Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

474 results about "Sound intensity" patented technology

Sound intensity, also known as acoustic intensity, is defined as the power carried by sound waves per unit area in a direction perpendicular to that area. The SI unit of intensity, which includes sound intensity, is the watt per square meter (W/m²). One application is the noise measurement of sound intensity in the air at a listener's location as a sound energy quantity.

Tunnel fire air curtain smoke prevention control method and system

The invention discloses a tunnel fire air curtain smoke prevention control method and system, and relates to the technical field of intelligent fire fighting, and the method comprises the steps: building a digital twinborn prediction model, and generating a fire source position coordinate and a smoke diffusion trend prediction map through multi-physics field coupling simulation; analyzing the stability requirement of the air curtain jet flow through a Brapare-Prandtt boundary layer analysis algorithm, and generating a jet flow enhancement requirement parameter table in combination with temperature gradient correction; optimizing an acoustic vortex main frequency band by adopting a Slodhaar number, and generating an acoustic vortex control parameter set in combination with a matched sound pressure level and a configured resonator phase difference; and converting the acoustic vortex control parameter set into an execution instruction, monitoring the jet velocity, the vortex street stability and the smoke retardation effect in real time, and dynamically correcting the parameters of the digital twinborn prediction model. According to the method, physical quantity outline matching of the blocking intensity and the sound pressure level is achieved through the sound intensity-momentum equivalent method, and the optimal phase configuration is determined in combination with POD modal analysis.
Owner:ANHUI ZHONGYI NEW MATERIAL TECH CO LTD

Sound standardization evaluation system for multi-dimensional acoustic parameter and emotional scene dynamic analysis

The invention provides a sound standardization evaluation system for multi-dimensional acoustic parameter and emotional scene dynamic analysis, and aims to realize structured and objective evaluation of voice performance. The system comprises an audio acquisition module, an audio processing module, a standard evaluation module and an integration processing module. The audio processing module performs noise reduction, pre-emphasis, sampling rate adjustment, framing and slicing operation on the original voice data; the standard evaluation module executes character and pronunciation accuracy analysis, acoustic basic skill feature evaluation or emotion and scene adaptation degree analysis based on multi-modal fusion according to an evaluation type set by a user; parameters including fundamental frequency, formant, sound intensity, fundamental frequency perturbation, amplitude perturbation and the like are extracted in evaluation, and classification prediction is completed in combination with a machine learning model; and finally, the integration processing module generates an evaluation report including a scoring result, question prompts and personalized training suggestions, and provides closed-loop feedback to support sound training and expression optimization.
Owner:GUANGZHOU SENJI SOFTWARE TECH CO LTD

Sound source orientation identification method based on three-array-element miniature microphone array

The invention belongs to the technical field of sound source positioning, and particularly relates to a sound source orientation identification method based on a three-array-element miniature microphone array. According to the method, sound source localization is converted into a deep learning classification task by extracting a microphone array sound intensity feature map. The method comprises the following steps: firstly, on the basis of a three-array-element differential microphone array, extracting orthogonal sound intensity features and converting the orthogonal sound intensity features into an RGB sound intensity spectrogram; secondly, designing a new lightweight neural network to meet the requirements of sound source localization and deployment; and finally, the horizontal plane sound source orientation is divided into different angle categories, a sound intensity spectrogram data set is made and sent to a neural network for training and testing, and a sound source orientation recognition result is obtained. Compared with the prior art, the feature map and the network model provided by the invention have better robustness in a high reverberation environment, the azimuth recognition angle precision is high, the calculation complexity is low, and the method is not influenced by voice characteristics.
Owner:NANJING TECH UNIV

Sound source imaging calculation method and system, electronic equipment, storage medium and computer program product

