31 results about "Sound source identification" patented technology

The invention is applicable to the technical field of grouting of mining engineering and geotechnical engineering, and provides a grouting diffusion space real-time sensing and tracking method based on slurry dynamic sound source localization, which comprises the following steps: active enhancement and characteristic modulation of a slurry dynamic sound source; building a stereo wave sensing network and acquiring high-fidelity sound wave data; carrying out AI-driven slurry sound source identification and three-dimensional space positioning; and the grouting diffusion process is subjected to three-dimensional real-time visualization and intelligent early warning. The invention creatively provides a comprehensive solution integrating sound source active enhancement modulation, stereophonic sensing network, artificial intelligence deep noise reduction and three-dimensional space inversion positioning, and the core of the comprehensive solution lies in that slurry flow sound signals which are originally weak and difficult to use are actively enhanced and are endowed with features; a traceable slurry power sound source signal with a high signal-to-noise ratio is constructed, and three-dimensional space real-time sensing and visual tracking of the slurry diffusion frontal surface position and the overall diffusion range are realized in combination with an advanced signal processing and positioning algorithm.

The present application relates to the technical field of noise diagnosis, in particular to a method and device for identifying abnormal sound source applied to a vehicle transmission system, the method comprising: acquiring abnormal sound noise data, and confirming an abnormal sound generation period according to the abnormal sound noise data; acquiring transmission system vibration data, and performing time-frequency domain analysis on the transmission system vibration data and the abnormal sound noise data according to the abnormal sound generation period to obtain abnormal sound time domain data; the transmission system vibration data is obtained by vibration detection of the vehicle transmission system at a previous time; performing cross-correlation identification of the abnormal sound source according to the abnormal sound time domain data to obtain an abnormal sound source identification result; the abnormal sound source identification result is used to represent that the abnormal sound source is a gearbox and / or a drive axle. By considering the state of strong coupling connection between the gearbox and the drive axle in the vehicle transmission system, cross-correlation analysis is performed on the abnormal sound time domain data to identify the abnormal sound source, thereby improving the accuracy of identifying the abnormal sound source of the vehicle identification system.

This invention discloses a construction area vibration zoning control method based on multi-source sound identification, relating to the field of engineering construction control. The method includes: acquiring the coordinate positions of the target construction area and the railway track, and determining the upper limit of vibration intensity in the target construction area; determining the target set of construction equipment, and based on the construction movement line, determining the fixed positions of the foundation construction equipment set within the target construction area to form a foundation equipment layout scheme, and generating a foundation construction vibration distribution through multi-source sound identification analysis; performing vibration zoning on the foundation construction vibration distribution, and based on the vibration zoning results and the upper limit of vibration intensity, optimizing the equipment layout of the movable construction equipment set based on the foundation equipment layout scheme to generate a target equipment layout scheme. This solves the technical problem in existing technologies where regional vibration load imbalance prevents the optimal allocation of vibration energy in the construction area, leading to both low construction efficiency and potential safety risks.

This invention relates to a method and system for locating coaxial counter-rotating sound sources in rotorcraft, belonging to the technical field of sound source identification methods. It includes: processing the sound pressure signal of the moving sound source using continuous wavelet transform to obtain time-frequency domain variation results; performing Doppler effect correction based on experimental conditions; estimating the spatial location and relative intensity of the noise source using a cross-spectral matrix and weight vector; and performing phase-locked analysis of the rotor noise source intensity using a phase-locked averaging method. This invention differs from traditional time-domain delay superposition algorithms and frequency-domain cross-correlation spectrum methods. It can image unsteady sound sources using time-frequency domain characteristics, solving the acoustic imaging problem of counter-rotating propeller noise and possessing potential applications in the rotorcraft industry.

This invention discloses an FPGA implementation method for visual image processing of sound source identification, comprising: 1. Normalizing the sound intensity values ​​obtained from sound source identification and converting them into grayscale values; 2. Obtaining corresponding color pixel values ​​by performing three independent mappings on the grayscale values; 3. Upsampling the low-resolution color acoustic cloud map using an interpolation algorithm to improve the image resolution and form a visual acoustic cloud map that represents sound intensity in color. This invention enables the visual image processing of sound source identification to be implemented on an FPGA in the form of digital circuits, thereby improving the real-time performance of the entire sound source identification process, reducing the hardware complexity of the sound source identification platform, and saving time and hardware costs.

