225 results about "Sound source location" patented technology

The invention relates to the field of gas leakage identification, and discloses a gas leakage identification method and system based on sound localization, a medium and equipment, and the method comprises the steps: collecting a leakage sound wave signal through a microphone array, and extracting acoustic features in a complex background; simulating a diffusion process of gas in a turbulence environment after gas leakage through an established leakage gas convection-diffusion model, and combining gas concentration distribution in the simulated diffusion process with acoustic characteristics to predict sound source localization at a leakage position; modeling a sound source localization search process as POMDP, and iteratively updating a confidence state of a sound source position through a particle filter; spatial distribution features are extracted from the confidence state through DBSCAN clustering to serve as input of the LSTM-DQN network, spatial and temporal features are fused through the constructed LSTM-DQN network, cross-scene generalization is achieved through transfer learning, and sound source coordinates are dynamically optimized and output through the Q network. According to the invention, the positioning accuracy and real-time performance in a complex environment are improved.

The invention belongs to the technical field of sound source processing, and provides a sound source positioning and detecting method and device. The method comprises the following steps: acquiring delay estimation of microphones I and II and delay estimation of microphones I and III based on a three-path linear uniform microphone array; based on the delay estimation sum, respectively carrying out positioning calculation under near-field and far-field conditions; according to the sound source distance under the near-field condition, comparing the sound source distance with a distance judgment threshold value, and determining a far-field / near-field output sound source position; and carrying out feature extraction on the signals of any microphone array, and carrying out event classification based on a pre-trained convolutional neural network. According to the method, far / near field model selection is carried out according to the distance judgment threshold, large deviation generated by a single model in a critical region is avoided, continuous and stable positioning from short distance to long distance is achieved, time classification can be achieved while position calculation is carried out, and integrated output is achieved.

The invention relates to the technical field of data processing, in particular to a three-dimensional live-action model construction system for building structure demolition and reconstruction. The system extracts event combinations with obvious transfer correlation features for localization and analysis of dangerous sound sources. Through simulation of transmission of test waves in an initial acoustic slowness field, a most probable dangerous sound source position for generating a current event combination under each test wave is obtained by using an objective function optimization solution method. And further performing statistics on simulation information of all test waves, establishing a residual curve, screening out a brittleness event position based on feature extraction, and adjusting a slowness value in a current voxel through various parameters corresponding to the brittleness event position in an initial acoustic slowness field. Through the dynamic correction method, the obtained corrected acoustic slowness field can more effectively represent the specific change of the building structure in the dismantling process, so that the internal damage can be more clearly quantified.

The invention discloses a conference sound reinforcement system based on an AI intelligent algorithm and 360-degree omni-directional noise reduction, and relates to the technical field of audio signal processing, the conference sound reinforcement system comprises a conference management center, the conference management center is in communication connection with the following modules: a multi-sound-source sensing module used for capturing 360-degree omni-directional sound field information in a conference environment and constructing a sound source space distribution model; according to the invention, the omnidirectional microphone array unit covers all directions of a conference space, synchronously collects audio data streams, eliminates the limitation of a conventional unidirectional microphone, combines the sound source positioning space mapping unit, constructs a sound source space distribution model based on the time difference of arrival and the phase difference through a deep learning model, and improves the sound source positioning accuracy. The azimuth angle, pitch angle and distance parameters of the sound source are accurately analyzed, the position of the sound source is mapped to a virtual space coordinate system, a dynamically updated 3D sound source distribution diagram is generated, the position change and intensity distribution of the sound source are reflected in real time, and the positioning precision in a complex acoustic environment is remarkably improved.