The invention provides a sound source imaging calculation method and system, electronic equipment, a storage medium and a computer program product, and the method comprises the steps: carrying out the preprocessing of obtained audio data, so as to obtain a center frequency in a scanning frequency range, and the audio data are collected through a microphone array; sound intensity grids are divided within the visible range of the video collection device. And determining an Euclidean distance matrix and an array steering vector from the microphone array to the sound intensity grid. And obtaining an output power spectrum matrix according to the array steering vector and the cross-spectrum matrix. And coloring the sound intensity grids to obtain a thermodynamic diagram. The sound source imaging method is optimized and innovated by utilizing the parallel computing capability of the CUDA technology, the accurate positioning of the sound source is realized, the processing speed and the positioning precision of the CUDA architecture model are improved, and powerful technical support is provided for the development of the sound source imaging field.
Owner:NR ELECTRIC CO LTD +1

Vehicle-mounted voice identification and positioning intelligent early warning system and method

The invention discloses a vehicle-mounted voice identification and positioning intelligent early warning system and method, and relates to the technical field of vehicle-mounted intelligent early warning. The system comprises a sound detector module which collects an audio signal of a surrounding environment in real time, and a sound recognition module which analyzes the audio signal through a deep learning model and recognizes a sound source type. And the calibration module performs space-time calibration to ensure data synchronization and alignment of the sensors. The positioning module combines time difference of arrival (TDOA) and a sound intensity attenuation model, and optimizes sound source positioning through particle swarm optimization (PSO) and extended Kalman filter (EKF) technologies. The risk assessment module assesses the collision risk based on the sound source position, the shielding state and the object type, gives an alarm to a driver in time through the early warning module, and automatically triggers a deceleration instruction. And the self-learning module dynamically adjusts the early warning sensitivity and the noise compensation coefficient through a federated learning framework updating model. The environmental adaptability of the vehicle-mounted early warning system is improved, and the vehicle-mounted early warning system has remarkable safety improvement and wide application prospects.
Owner:RIVOTEK TECH (JIANGSU) CO LTD

Sound signal feature optimization method for analysis and recognition of underwater small target object

The invention belongs to the technical field of underwater small target object analysis and recognition methods, and particularly relates to a sound signal feature optimization method for underwater small target object analysis and recognition. Comprising the following steps: 1, acquiring and processing original data; 2, eliminating interference line spectrums, and intercepting and splicing by adopting a time window to obtain a time recombination sound signal; using range transformation to optimize signal amplitude characteristics; processing the sound signal by using an FIR digital high-pass filter; obtaining an optimized signal by using a homomorphic filter; 3, extracting structural features, energy features, frequency features and sound intensity features of the optimized digital signals; step 4, sound signal feature fusion: carrying out underwater target sound signal feature fusion processing based on a canonical correlation analysis method; the invention provides a method for extracting effective sound signal data of an underwater target under the background of optimizing a complex marine environment, enhancing signal effectiveness during long-distance detection, and constructing effective sound signal features capable of being used for classification and recognition of the underwater target at the same time.
Owner:NAVAL UNIV OF ENG PLA

Method and system for constructing electrolysis energy consumption model and storage medium

The invention relates to the technical field of model construction, in particular to a construction method and system of an electrolysis energy consumption model and a storage medium. The method comprises the following steps: collecting electrolysis process parameters by using a multi-mode sensor system, wherein the electrolysis process parameters comprise a current value, a voltage value, an electrolyte temperature and electrolysis time; constructing an electrolysis energy consumption initial model based on the electrolysis process parameters, and inputting the electrolysis process parameters into the electrolysis energy consumption initial model to output a unit product energy consumption value and a current-voltage efficiency curve; electrolytic bubble acoustic monitoring is conducted on the side wall of the electrolytic cell to obtain bubble breakage acoustic wave signals; and analyzing the sound intensity and the rupture frequency of the bubble rupture sound wave signal. According to the method, through the multi-modal sensor, multi-dimensional signal analysis and dynamic parameter correction, the defects of single data and static state of a traditional electrolysis energy consumption model are broken through, and high-precision dynamic modeling and optimization of energy consumption in the electrolysis process are achieved.
Owner:SHENZHEN JINGHENGYU ENVIRONMENTAL TECH CO LTD +1