The invention discloses a rotating sound source recognition and positioning method based on a deep convolutional attention neural network, and belongs to the field of rotating sound source recognition, and the method comprises the steps: firstly carrying out the motion compensation and modal expansion of a sound pressure cross-spectrum matrix through a modal decomposition rotating beam forming algorithm, and generating a sound source distribution diagram in a rotating scene; then the sound source distribution map is input into a deep convolution attention neural network model, the model adopts an encoder-decoder structure, a channel and a space attention mechanism are fused, key sound source features are dynamically focused, noise interference is suppressed, and high-precision reconstruction of the sound source distribution map is achieved; and finally, carrying out local maximum value detection on a prediction map output by the network, and extracting a sound source space position. According to the method, the Doppler effect and phase distortion problems in rotating sound source positioning are effectively overcome, and the positioning precision, the anti-noise performance and the calculation efficiency in a complex rotating field are remarkably improved.

The invention discloses a scenarized audio recognition method and device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence sound signal processing. The method comprises the following steps: inputting a collected original audio waveform into a shared feature extraction network for feature extraction processing to obtain a first audio feature map; performing prior information processing based on the first audio feature map and the external input vector to obtain dynamic sound source prior information; the dynamic sound source prior information comprises an internal activeness label vector and an external sound source activeness vector; performing parameter generation processing according to the internal activeness label vector and the external sound source activeness vector to obtain a feature modulation parameter; performing affine transformation processing on the first audio feature map according to the feature modulation parameter to obtain a modulated second audio feature map; and inputting the second audio feature map into a sound source classifier for identification processing to obtain a sound source identification result. The environment dynamic adaptability and accuracy of scenarized audio recognition can be improved.

This application discloses an integrated monitoring boundary marker system based on multimodal sensing and redundant transmission, relating to the field of nature reserve monitoring technology. The system includes multiple boundary markers, each containing sensing and imaging equipment, a dual-power management unit, a sound source identification unit, a multi-source data fusion processing unit, and a multi-mode communication unit electrically connected to the system. This system can effectively monitor and accurately transmit monitoring data for protected areas with an average area of ​​82,000 to 83,000 hectares when only 58 to 59 boundary markers are used. It offers high monitoring reliability and reduces data mistransmission.

Soundproof chamber construction equipment (100, 200, 300), comprising: an audio procurement unit (101, 201) that procures audio data that includes audio from a variety of sound sources; a sound source identification unit (102, 202) which, based on the audio data, determines a plurality of sound source positions as positions of the plurality of sound sources; an audio extraction unit (103) that generates a multitude of pieces of extraction audio data by extracting audio represented by the audio data with respect to each sound source and generating the extraction audio data representing the extracted audio; a format conversion unit (104) that generates a multitude of stereophonic tones corresponding to the multitude of sound sources by converting a format of the multitude of pieces of extraction audio data into a stereophonic audio format; a position procurement unit (105) that procures a listening position as a position at which audio is listened to; a motion processing unit (106) that calculates an angle and distance between the listening position and each of the multitude of sound source positions; an angle-distance adjustment unit (107) that adjusts each of the plurality of stereophonic tones using the angle and distance according to each of the plurality of sound source positions, thereby producing a plurality of set stereophonic tones as a plurality of stereophonic tones at the listening position; and a superposition unit (108, 308) that superimposes the multitude of set stereophonic tones.

The method of operation of a wearable device according to the present invention comprises: a step in which a microphone array module acquires noise magnitude information and direction information; a step in which a wireless communication module transmits the noise magnitude information and direction information to an external cloud server via a user's smart device under the control of a processor; a step in which the wireless communication module receives noise source identification information and risk level information corresponding thereto from the external cloud server via the smart device under the control of a processor; a step in which the processor generates a control signal to provide at least one stimulus among vibration stimulation, electric stimulation, and visual stimulation by a light-emitting element to a user using at least one of the noise magnitude information, the noise direction information, the noise source identification information, and the risk level information corresponding thereto; and a step in which at least one of a vibration element, an electric stimulation array, and a light-emitting element operates to generate at least one stimulus according to the control signal.