The invention relates to an equipment health optimal monitoring point selection method and system, and relates to the field of equipment monitoring, and the method comprises the steps: collecting sound signals of monitoring points around monitored equipment; determining a signal spectrum and a signal attenuation based on the sound signal; determining a sound source position according to the signal spectrum and the signal attenuation; calculating a signal-to-noise ratio based on the signal spectrum, matching and determining a noise reduction level, and weighting according to the noise reduction level and the sound source position to obtain a comprehensive score; calculating a comprehensive score in combination with the sound source position and the noise reduction level; according to the monitoring points and the sound signals, calculating a fluctuation ratio, and screening out a position with the fluctuation ratio smaller than a stable threshold value and higher than a score threshold value in the comprehensive score as a secondary monitoring point; determining the position distribution of secondary monitoring points according to the sound source position and the equipment structure; and selecting a point location with the maximum coverage degree from the position distribution, and determining the point location with the highest coincidence degree as the optimal point location based on matching of the signal spectrum and the fault spectrum. The application has the effects of improving the monitoring effect and realizing high-precision monitoring.

The invention discloses a multi-voice separation method based on a lightweight dual-path Transform network, and the method comprises the steps: collecting audio multi-voice data, and carrying out the preprocessing of the data, and forming a data set; the method comprises the following steps: constructing a dual-path Transform network model DPTNet, and introducing a recurrent neural network to optimize the dual-path Transform network model DPTNet; and training the dual-path network model DPTNet, and performing engineering deployment based on the trained model. The method is beneficial to obtaining higher-quality audio fingerprint recognition capability, sound source separation capability and voice enhancement function, can be used for tracking and positioning the position of a sound source, helps positioning and tracking related applications, can be expanded to the medical field, can be used for heart sound segmentation, namely, recognition of specific signals of the heart, and can be applied to the field of medical science. The method helps to diagnose cardiovascular and other medical problems, and has technical innovation and practical application value.

The invention relates to a digital conference voice processing method, system and device and a storage medium, and the method comprises the following steps: carrying out the pickup of a conference voice, obtaining a mixed voice signal, carrying out the framing sampling, and forming a voice sampling sequence; carrying out sound source direction estimation based on the sequence to obtain multi-sound-source position information, and carrying out beam forming and spatial filtering on the voice sampling sequence according to the multi-sound-source position information to obtain a sound source separation signal; performing voice segment segmentation on the signal to obtain a voice segment sequence, extracting voiceprint features of each segment, and generating a speaker feature mark; and performing time sequence recombination on the voice fragment sequence by using the mark, constructing a speaking time sequence table, selectively outputting the voice fragment sequence according to the table, and finally generating clear and ordered conference voice. The technical problems that due to the fact that a traditional voice processing method lacks effective space-voiceprint joint constraint, voice separation is not thorough, identities of speakers are confused, and the speaking time sequence is disordered are solved.

The invention discloses a sound source localization method and device based on an improved generalized cross-correlation algorithm and a medium, and belongs to the field of sound source localization, and the method comprises the steps: collecting a sound source signal through a quaternary cross sensor array; constructing an improved weighting function according to the sound source signal; wherein the improved weighting function is obtained by weighted summation of a phase transformation weighting function and a maximum likelihood weighting function; performing generalized cross-correlation operation according to the sound source signal and the improved weighting function to obtain time delay; and performing geometric operation in the three-dimensional rectangular coordinate system based on the time delay to obtain a sound source position. Therefore, the accuracy and robustness of sound source localization can be improved in a low signal-to-noise ratio environment and a strong reverberation environment by implementing the method and the device.

The invention relates to the field of microphone sound reception, in particular to a precise sound reception system and method based on double microphone arrays and 3D visual identification, and the system comprises a sound source positioning module, a visual identification module, an audio processing module, a sound reception control module and a precise tracking module. The visual identification module is used for calculating the listening angle of the microphone array, the audio processing module is used for obtaining the sound arrival time difference of each microphone, the sound reception control module is used for outputting the position of a target sound source, and the precise tracking module is used for enabling the camera to track the target sound source. The method is advantaged in that requirements of real-time interaction scenes are satisfied, sound reception capability of the microphone array in complex scenes is improved, good robustness and accuracy are realized, sound source positioning precision and dynamic tracking capability are improved, and environment adaptability and real-time performance of microphone sound reception are improved.