Acoustic coalescence elimination method for hydrogen bubbles in molten aluminum

The invention provides an acoustic coalescence elimination method for hydrogen bubbles in molten aluminum, and belongs to the technical field of molten aluminum bubble elimination. According to the method, sound field collaborative focusing is achieved by arranging a phase control array transducer set in a molten aluminum smelting furnace, primary gathered sound waves and efficient coalescence sound waves are applied in stages according to bubble size evolution in a double-frequency scanning mode, and the hydrogen bubbles in the molten aluminum are eliminated. A target frequency is dynamically adjusted in combination with a bubble resonance frequency optimization model to match the inherent frequency of a bubble, a sound-bubble coupling dynamic tracking system is used for monitoring bubble evolution triggering stage switching in real time, and a sound field focus point dynamically scans and covers a three-dimensional space area through phase delay control. A delay detection method is adopted to eliminate cavitation bubble interference and accurately measure the hydrogen content, sound intensity and frequency parameters are optimized according to a sound field parameter self-adaptive regulation and control model, and the technical problem that hydrogen bubbles in a molten aluminum deep area are difficult to be effectively driven by sound waves and cannot be fully coalesced and eliminated is solved.
Owner:QINGDAO UNIVERSAL ALUMINUM IND CO LTD

Aircraft noise source positioning method

The invention discloses an aircraft noise source positioning method comprising the following steps: sound field signals are collected, and the sound field signals comprise sound pressure signals and three-dimensional particle vibration velocity signals; preprocessing the sound pressure signal and the three-dimensional particle vibration velocity signal to obtain frequency spectrum data; inputting the frequency spectrum data into a trained noise recognition model, and judging a noise event; when the noise event is judged to be aircraft noise, noise source positioning is carried out according to corresponding spectrum data; according to the invention, noise event identification can be carried out firstly, so that the influence of the sound source arrival direction and other noise sources is eliminated, and errors are avoided; and the sound pressure and the three-dimensional particle vibration velocity are collected for preprocessing, effective sound intensity signals are obtained for positioning, and the positioning precision is improved.
Owner:HANGDA LVYI (TIANJIN) TECH CO LTD

New medicine application of local injection acoustic response stent to enhancement of ultrasound histotripsy

The invention discloses a new medicine application of a local injection acoustic response stent in enhancing ultrasound histotripsy. The acoustic response scaffold (ARS) comprises a scaffold material, fluorocarbon gas or liquid fluorocarbon particles with liquid-vapor phase change capacity, and microbubble cloud in the scaffold generates a strong cavitation ablation treatment effect in a target area under the action of low-frequency and low-sound-pressure ultrasound. Fluorocarbon gas or liquid fluorocarbon particles contained in the ARS form microbubble cloud and ideal cavitation nuclei under low-frequency low-sound-pressure ultrasonic excitation, inertia cavitation resonance is achieved under the ultrasonic action, and then cavitation mechanical damage with local tissue controllable strength is generated. The low-intensity ultrasonic histotripsy has the characteristics of low sound pressure, low sound intensity, high targeting property, small tissue damage outside a target region, simplicity in instrument manufacturing and the like, and the targeting property and the safety of treatment are improved. The method does not need very accurate ultrasonic focusing, reduces the operation difficulty, and has application prospects in multiple medical fields such as prostatic hyperplasia, tumor ablation and tumor immunotherapy.
Owner:刘政 +1

Low-power-consumption intelligent recording system based on keyword triggering and control method thereof

The invention provides a low-power-consumption intelligent recording system based on keyword triggering and a control method thereof, and relates to the technical field of intelligent audio processing, and the method comprises the following steps: the system is regularly awakened in a low-power-consumption standby state, and audio is collected and keyword identification is carried out; when a preset keyword is detected, the system enters a continuous recording mode and transmits audio data to a storage module in real time; after recording is finished, the system compresses, encrypts and stores audio data, and selects a proper sleep mode according to the current battery state; the system also supports wakeup by sound intensity or timer. Through an adaptive power consumption control algorithm, a multi-stage dormancy mechanism and an efficient data compression technology, long-time, stable and efficient recording work under a low-power-consumption condition is realized, and the system and the method are suitable for various application environments such as campus security and business scenes.
Owner:KEEN GUY (SHAOXING) TECHNOLOGY CO LTD

Sound source direction finding positioning method and system oriented to complex environment