The embodiment of the invention provides an acoustic horn immersion type sound field rendering method and system, and relates to the technical field of sound field rendering, and the method comprises the steps: obtaining a user position and a head posture in a virtual space; acquiring the position and intensity of a virtual space sound source; identifying a focus sound source currently concerned by the user according to the user position, the head posture, the sound source position and the intensity; identifying sound sources except the focus sound source as environment sound sources; performing sound field rendering on the environmental sound source to obtain a shared environmental sound field signal, the computing resource of the environmental sound source being lower than the computing resource of the focus sound source; performing convolution operation on the original audio signal of the focus sound source and the head acoustic transmission function to obtain a personalized high-resolution signal; and superposing the shared environment sound field signal and the personalized high-resolution signal to generate a binaural signal, and playing the binaural signal through an acoustic horn array. According to the method, the immersion and the actual effect of virtual reality training can be improved.

This application discloses a noise source identification method, apparatus, engineering equipment, and machine-readable storage medium, relating to the field of noise source identification technology. The method includes: acquiring near-field noise of a hoisting mechanism operating at different times; determining the vibration frequencies of various components of the hoisting mechanism at different times based on the drum rotation speed of the hoisting mechanism at different times; determining target times at each time based on abnormal frequencies in the near-field noise; determining target components based on all vibration frequencies and abnormal frequencies corresponding to the target times; and accurately identifying noise sources by locating the target components. When multiple target components exist, determining whether resonance exists between the target components based on the vibration frequencies of each target component at different drum rotation speeds; and generating noise source identification results based on the target components and resonance information when resonance exists. This provides a basis for optimizing the vibration and noise characteristics of the hoisting mechanism.

The invention discloses a method for positioning a pulse sound source under a strong harmonic background, which comprises the following steps of: arranging a microphone array in a sound field containing a pulse sound source to be detected to acquire a time domain sound pressure signal, performing continuous wavelet transform on the time domain sound pressure signal to obtain a wavelet coefficient matrix, and determining a characteristic frequency band with remarkable pulse signal energy based on a time frequency distribution diagram; performing inverse continuous wavelet transform on the wavelet coefficient matrix in the characteristic frequency band to obtain a pulse signal enhanced reconstructed wavelet time domain signal; and taking the reconstructed wavelet time-domain signal as input, reconstructing wavelet time-domain sound pressure on a sound source reconstruction surface by adopting a time-domain equivalent source method, identifying a pulse generation target moment according to the reconstructed sound pressure, generating a sound pressure cloud picture, and determining the position of a pulse sound source through the maximum sound pressure amplitude, thereby realizing positioning of the pulse sound source under the strong harmonic background. According to the method, the precision and reliability of pulse sound source positioning are remarkably improved, and an effective technical means is provided for transient sound source recognition and acoustic imaging in a complex sound field.

The application belongs to the technical field of acoustic measurement, and discloses a free space sound field measurement method and system, which constructs a free light path sound field measurement system based on the principle of Michelson interferometer; collects a reference image, introduces a sound field to be measured, performs translation and rotation scanning through a computer to control a loudspeaker or a laser beam, and completes interference pattern data collection; pre-processes the collected interference pattern, identifies the edge of the interference fringe by using edge detection technology, and calculates the light phase change amount; sound field reconstruction is performed by using a Radon inverse transform algorithm, sound field integral information carried by the laser beam is converted into the sound pressure value of each point in the real space, and a free field sound pressure distribution map is reconstructed. The application has the advantages of non-destructive and low cost, and significantly improves the sound field measurement accuracy and the integrity and reliability of reconstruction, can effectively capture the nanometer level optical path change caused by the sound field, and ensures the high accuracy of sound field measurement and the accuracy of sound source identification.