The invention discloses a multi-modal speech enhancement method and device based on a deep learning model, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining the head posture data, binaural audio signals and visual context information of a user in a virtual reality environment, coding the binaural audio signals into three-dimensional space acoustic features, and carrying out the coding of the three-dimensional space acoustic features; and extracting virtual sound source position features and lip motion features from the visual context information, inputting the features into an immersive fusion enhancement network, selectively enhancing or inhibiting acoustic features from different spatial directions, generating an enhanced audio stream, and outputting the enhanced audio stream through a binaural rendering engine. According to the method, the technical problems that in the prior art, due to the fact that multi-modal prior information cannot be effectively fused, voice enhancement lacks spatial selectivity, and an interference sound source irrelevant to vision is difficult to restrain are solved, and head posture dynamic attention and lip motion cross-modal constraint are fused; the technical effects of natural binding of auditory attention and a visual focus and effective suppression of an interference sound source are achieved.

The embodiment of the invention discloses an information processing method and device, electronic equipment and a computer readable storage medium, and relates to the technical field of augmented reality. The method comprises the following steps: separating single-person voices corresponding to a plurality of sound source positions from mixed voices; determining character features of a plurality of characters under the plurality of spatial positions; determining a first association relationship between the single-person voice and the character features and a second association relationship between the translated text and the character features; when the scene backtracking function is started, playing the stored mixed voice and scene image; when the sight line of the wearer focuses on the played virtual character, obtaining a target first association relationship and a target second association relationship corresponding to the playing moment, and further obtaining a target single-person voice and a target translation text of the virtual character at the playing moment; and playing the voice of the target single person, and displaying the target translated text space at the position of the virtual character. Therefore, according to the scheme, the user can obtain more effective information through scene backtracking.

The invention relates to a multi-source intelligent combined pose measurement method for a floating hydrophone array, and the method comprises the following steps: 1, obtaining the pose information of each node of the hydrophone array through a multi-source sensing module, and synchronously receiving sound signals and extracting the TDOA information of each node under the condition that the sound source position is known; step 2, constructing a measurement equation based on TDOA information, and performing inverse solution on the position of each node of the hydrophone array in combination with a hyperbolic positioning principle and a sound velocity model; according to the method, an inverse solution positioning mode of'known sound source position and inverse solution of receiving array node position 'is adopted, a flexible underwater acoustic array dynamic measurement scene under the traction of a floating platform is specially aimed at, the technical limitation that traditional TDOA and USBL positioning depends on a fixed geometric structure is broken through, the method does not need to arrange a plurality of reference receiver arrays, and the positioning accuracy is improved. And a high-precision synchronous clock system is not needed, and high-precision acoustic positioning can be realized only by depending on a single sound source and the distributed nodes, so that the system complexity and the field deployment cost are remarkably reduced.

A sound source positioning device based on multi-microphone and time difference algorithm, the device comprises a sound signal acquisition module, a signal processing module, a positioning and communication module, a display module and a power module; the sound signal acquisition module adopts multiple output analog signal microphones to realize omnidirectional acquisition of sound signals; the signal processing module takes a single-chip microcomputer as the core and integrates analog signal amplification, filtering, peak detection, analog-to-digital conversion and time difference algorithm processing functions; the positioning and communication module combines a Beidou positioning module and a mobile communication module to realize sound source position determination and remote data transmission; the power module stably supplies power to each module in multiple gears. The present application combines multi-microphone cooperative acquisition with the time difference algorithm to improve the accuracy and stability of local single-point sound source positioning and can be applied to security monitoring, environmental monitoring, industrial inspection and other scenes.

The invention provides a sound wave propagation spatial distribution and sound source position control method, and relates to the technical field of loudspeaker control, and the method comprises the steps: building an analysis control model based on a sound source and a propagation auxiliary object; constructing a first area of sound wave propagation of the sound source in the analysis control model, and marking a second area of spatial distribution of sound wave propagation of the current sound source; mapping the target position to an analysis control model to generate a mapping point location; when the mapping point is in the second area or the mapping point is not in any first area, the sound source position is not controlled; and when the mapping point location is not in the second area but is in any first area, determining a target sound source in the first area, and determining a sound source position control parameter based on the control library correspondingly associated with the target sound source and the mapping point location. According to the sound wave propagation spatial distribution and sound source position control method, sound delivery is carried out according to the position of a film viewer, and the viewing experience of the film viewer is guaranteed.