The invention relates to the technical field of voice processing, in particular to a sound source direction-finding positioning method and system for a complex environment, and the method comprises the steps: serializing the sound intensity of each microphone, and calculating a maximum receiving interval according to the distance between adjacent microphones, the sound transmission speed and the sampling frequency; the method comprises the following steps: determining a short-time audio similarity through moving a sound source signal sequence, extracting a sound source synchronization sequence and a sound source same-frequency sequence, and further evaluating a tone quality deviation degree; optionally selecting a reference microphone, and comparing the reference microphone with a sound source synchronization sequence of other microphones to obtain a time delay data length and a sound source similar sequence; based on the arrangement values of the same position elements of the sound source similar sequence, a sound intensity distribution sequence is obtained, and the sound intensity interference degree of each microphone is obtained; and determining a fixed beam direction and calculating the distance between the reference microphone and the sound source. The invention aims to improve the accuracy of sound source positioning.
Owner:SUZHOU AUDITORYWORKS CO LTD

Containment boundary cable hole plugging and leakage detecting method

PendingCN119132660AGuaranteed tightnessAvoid the problem of difficulty in accurately recording reference sound intensity valuesNuclear monitoringElectric cablesMechanics
The invention particularly relates to a containment boundary cable hole plugging and leakage detecting method. The method comprises the steps that a test piece is manufactured; measuring and fitting net sound intensity values and leakage rates of leakage points with different apertures on the hole plugging surface of the test piece to obtain a relation curve of the net sound intensity values and the leakage rates of the leakage points; measuring the net sound intensity value of each leakage point of the containment boundary cable hole plugging surface, and calculating the net sound intensity value and leakage rate of each leakage point of the containment boundary cable hole plugging surface in combination with the net sound intensity value and leakage rate relation curve of the leakage point; determining a final leakage rate value of each leakage point of the containment boundary cable hole plugging surface; and adding the final values of the leakage rates of the leakage points of the containment boundary cable hole plugging surface to obtain the leakage rate of the containment boundary cable hole plugging surface. According to the containment boundary cable hole plugging leakage detection method, accurate measurement of the sound intensity value of containment boundary cable hole plugging and semi-quantitative leakage rate detection of containment boundary cable hole plugging are realized.
Owner:CNNC LONGYUAN TECH CO LTD +1

Neural regulation and control system based on alpha wave closed-loop flour noise stimulation

The invention discloses a nerve regulation and control system for closed-loop pink noise stimulation based on alpha waves. The nerve regulation and control system comprises a real-time sleep monitoring module, a data quality detection module, an alpha wave intensity calculation module, an alpha wave rising edge detection module and a pink noise regulation and control module. The rising edge of the alpha waveform is monitored through a personalized morphological waveform monitoring algorithm, the Alpha wave activity of the brain is adjusted through closed-loop pink noise stimulation in the specific rising stage, meanwhile, the sound intensity of pink noise can be adjusted in a self-adaptive mode, accurate sound stimulation is provided, the sleeping experience of a user is improved, and the sleep experience of the user is improved. Compared with a traditional sleep aiding system, the sleep aiding system has the advantages that the sleep aiding system based on the Alpha waves not only can improve the speed of falling asleep, but also can improve the overall quality of sleep, and has wider applicability and practical significance.
Owner:XIAMEN DNAKE INTELLIGENT TECH CO LTD

Sound insulation material matching parameter adaptability regulation and control method and device based on environmental characteristics

The invention relates to the technical field of sound insulation material proportioning parameter regulation and control, in particular to a sound insulation material proportioning parameter adaptability regulation and control method and device based on environmental characteristics, and the method comprises the steps: constructing an initial sound intensity fitting curve according to an initial center sound intensity set, carrying out the fitting precision verification of the initial sound intensity fitting curve, and if the precision verification value is not greater than a fitting precision threshold value, determining that the sound insulation material proportioning parameter is not greater than the fitting precision threshold value; if the precision check value is greater than a fitting precision threshold value, constructing an iteration center sound intensity set according to the initial center sound intensity set and the supplementary center sound intensity set, and reconstructing an initial sound intensity fitting curve, if the precision check value is greater than the fitting precision threshold value, performing sound intensity sound insulation calculation to obtain a target sound insulation curve set, and extracting an optimal sound insulation curve from the target sound insulation curve set, according to the optimal material matching parameters, sound insulation material matching parameters are regulated and controlled. The problems that an existing sound insulation material is low in noise reduction adaptability and poor in sound insulation effect can be solved.
Owner:JINZHONG HONGXU SHENGFA THERMAL INSULATION MATERIAL CO LTD