This invention provides a method, apparatus, and storage medium for multi-source sound recognition based on depthwise separable convolution, relating to the field of audio signal processing technology. The method acquires raw audio data containing multiple sound source signals and environmental noise within a target monitoring area using a microphone array. This data is then standardized to obtain standardized time-domain audio data. Feature transformation and filtering are performed on this data to obtain characteristic audio data. A lightweight convolutional backbone network, trained on-the-fly, extracts high-dimensional features layer by layer. A hybrid pooling strategy, combining global average pooling and global max pooling, is then used to aggregate global features, resulting in aggregated feature vectors. Finally, classification and coordinate regression processing are performed to output sound source classification results and three-dimensional spatial coordinate data. This invention achieves integrated multi-source sound recognition and localization in complex environments with lightweight deployment, adapting to diverse application scenarios.

The invention relates to the technical field of machine learning, in particular to a sound source recognition method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a target sound source; performing sound source analysis on the target sound source to obtain a target sound source positioning feature of the target sound source, a target noise feature of the target sound source and a target transmission physical feature of the target sound source; performing acoustic feature extraction on the target sound source based on an acoustic feature extraction layer of a target sound source recognition model to obtain a target acoustic feature of the target sound source; and inputting the target sound source positioning feature, the target noise feature, the target transmission physical feature and the target acoustic feature into a sound source classification layer of the target sound source recognition model for classification and recognition to obtain a classification and recognition result of the target sound source. The scene adaptability and accuracy of sound source recognition in different environments can be improved.

The invention discloses an active coherent plane wave silencing device and a sound source identification method. The device comprises a sound wave guide tube designed according to the highest frequency of a target sound wave, a main sound source sound pressure signal acquisition module, a signal analysis processing control unit, an adjustable power amplifier and a secondary sound source. The sound wave guide tube converts spherical waves or cylindrical waves into plane waves through a cut-off section or an adjustable section structure; the signal analysis processing control unit identifies the characteristic parameters of the main sound source through time-frequency transformation and phase inversion calculation and generates a control signal; the secondary sound source generates interference sound waves with the same frequency and opposite phases as the main sound source, and the two form surface contact interference in the conduit to counteract target sound energy. Plane wave interference is achieved through the sound wave guide pipe, real-time sound pressure monitoring and a self-adaptive algorithm are combined, sound wave parameters are dynamically adjusted, wide-band and multi-sound-source type self-adaptive noise elimination can be achieved, and sound energy counteracting efficiency and system stability are remarkably improved.

The invention discloses a distributed optical fiber sound source identification and classification method fused with an i-vector algorithm, relates to the technical field of distributed optical fiber sound sources, and aims at solving the problem of reducing the identification efficiency of the distributed optical fiber sound sources by setting a plurality of environment detection point locations in a sound source identification environment and detecting the background noise intensity of each point location. Emitting reference sound waves, collecting sound wave absorption amount, calculating sound wave absorption characteristics, analyzing a sound source recognition state, and screening target point locations based on the recognition state to perform sound source recognition; the method comprises the following steps: playing to-be-identified optical fiber sound source information at a target point location, counting the number of storage types and the total occupied space, calculating a to-be-identified range, setting an acquisition time window, acquiring volume at a plurality of time points, calculating volume fluctuation, and judging whether the sound source information is introduced into an i-vector algorithm for processing or not by combining the identification range, so that the processing environment of the i-vector algorithm is guaranteed, and the processing efficiency of the i-vector algorithm is improved. And the distributed optical fiber sound source identification efficiency is improved.

The invention provides a three-dimensional dereverberation beam forming method and system based on a cross-correlation matrix, and relates to the technical field of sound source recognition, and the method comprises the steps: collecting sound pressure data through a spherical microphone array; performing fast Fourier transform on the sound pressure data to obtain corresponding frequency domain data; calculating a cross-spectrum matrix corresponding to the spherical array according to the frequency domain data; eliminating reflected sound components contained in the cross-spectrum matrix to obtain a filtered cross-spectrum matrix; and drawing a sound source identification cloud picture based on the filtered cross spectrum matrix. According to the three-dimensional dereverberation beam forming method based on the cross-correlation matrix, the technical problem of insufficient sound source recognition precision of a spherical array in a complex sound field environment in the related technology is solved.

