and a feedback module. The initialization module is used for equipment deployment and basic data acquisition, and a three-dimensional space-time coordinate system is established. The noise reduction module is used for obtaining a water flow disturbance coefficient and a dynamic wavelet threshold value based on working condition parameters, and performing noise reduction processing on an original image. The analysis module is used for extracting static features and dynamic features of pollutant particles, and analyzing each feature parameter. The self-adaptive wavelet noise reduction algorithm is designed by fusing condensate water working condition parameters, the noise reduction threshold value is dynamically adjusted, the error of the static feature extraction of the pollutant particles is reduced, the accuracy of subsequent classification and recognition is significantly improved, and the misjudgment rate of fine components is effectively reduced.

An active noise reduction system for the passenger compartment (4) of a vehicle (1) includes: a reference sensor (16) designed to detect a noise reference signal indicating ambient noise to be eliminated; an error sensor (17) disposed within the passenger compartment (4) for detecting an error signal in a noise reduction area to achieve noise reduction feedback control; a loudspeaker (12) designed to reproduce sound within the passenger compartment (4); and a digital processing unit (14) designed to control the loudspeaker (12) to generate an anti-noise signal to be reproduced within the passenger compartment (4) through a noise reduction algorithm based on the reference signal, the error signal, and the determination of acoustic paths within the passenger compartment (4) to achieve noise reduction. In particular, the system has distributed intelligence, wherein the reference sensor (16) and / or the error sensor (17) have embedded digital processing capabilities and are configured to cooperate with the digital processing unit (14).

The invention is suitable for the technical field of audio processing, and provides a self-adaptive earphone active noise reduction method and device, and the method comprises the steps: a mobile terminal receives an in-ear noise signal transmitted by an earphone terminal; wherein the in-ear noise signal is a noise sound wave acquired through a feedback microphone after noise reduction processing is carried out on the basis of an initial anti-phase sound wave; according to a time domain saliency map corresponding to the in-ear noise signal, determining a sound wave rule feature corresponding to the in-ear noise signal; wherein the time domain significance map is used for identifying a specific acoustic event; and according to the sound wave rule characteristics, adjusting the initial reverse sound wave to obtain a target reverse sound wave, and sending the target reverse sound wave to an earphone terminal to perform noise reduction processing. Compared with a traditional fixed noise reduction algorithm, the real-time adaptability remarkably improves the noise reduction performance.

The present invention relates to the technical field of wireless communications. Disclosed are a surface acoustic wave device model coefficient extraction and simulation method and apparatus, and a related device. The method comprises the following steps: step S1, acquiring admittance parameters of a batch of surface acoustic wave devices; step S2, removing abnormal waveforms and random noise in measured curves by means of a filtering and noise reduction algorithm, so as to obtain true values of the measured curves; step S3, searching for feature information in the measured curves by using a moving window of a preset size in combination with a preset limiting condition; step S4, on the basis of a feature change relationship between the coefficient of a phenomenological model and each of the conductance of a conductance curve and the susceptance of a susceptance curve, sequentially optimizing all model coefficients step by step; and step S5, using a neural network model to develop a simulation method for surface acoustic wave devices within a preset structural dimension range and obtain a simulation result. The surface acoustic wave device model coefficient extraction and simulation method of the present invention can improve the accuracy of surface acoustic wave device simulation.

This invention proposes an image-based method, medium, and device for detecting NOx emissions from combustion, comprising: acquiring flame images of a furnace burner and preprocessing them using a bilateral filtering noise reduction algorithm; establishing an empirical formula to extract statistical features from the flame images; establishing a convolutional autoencoder to extract deep features from the flame images; using principal component analysis to reduce the dimensionality of the flame images and obtain principal component features; concatenating the statistical features, deep features, and principal component features into a comprehensive feature; establishing a fully connected autoencoder to extract high-level features from the comprehensive feature; inputting the extracted high-level features into a long short-term memory network to extract temporal features; introducing a self-attention mechanism to process the temporal features; and finally predicting and outputting the combustion NOx concentration. This invention can more accurately describe the combustion state of the flame, improve the ability to capture data change trends, enhance the generalization and adaptability of the model, and achieve accurate monitoring and prediction of combustion NOx emissions.