Speech emotion recognition method and system

The invention relates to the technical field of speech recognition, and particularly discloses a speech emotion recognition method and system. According to the method, time domain feature information, frequency domain feature information and channel domain feature information are acquired, sound intensity, timbre feature values and voiceless rate are acquired according to the time domain feature information, the frequency domain feature information and the channel domain feature information, finally, comprehensive association value feature values are acquired according to the sound intensity, the timbre feature values and the voiceless rate, and finally, the sound quality is improved. The emotion timbre keyword is extracted according to the comprehensive association value feature value, and the emotion timbre keyword is compared with a preset emotion timbre definition library to obtain an emotion timbre definition, so that the keyword is mapped to a specific emotion category by comparing the preset emotion timbre definition library, and the emotion timbre definition is obtained. Therefore, emotion features of the voice in the appeal process can be obtained through emotion recognition, and the real intention of the voice content can be obtained through emotion tone definition.
Owner:HANGZHOU JET-VOICE SCI & TECH CO LTD

Demisting water-saving natural ventilation wet cooling tower and working method

The invention discloses a demisting water-saving natural ventilation wet cooling tower and a working method, the cooling tower comprises a cooling tower body, a filler, a water distribution system, a dehydrator and a plurality of sound wave generators are arranged in the cooling tower body, and the sound wave generators are mounted at the upper part and the nearby area of a water distribution tank maintenance channel in the cooling tower; the sound wave generators are distributed in a high-humidity air flow area, a high-water-drop-content area, a medium-humidity air flow area and a medium-water-drop-content area. The sound wave generator adjusts the frequency and the sound intensity to the maximum extent according to the water drop characteristics, the environmental conditions and the water collecting efficiency; a certain proportion of water is recycled according to different working conditions through the sound wave water collecting technology, waste of water resources is effectively reduced, and the water saving effect is more prominent when the unit operates at low load; and meanwhile, when the water is recovered, the generation of fog plumes around the cooling tower is reduced, the surrounding environment is improved, and the potential influence of the fog plumes on peripheral equipment and facilities is reduced.
Owner:JINAN DANENG POWER TECH +1

GIS equipment defect three-dimensional visual positioning method based on acoustic imaging

The invention discloses a GIS equipment defect three-dimensional visual positioning method based on acoustic imaging, and relates to the related technical field of GIS equipment, and the method comprises the steps: constructing a sound intensity detection dual system; sound source signals of the GIS equipment are synchronously acquired, and near-field acoustic signals and far-field acoustic signals are output; performing frequency band separation through a self-adaptive band-pass filter, and identifying near acoustic abnormal features and far acoustic abnormal features of the separated frequency band; carrying out spatial positioning fusion and outputting a positioning point; and importing a GIS equipment three-dimensional model according to the sound source fusion positioning point, and outputting a GIS equipment visual positioning result. The technical problems that in the prior art, the GIS equipment defect detection range is limited, the positioning precision is insufficient, the defect space position is difficult to visually present, the equipment defect positioning is not rapid and accurate enough, and the equipment operation and maintenance efficiency and reliability are affected are solved. The technical effects of quickly and accurately positioning the equipment defects and effectively improving the operation and maintenance efficiency and reliability of the equipment are achieved.
Owner:BAIHE POWER SUPPLY BUREAU OF GUANGXI POWER GRID CO LTD

Acoustic response luminescent composite nanomaterial and preparation method and application thereof