This invention discloses a sound source identification method and system based on the nonlinear harmonic phase conjugation method (PCD). The method involves acquiring the sound pressure gradient time-domain signal of the target sound source using a pre-constructed planar microphone array. After performing a fast Fourier transform on the sound pressure gradient time-domain signal to obtain the sound pressure gradient frequency-domain signal, a sound pressure gradient frequency-domain signal that meets the resolution requirements for reconstructing the sound field is selected as the higher harmonic sound pressure gradient signal. The sound field of the target sound source is reconstructed by establishing the phase conjugation method and the higher harmonic sound pressure gradient signal using dipole source emission based on the sound pressure gradient time-domain signal. This allows personnel to identify the target sound source through the reconstructed sound field. This method improves the resolution of sound field reconstruction by using the nonlinear harmonic phase conjugation method for sound source identification and is not limited by the near-field limitation of evanescent waves.

The application provides a driving blind area detection and early warning method and device, a storage medium and a vehicle. The method comprises the following steps: performing sound source identification on a plurality of first sound signals of a vehicle by using a voiceprint recognition hierarchical algorithm to obtain at least one sound source and a sound source type of the sound source; determining a three-dimensional space coordinate of the sound source relative to the vehicle according to a collection time of the plurality of first sound signals; performing data fusion on the sound source type corresponding to at least one sound source, the three-dimensional space coordinate and other sensor data of the vehicle to obtain environment perception information, wherein the environment perception information comprises target information of at least one target around the vehicle; determining that the target is a potential collision risk according to the environment perception information, and controlling the vehicle to perform a warning operation, so that the cost and technical complexity of driving blind area detection can be reduced.

This invention belongs to the field of sound field reconstruction and sound source identification technology. It discloses an equivalent source sound field localization method and system based on sparse sound intensity measurement. The method involves acquiring complex sound pressure and complex particle velocity at measurement points on a holographic surface using a vector sensor array, and calculating the measured sound intensity vector. A sound intensity transfer matrix is ​​constructed based on the equivalent source method, establishing a linear measurement equation between the measured sound intensity vector and the equivalent source intensity vector. Utilizing the spatial sparsity of the equivalent source intensity, the solution for the equivalent source intensity vector is transformed into an L1 norm sparse optimization problem, solved using a convex optimization algorithm to obtain the optimal equivalent source intensity vector. Based on the optimal equivalent source intensity vector, the acoustic quantities at any point in the target sound field are reconstructed using a free-field Green's function. This invention utilizes the active component of the sound intensity vector to suppress uncorrelated noise and combines compressed sensing theory to improve the ill-conditioned nature of the inversion, achieving highly robust and accurate sound source localization and sound field reconstruction without the need for a reference microphone.

The application discloses a distributed optical fiber sound source identification and classification method fusing an i-vector algorithm, relates to the technical field of distributed optical fiber sound sources, and is used for reducing the identification efficiency of the distributed optical fiber sound sources. A plurality of environment detection points are arranged in a sound source identification environment, background noise intensity of each point is detected, a reference sound wave is emitted and sound wave absorption is collected, sound wave absorption characteristics are calculated and sound source identification states are analyzed, and target points are screened based on the identification states to identify the sound sources. Sound source information of an optical fiber to be identified is played at the target points, the number of storage types and the total occupied space are counted, an identification range is calculated, a collection time window is set, volume is collected at a plurality of time points, volume fluctuation is calculated, and whether the sound source information is input into an i-vector algorithm for processing is judged in combination with the identification range, so that the i-vector algorithm processing environment is ensured, and the identification efficiency of the distributed optical fiber sound sources is improved.