The application discloses a near-field strong interference suppression method based on spherical wave deconvolution beam forming positioning, which comprises the following steps: performing fine grid division on a near-field scanning area of a linear array; performing spherical wave focusing beam forming on the near-field scanning area and two-dimensional deconvolution beam forming about distance-angle under the condition of unknown sound source position; calculating the distribution entropy characteristics of the deconvolution beam forming result in the angle dimension, and using a preset threshold to correlate the interference positioning of a target; constructing an array flow pattern matrix A of each near-field target l and generating a covariance matrix A; calculating the orthogonal complement space projection matrix of the covariance matrix A, and applying the orthogonal complement space projection matrix to the array element domain covariance matrix C to perform near-field interference suppression; using a far-field plane wave model to perform deconvolution beam forming calculation on the covariance matrix for suppressing near-field interference, so as to obtain passive detection results of the near-field strong interference suppression. The application can realize near-field interference positioning and interference suppression under the condition that the interference position is unknown.

To provide an inspection device capable of locating a position of an abnormal sound source even if an abnormal sound of a rotating machine has periodicity.SOLUTION: An inspection device includes: multiple microphones detecting sound generated from each of multiple rotating machines; a sound waveform processing unit obtaining a feature amount of a sound waveform detected by the multiple microphones; an abnormality detection unit detecting an abnormal sound on the basis of the feature amount; a waveform time difference calculation unit calculating the minimum time difference of sound waveforms among the multiple microphones; and an abnormal sound source position locating unit locating a rotating machine that generates an abnormal sound from among the multiple rotating machines on the basis of the minimum time difference.SELECTED DRAWING: Figure 1

The application provides a device sound source position determination method based on a multi-sensor acoustic array imaging, and belongs to the technical field of sound field imaging, and comprises the following steps: S1, acquiring microphone sensor array experimental data; S2, data preprocessing and calculating sample covariance matrix; S3, performing characteristic decomposition and determining the number of sound sources; S4, preliminarily judging the sound source parameter range to determine the iteration initial value, and calculating the power parameter initial value corresponding to each sound source; S5, estimating noise variance S6, calculating the characteristic value and characteristic vector theoretical value of the sound source subspace; S7, solving S+1 dimensional nonlinear equation set to obtain the estimation result. The application can take the positions and powers of multiple sound sources as parameters to be estimated, model the sound pressure signal covariance matrix, then perform characteristic decomposition on the covariance matrix to obtain the characteristic value and characteristic vector theoretical value.

This application relates to a conference screen processing method, device, storage medium, and system. It involves acquiring multiple audio data streams using a data acquisition device, determining the sound source location information based on the first audio data stream where the human voice energy exceeds a first threshold, acquiring the image corresponding to the sound source location information, identifying the speaker in the image whose human voice energy meets preset conditions, and obtaining the facial deflection angle between a preset position representing the speaker's face and the data acquisition device. The speaker's image and facial deflection angle are then sent to a data processing device. The data processing device can display the image of the speaker with the smallest facial deflection angle using a display device. This eliminates the need for the data processing device to expend significant computing resources for image recognition, reducing its computational resource consumption and improving the efficiency of displaying the speaker's face at the conference.

The present application relates to a kind of multi-sensor wideband sound source positioning method suitable for deep-sea reliable sound path environment, utilize the same sound source D-SR time delay measurement value observed by deep-sea large depth multi-sensor to carry out three-dimensional positioning to sound source.In the first stage, based on the position of each sensor, depth, observed D-SR time delay and water body sound velocity profile information, a matrix and a vector are constructed, there is a linear relationship between the two and the position of sound source, the least square method is used to solve this linear relationship, obtain the estimation result of the two-dimensional position of sound source, based on two-dimensional position estimation result, the depth estimation result of sound source is obtained using depth solution formula;In the second stage, based on the three-dimensional position of sound source estimated in the first stage, the D-SR time delay value of the position of each sensor is predicted, then an auxiliary variable matrix is constructed, and new sound source two-dimensional horizontal position estimation result is obtained according to the rule of auxiliary variable estimator (IVE), and finally the final sound source depth estimation result is obtained according to depth solution formula.