The invention discloses an acoustic response light-emitting composite nanomaterial as well as a preparation method and application thereof, and belongs to the technical field of light-emitting composite nanomaterials. The acoustic response luminescent composite nano material provided by the invention comprises hollow mesoporous silica nano particles and europium-doped barium titanate nano particles loaded on the surfaces of the hollow mesoporous silica nano particles and in mesopores; the chemical formula of the europium-doped barium titanate nanoparticles is BaTiO3: Eu < 3 + >; the mass ratio of the hollow mesoporous silica nanoparticles to the europium-doped barium titanate nanoparticles is 1: (0.8-1.5). The sound response luminescent composite nano material provided by the invention can realize detection of sound intensity, and has good temperature stability, and meanwhile, the preparation method is simple and low in cost.
Owner:BIOGENOUS BIOTECH INC

Sound wave soot blower for electrostatic dust collector

The utility model relates to the technical field of sound wave dust removal, and discloses a sound wave soot blower for an electrostatic precipitator, the electrostatic precipitator comprises a dust removal chamber, a plurality of stages of electric fields connected in series are arranged in the dust removal chamber, the sound wave soot blower comprises a compressed gas source, a resonant cavity high-sound-intensity sound wave generator, a sound wave sound transmission horn and an adjustable valve, the top of each electric field is provided with a plurality of resonant cavity high-sound-intensity sound wave generators, each resonant cavity high-sound-intensity sound wave generator is connected with the compressed gas source through a gas pipeline, and the adjustable valve is connected to the input end of the resonant cavity high-sound-intensity sound wave generator. The sound wave transmission horn is connected to the output end of the resonant cavity high-sound-intensity sound wave generator; according to the resonant cavity high-sound-intensity sound wave generator, the sound wave intensity and starting and stopping of the resonant cavity high-sound-intensity sound wave generator can be achieved by adjusting the opening degree and opening and closing of the valve, then the sound wave intensity of different electric fields can be adjusted and controlled, and the flexibility is high.
Owner:润电能源科学技术有限公司

Moving target Doppler compensation coherent detection method based on single vector hydrophone

The invention provides a moving target Doppler compensation coherent detection method and system based on a single-vector hydrophone, and the method comprises the steps: S1, collecting a receiving signal of the single-vector hydrophone, and carrying out the segmentation of the receiving signal, and obtaining segmented data; s2, estimating a scale factor of the received data of the current segment according to the segmented data; s3, compensating the corresponding segmented data according to the scale factor to obtain a compensated signal; and S4, performing coherent accumulation processing on the compensated signal to obtain a sound intensity detection result, namely signal-to-noise ratio gain. The scale factor is a Doppler coefficient. Based on the improvement of a conventional sound pressure Doppler compensation method, in view of the advantages of the vector hydrophone, a new moving target Doppler compensation coherent detection method based on the single vector hydrophone is provided, and the detection performance of the single vector hydrophone on the moving target is improved.
Owner:SHANGHAI MARINE ELECTRONIC EQUIP RES INST (NO 726 RES INST OF CHINA STATE SHIPBUILDING CORP)

Vehicle door control method and device, electronic equipment and vehicle

The invention discloses a vehicle door control method and device, electronic equipment and a vehicle, and belongs to the technical field of vehicles. The method comprises the steps that when the vehicle senses an external knocking action, the environment sound intensity is detected; the response feasibility of the knocking signal is determined according to the environment sound intensity to control the vehicle door to be opened. According to the method, a user can unlock and open the vehicle door only through simple knocking without traditional key or key operation, the method is particularly suitable for the situation that a heavy object is held by hand or the key cannot be easily taken out, whether the knocking signal is responded or not is determined according to the environment sound intensity, false triggering can be reduced, high accuracy of knocking to open the door in the complex environment is achieved, and the user experience is improved. And the trouble that the user can take effect and is invalid when knocking to open the vehicle door is reduced.
Owner:BYD CO LTD

Woodworking machine tool noise sound power level measuring method based on sound intensity method