The invention provides a lightweight convolutional network sound source identification method based on dependency graph pruning and channel distillation. Comprising the following steps: calculating a 64 array sound source distribution diagram under a function beam forming algorithm by using a sound pressure cross-spectrum matrix, and jointly inputting the sound source distribution diagram and a sound source position label into a dense connection full convolutional neural network for pre-training; components in the pre-trained network model are grouped through a dependency graph, a pruning part is accurately identified and cut off, and a network lightweight target is achieved on the premise of keeping the overall architecture of the network stable; taking a dense connection full convolutional neural network as a teacher network, taking the pruned network as a student network, and extracting intermediate features of the two networks to implement channel distillation to obtain a model after distillation; and detecting the number of sound sources by predicting the sound source distribution diagram, and determining the specific position of the sound source according to the local maximum value. According to the method, the positioning performance of the original network model is basically maintained, and meanwhile, the parameter quantity and the calculation quantity of the network model are effectively reduced.

The present disclosure provides a method for synchronous processing of sound source identification and distance estimation, comprising: obtaining underwater acoustic data of a target sea area; performing data preprocessing on the underwater acoustic data of the target sea area to obtain target feature data; obtaining a multi-task learning model based on transfer learning trained in advance; inputting the target feature data into the multi-task learning model based on transfer learning, and determining the sound source category and sound source distance value corresponding to the target feature data through the output result of the multi-task learning model based on transfer learning. Thus, by combining the multi-task learning model and the transfer learning model, a multi-task learning model based on transfer learning is constructed, which can simultaneously identify the underwater sound source category and the underwater sound source distance estimation.

The invention discloses a Newton orthogonal matching pursuit deconvolution beam forming sound source identification method. The method comprises the following steps: 1) establishing a sound source identification model; 2) using a sound source identification model to preliminarily estimate a single sound source position coordinate and a corresponding average sound pressure contribution; 3) performing local optimization on the initially estimated position coordinates of the single sound source and the average sound pressure contribution; 4) performing global optimization on all identified sound source positions and average sound pressure contribution until an iteration termination condition is met; and 5) carrying out orthogonal solution on the average sound pressure contribution of all the identified sound sources, and completing sound source identification when the number of the identified sound sources reaches an estimated value. The NOMP-DAMAS method provided by the invention not only is clear in imaging result, but also has good adaptability to a sound source deviating from a focus point, can accurately position the sound source and accurately quantify the sound pressure contribution of the sound source, realizes high-efficiency and high-precision sound source recognition, is small in influence of grid spacing on the performance, and is stable in sound source recognition performance.

The application discloses a display method and a display device, wherein a camera can rotate within a preset angle range, a controller is configured to acquire person sound source information collected by a sound collector and perform sound source identification to determine sound source angle information for identifying an azimuth angle of a position where a person is located; based on a current shooting angle of the camera and the sound source angle information, a target rotation direction and a target rotation angle of the camera are determined; and the shooting angle of the camera is adjusted according to the target rotation direction and the target rotation angle, so that a shooting area of the camera is directly opposite to a position where the person is located when the person speaks.

This improves the accuracy of sound source localization processing, targeting the desired sound source within the sound pickup space. [Solution] The sound source localization device includes: performing a sound source localization process to estimate the position of a sound source based on the acoustic signals of the sound pickup space picked up by a sound pickup device placed in the sound pickup space where multiple sound sources may exist; performing a sound source tracking process to track the position of the sound source within the sound pickup space based on the results of the sound source localization process; performing a sound source identification process to identify the type of sound source based on the results of the sound source tracking process; and performing the sound source localization process by correcting parameters based on the acoustic signals used for the sound source localization process.

The invention discloses a microphone array sound source identification method based on generalized sidelobe cancellation and linear discriminant analysis joint optimization. The method comprises the following steps: constructing a joint optimization framework comprising a front-end sound source enhancement module and a rear-end identification module; a parallel generalized sidelobe cancellation structure is adopted at the front end to enhance a sound source signal, and a joint optimization matrix is introduced into a lower branch to receive feedback of an identification module; carrying out feature projection on the enhanced signal at the rear end by adopting linear discriminant analysis; by coupling a joint optimization matrix and a linear discriminant analysis projection matrix, the two modules are alternately optimized in an iterative mode, so that the enhanced output retains identification key features while suppressing interference. According to the method, the problem of optimization target mismatch of the front-end enhancement module and the rear-end identification module based on microphone array signal processing is effectively solved, and reliable identification of parallel sound sources with random arrival directions can be realized in an outdoor multi-sound-source concurrent scene with limited training data.