The present application relates to the technical field of computer vision, and especially relates to a boiler heating surface detection method and device, electronic equipment and storage medium. The present application applies the edge-preserving denoising algorithm and the adaptive contrast enhancement algorithm to image preprocessing, effectively suppresses noise while maintaining defect edge integrity, and performs brightness equalization processing, significantly improving the contrast and detail definition of images under non-uniform illumination conditions. At the same time, the defect recognition model is trained using the same preprocessing method as the detection stage, ensuring the consistency of the distribution of training data and detection data, so that the model can fully learn the optimized and enhanced defect features. The present application effectively overcomes the interference of the complex lighting environment of the boiler furnace on visual detection, improves the accuracy and robustness of defect recognition, and provides reliable technical support for unmanned aerial vehicle intelligent inspection of the boiler interior.

The invention discloses an amphibious vehicle propeller noise control system and method based on PID adjustment, and belongs to the technical field of automobile control, and the amphibious vehicle propeller noise control system based on PID adjustment combines a PID adjustment algorithm with an active noise reduction algorithm, monitors an external environment, adjusts dynamic variable parameters, and improves the noise reduction performance of the amphibious vehicle propeller. The control parameters are converted into propeller control parameters and active noise reduction module control parameters to control noise reduction parameters of an impeller adjusting mechanism and a microphone, and finally noise reduction signals processed through an algorithm are used for sending out reverse sound waves through a loudspeaker to reduce noise in a vehicle.

The invention discloses a self-adaptive Wiener filtering noise reduction method and system based on three-state classification voice activity detection and a storage medium, which are used for solving the technical problem of poor noise reduction effect of a voice noise reduction algorithm in an artificial cochlea in a non-stationary noise environment. According to the method, firstly, audio frames are divided into voice frames, mute frames and noise frames through improved voice activity detection, and time-frequency domain minimum value tracking is carried out to realize power spectrum estimation of noise; the system further introduces a noise environment change detection mechanism, dynamically evaluates noise stability, and adaptively adjusts parameters of the Wiener filter according to the noise stability. For different types of frames and frequency points, the system dynamically optimizes filtering parameters including a smoothing coefficient, a gain lower limit and a frequency band weight. Through the multi-stage adaptive processing mechanism, the method can realize higher voice signal-to-noise ratio and definition in a complex noise environment, and is suitable for single-microphone noise reduction of the artificial cochlea.

This invention relates to the field of hydropower equipment inspection, and in particular to a method and apparatus for temperature anomaly identification through dual-light image fusion of hydropower equipment. The method includes the following steps: acquiring infrared and visible light dual-light images of the hydropower equipment; using a rigid-flexible registration method based on feature points of key components of the equipment, combined with a noise reduction algorithm specific to humid environments, to generate a preprocessed dual-light image set; based on the preprocessed dual-light image set, extracting visible light texture features and infrared temperature grayscale features according to the temperature sensitivity of different detection parts of the hydropower equipment, generating a feature vector set representing the equipment status; based on the feature vector set, dynamically adjusting the fusion weights of the two types of features in conjunction with the real-time operating conditions of the hydropower equipment, and constructing a standardized fusion feature matrix adapted to the detection requirements after weighted fusion; dividing the standardized fusion feature matrix into a training set and a test set according to a preset ratio, and using oversampling optimization training to address sample imbalance.

The invention discloses a noise reduction method, a noise reduction device, electronic equipment and a computer program product. The method is applied to the noise reduction system, the noise reduction system comprises a time domain noise reduction module and a space domain noise reduction module, the time domain noise reduction module is realized based on an artificial intelligence model, the space domain noise reduction module is realized based on a preset noise reduction algorithm, and the time domain noise reduction module and the space domain noise reduction module adopt a series structure. The time domain noise reduction module and the space domain noise reduction module are provided with independent control switches. The method comprises the following steps: determining a current noise reduction scene; determining a target noise reduction module in the time domain noise reduction module and the space domain noise reduction module according to the noise reduction scene; and carrying out noise reduction processing on the collected current image frame through the target noise reduction module. According to the scheme of the invention, a good noise reduction effect can be realized in various scenes.

This invention discloses an audio dynamic noise reduction method, a computer-readable storage medium, and an electronic device, comprising: acquiring an original audio signal; extracting signal features from the original audio signal to obtain a feature audio signal; performing noise reduction processing on the feature audio signal using an audio dynamic noise reduction algorithm to obtain a valid audio signal, wherein the noise reduction processing includes amplifying, preserving, and suppressing the original audio signal; and outputting the valid audio signal. The audio dynamic noise reduction method, computer-readable storage medium, and electronic device provided by this invention can dynamically process audio signals, extract valid signals, filter out invalid signals, and make the sound sound smooth and mellow while preserving the complete details of the sound.