The invention discloses a woodworking machine tool noise sound power level measurement method based on a sound intensity method, and belongs to the technical field of machine tool noise measurement, and the method specifically comprises the steps: determining a housing surface covered by a tool rotation plane projection as a main sound radiation region, and determining a main bearing pedestal installation surface as an infrasound radiation region; sound pressure, vibration acceleration signals and dynamic air pressure signals of a main sound radiation area are collected; resampling a dynamic air pressure signal rotation angle domain, extracting a reference pneumatic pulsating waveform synchronous with tool tooth sweeping, and establishing an airflow induced sound pressure model according to the reference pneumatic pulsating waveform and a phase relation; calculating a surface normal vibration speed according to the vibration acceleration, and establishing a structure radiation sound pressure model in combination with a sound wave equation; decomposing the sound pressure signal to obtain two types of component estimation values, and performing parameter optimization to obtain net sound intensity of a main sound radiation area; extracting vibration frequency band energy of an infrasound radiation area, calculating equivalent sound intensity by combining a sound radiation efficiency model, and outputting a total sound power level by space integration; the invention provides an effective method for accurately measuring and controlling the noise of the woodworking machine tool.
Owner:FUJIAN PROV AGRI MACHANIZATION INST

Video editing method and system based on multi-modal large model collaboration

The invention discloses a video editing method based on multi-modal large model collaboration, and belongs to the technical field of video processing. The method specifically comprises the following steps: S1, video preprocessing and intelligent blocking: preprocessing an original video, cutting the video into small blocks, ensuring that the end of each small block is a complete statement, outputting a timestamp and an audio text segment of each block, and storing the timestamp and the audio text segment in the form of structured data; and S2, multi-modal scene separation and verification: inputting each block, namely an audio text segment and a timestamp thereof into a large language model, initially dividing a scene according to a rule, then constructing a spurious chart, inputting a large visual model to verify whether a commodity is switched, and finally outputting scene time, a title and a brief introduction. Through a combination strategy of audio feature extraction, semantic integrity judgment and quantitative blocking rules, the problems of statement truncation and timestamp confusion which are easy to occur in traditional video blocking are solved. Specifically, sound wave intensity, voice pause features and a statement boundary identified by a language large model are combined.
Owner:HANGZHOU YUNZHI CHUANGXIN NETWORK CO LTD

Personalized tone migration and synthesis method based on virtual singer

The invention relates to a personalized timbre migration and synthesis method based on a virtual singer, and the method comprises the steps: obtaining a reference singing audio of a target virtual singer, and extracting a timbre identity benchmark feature used for representing the timbre identity stability through timbre coding; obtaining personalized timbre migration demand information for the virtual singer, wherein the demand information comprises a to-be-migrated timbre attribute and a corresponding target change amplitude or change direction; calculating a compatibility score according to the timbre identity reference feature and a migration demand, generating a timbre migration risk indication value, and comparing the risk indication value with a preset threshold value or a preset threshold value interval to determine that the migration is high-risk migration or low-risk migration or conservative-risk migration; according to the method, the tone identity benchmark features in the reference singing audio are extracted, and the tone identity invariant set with stable transpitch and sounding intensity is further constructed, so that the core tone identity of the virtual singer is accurately described.
Owner:CHANGSHA NORMAL UNIV

Integrated digital test method under noise for evaluating hearing and cognitive functions

The invention relates to a method for testing a participant's ability to accurately detect speech under background noise, comprising: (a) audibly presenting a series of 2-bit numbers, 3-bit numbers, 4-bit numbers and / or 5-bit numbers in a random or fixed order to a participant's first ear at a fixed or varying signal-to-noise ratio (SNR) in a quiet or noisy environment, (b) audibly presenting a series of 2-bit numbers, 3-bit numbers, 4-bit numbers and / or 5-bit numbers in a random or fixed order to the second ear of the participant at a fixed or random signal-to-noise ratio (SNR) in a quiet or noisy environment, where the numbers are presented in the native language of the participant or the fluent language of the participant, (c) recording the numbers or sequence of numbers correctly recognized by the participant, and (c) storing the recorded numbers or sequence of numbers at the second ear of the participant. And (d) calculating a score as a function of the percentage of the number or sequence of numbers correctly replicated by the subject, or as a function of the sound intensity difference between the speech and noise required to achieve the correct recognition of 50% sequence of numbers. The invention also relates to a device and a method for measuring the digital recognition capability related to hearing loss, and to a computer-implemented method for evaluating the speech recognition capability of a participant.
Owner:THE UNIVERSITY OF HONG KONG