To acquire an ROI image excellent in image quality.SOLUTION: An image processing system comprises: a setting part that sets an attention region including a sound source position or a sound source direction, in an acquired image acquired by an image acquisition part, on the basis of the sound source position or the sound source direction, identified by using a sound signal acquired from a sound acquisition part; and a change part that changes characteristics of an image of the attention region, by image processing based on image information within the attention region.SELECTED DRAWING: Figure 2

The invention discloses a steel plate slitting cutting parameter correction method and system, a medium and a program product, and relates to the field of intelligent monitoring devices.The method comprises the steps that initial cutting parameters and a quality judgment benchmark are obtained, and a slitting unit is started; acquiring real-time sound data of a slitting unit and real-time image data of the edge of the steel strip; identifying an abnormal sound event, and determining a sound source position as an abnormal cutter position; extracting a target edge image corresponding to the abnormal tool position from the real-time image data, determining a quality defect of the abnormal tool position, and generating a defect confidence coefficient corresponding to the quality defect; when the confidence coefficient of the quality defect event exceeds a preset confidence threshold value, generating a parameter adjustment instruction according to the sound feature of the abnormal sound event and the geometric defect type of the target edge image; and correcting the cutting process parameters of the slitting unit based on the parameter adjustment instruction. By implementing the method, the adjustment response time of the production line to the abnormal cutting state can be shortened.

Methods and vehicle with sound visualization are provided. A vehicle includes a graphic projection display; exterior microphones mounted to the vehicle; and a processing device programmed to receive audio signals from the exterior microphones; retrieve map data in a region around the vehicle; identify from the audio signals a sound of interest; identify a location of a source of the sound of interest; determine a stationary status or a moving status of the source; when the source has the moving status, determining a direction and speed of movement of the source; ascertain from the map data and from the location, stationary status, moving status, direction, and / or speed, a preferred driving maneuver; determine a graphic exemplifying the preferred driving maneuver; and display the graphic upon the graphic projection display.

The invention provides a deep learning-based human mouth shape and voice matching recognition method, which comprises the following steps of: recognizing respective speaking mouth shape characteristics of all people in a surrounding environment through an image, and recognizing a sound source position and an audio characteristic of the surrounding environment through a pickup array; according to the speaking mouth shape features, correcting the sound source position so as to separate the audio features to obtain the subordinate audio features of each person; performing deep learning on the audio features and the speaking mouth shape features of each person to obtain voice information sent by each person; carrying out background noise processing on the voice information to obtain the speaking voice and the text content of each person; personnel around the hearing aid in a noisy environment are identified in a visual and voice recognition mode, voice of the personnel is recorded and converted, the cocktail problem of the hearing aid in far-field recognition is effectively solved, voice interference is effectively restrained, and voice recognition accuracy and definition are improved.

The present disclosure relates to a method and device for acoustically imaging fan noise, an electric vehicle charging pile, and a storage medium. The method comprises: acquiring a noise time-domain signal generated by a fan when the fan is running; performing time-frequency conversion on the noise time-domain signal based on a short-time Fourier transform algorithm to obtain a noise frequency-domain signal; inputting the noise frequency-domain signal into a delay-and-sum beamformer to perform beamforming to obtain beam data; positioning principal component data of the beam data to obtain sound power data; and generating a sound image containing a sound source position according to the sound power data. In this embodiment, the resolution of the noise can be improved by positioning the principal component of the beam data, which achieves the effect of accurately positioning the sound source position and is conducive to obtaining a more accurate sound image.

According to the room acoustic parameter determination method and device, the electronic equipment, the wearable equipment and the storage medium provided by the invention, the reverberation time in the acoustic scene is determined, and the acoustic scene comprises the listener position, the sound source position and the room property; the reflectivity of each reflecting surface in a room with room properties is determined through random light tracing and reverberation time, the random light tracing is used for determining a light propagation path reaching a listener, and the light propagation path reaching the listener represents a propagation path of light emitted from a sound source position of the room and received by the listener at the listener position; the descent curve of the reverberation energy can be determined through the reverberation time, and the random light tracing result is corrected based on the descent curve of the reverberation energy, so that the reflectivity of each reflecting surface in a room is corrected, and a more real spatial audio signal can be generated based on the estimated reflectivity of each reflecting surface.