Passive target speed estimation algorithm based on sparse Bayesian learning cross spectrum

PendingCN119439170Asuppress noiseimprove signal-to-noise ratioMathematical modelsSystems with undesired wave eliminationNoiseBackground noise
The invention discloses a passive target speed estimation algorithm based on a sparse Bayesian learning cross spectrum, and belongs to the technical field of array signal processing. The method comprises the following steps: constructing a target cross-correlation field model, carrying out cross-spectrum on sound pressure and a delayed sound pressure channel to obtain cross-spectrum sound intensity flow, constructing a dictionary matrix according to target cross-spectrum frequency point features, establishing a joint probability density distribution function by virtue of a sparse Bayesian learning model, and finally estimating signal power according to maximum logarithm Bayesian evidence. And carrying out spectrum peak search on the signal power estimation value to realize speed estimation of the target. According to the method, the cross-spectrum sound intensity flow is used as input, all cross-spectrum frequency points are compensated, alignment of cross-spectrum results of different frequency points is achieved, the background noise suppression effect is achieved, and multi-frequency-point processing results are fused. Meanwhile, the method has good speed estimation precision, can maintain good performance under the condition of low signal-to-noise ratio, and has high engineering application value.
Owner:NAT INNOVATION INST OF DEFENSE TECH PLA ACAD OF MILITARY SCI

Directional sound pickup method and device

A directional sound pickup method and a device implement targeted sound pickup for one or more targets without affecting video recording. An electronic device may identify a directional sound pickup target based on selection of a target object (or a region) in a viewfinder frame so that during audio recording, a sound signal from an identified target is picked up in a targeted manner, for example, a sound intensity of the directional sound pickup target is enhanced and / or a sound intensity of another target is weakened, or a sound intensity of another target is excluded.
Owner:HUAWEI TECH CO LTD

Pet emotion recognition method and system based on sound analysis

The invention relates to the technical field of intelligent voice, in particular to a pet emotion recognition method and system based on sound analysis, and the method comprises the following steps: extracting a dominant frequency value, a frequency spectrum gravity center and an energy concentration degree through audio collection equipment, and respectively mapping the dominant frequency value, the frequency spectrum gravity center and the energy concentration degree into three-dimensional coordinate axes to generate time sequence emotion state points; and calculating a sound intensity change rate by utilizing Gaussian kernel density estimation, judging an emotion activation source through a tension response function to generate a response graph, executing gradient calculation and non-maximum suppression to generate a label intensity graph, and generating a composite emotion expression result by combining a path turning angle and the graph. According to the method, emotional coordinates are mapped through a main frequency value, a frequency spectrum gravity center and an energy concentration degree, sound intensity changes are estimated through Gaussian kernel density, disturbance and space are correlated through a tension response function, a focused emotional interval is suppressed through a non-maximum value, path turning is analyzed through dynamic time warping, emotional evolution is described through a label map, and judgment continuity and consistency are improved through multi-dimensional feature fusion.
Owner:DONGGUAN TIEFA ELECTRONIC TECHNOLOGY CO LTD

Intelligent camera with active defense and defense method thereof

The invention relates to the technical field of image communication, in particular to an intelligent camera with active defense and a defense method thereof, and the intelligent camera comprises a data acquisition module, an extraction module, a judgment module, a determination module, a screening module and a defense module. According to the invention, through fusion of a multi-parameter analysis technology and combination of the target position, the attitude angle and the height of a real-time image and dynamic changes of sound intensity, accurate identification of an intrusion target is realized, and the judgment module adopts a multi-level logic of combination of boundary judgment and attitude angle change, so that the accuracy of abnormal target judgment is effectively improved; the screening module reduces erroneous judgment through comprehensive screening of sound intensity and position; the defense module calculates a launching track based on the real-time position and height of the target, fixed-point active defense is achieved through a water bomb, passivity of a traditional voice alarm mode is avoided, and the problem that the response speed is not timely due to single fingerprint recognition and vibration monitoring data is effectively solved.
Owner:Zhuhai BIT Greater Bay Area Innovation Research Institute +2