The present application discloses a method, device, equipment and medium for determining the distance of a deep-sea sound propagation convergence zone, belonging to the field of marine acoustic technology. The method comprises: obtaining the water depth data and corresponding sound speed at the boundary of each layer of seawater in the target sea area, and constructing a three-layer broken line model of the sound speed profile; constructing a first circular arc trajectory group and a second circular arc trajectory group based on the three-layer broken line model, the sound source position of the target sea area and Snell's law; determining the first critical sound ray trajectory and the second critical sound ray trajectory of the deep-sea convergence zone of the target sea area based on the first circular arc trajectory group and the second circular arc trajectory group; determining the convergence zone distance of the target sea area based on the first critical sound ray trajectory and the second critical sound ray trajectory. This method improves the calculation efficiency of the deep-sea convergence zone distance.

The present application relates to a kind of all-weather power grid equipment abnormal sound monitoring device and its sound source positioning method, belong to the technical field of power equipment online monitoring and fault diagnosis.The device includes: multiple microphone units, each microphone unit includes microphone body and the e-PTFE sound-permeable film covered on its surface, for efficiently permeating sound wave while blocking wind and rain erosion;Multiple three-legged stand poles with water-blocking umbrella covers, at least one microphone unit is arranged on each stand pole, and is distributed around the power grid equipment to be monitored;Data processing unit;And solar power supply module and protection cabin.The method includes: setting loudspeaker array at the suspected abnormal sound source position, using exponential sine sweep method to measure the frequency response function matrix of loudspeaker to microphone unit;After removing the loudspeaker, based on the measured frequency response function matrix and the sound pressure signal collected in real time, the abnormal sound source signal is extracted and the path contribution is calculated using the transfer path analysis method based on regularization.

Provided are an environmental sound pass-through method and apparatus applied to VR, a device and a storage medium. The method includes the steps below. Environmental audio information of an ambient environment is acquired by a microphone on a VR device based on a see-through mode of the VR device. The environmental audio information is located to determine sound source position information according to the time difference of the environmental audio information reaching microphones on the VR device, and a filtering process is performed on the environmental audio information to determine filtered audio information. Directional pickup is performed on the filtered audio information to determine to-be-processed audio information according to the sound source position information. A signal amplitude and pass-through loudness of the to-be-processed audio information are adjusted to determine target audio information, and the target audio information is played by a speaker of the VR device.

The application discloses a wind direction control method and an air conditioner. The method comprises the following steps: obtaining at least two control commands from different sound source positions, wherein each control command comprises control information, and the control information is used for indicating whether the wind blows towards the sound source position; determining the swing angle value of the air deflector of the air conditioner at each sound source position according to the control information in each control command; determining the target swing angle value corresponding to the at least two control commands according to the swing angle value of the air deflector at each sound source position; and performing the wind direction control operation according to the target swing angle value. The technical scheme provided by the application aims to solve the problem of low wind direction control accuracy in the prior art.

The invention relates to the technical field of audio analysis, and discloses an intelligent microphone system based on environmental adaptation and a noise reduction method, and the system comprises a microphone array, an audio analysis module, an audio tracking module, a feature correction module and a parameter adjustment module. The noise reduction method corresponds to the system. According to the application, the target signal and the noise signal are acquired by the microphone array in a labor division manner, and accurate first-time noise reduction is realized by combining the audio analysis module; the audio tracking module monitors the position change of the sound source in real time and updates the characteristics, and ensures that the noise characteristics dynamically adapt to the position movement of the sound source; the feature correction module performs continuous dynamic correction based on real-time noise features; the parameter adjusting module actively avoids an interference area according to the noise position, so that the pickup parameter is adaptive to the environment change, the definition and anti-noise stability of the target signal in the complex dynamic environment are remarkably improved, the contradiction between target signal acquisition and noise suppression is effectively balanced, and the method is suitable for various complex scenes with frequent sound source movement.