219 results about "Directional sound" patented technology

The invention relates to an array microphone noise reduction recording method based on cascade noise reduction and blind source separation, which belongs to the technical field of voice signal processing and recording, and comprises the following steps: configuring a multi-channel array microphone, ensuring that the amplitude and phase of a channel signal are consistent, and collecting an original multi-channel voice signal; a weighted kernel function blind source separation algorithm is adopted, signal-to-noise ratio distribution characteristics of signals are extracted, kernel function weights are given, and target voice and interference signal components are obtained through decoupling of an independent component analysis model; executing target-oriented adaptive cascade noise reduction, locking the voice of a keynote speaker through directional pickup, reducing noise, filtering out reverberation, and enhancing the voice of a far-field target by combining a voice mask neural network with a far-field pickup algorithm in sequence; and processing the target voice through voice feature perception lossless coding and storing the target voice. According to the invention, stable acquisition of multi-channel signals, accurate separation of mixed signals and layered suppression of noise reverberation are realized, the signal-to-noise ratio and definition of far-field voice are significantly improved, and the method is suitable for single-person speaking or multi-person dialogue scenes.

The voice directional enhancement method comprises the steps that a current frame and a staring direction of mixed voice are acquired, and the mixed voice is acquired by a microphone array; constructing a direction feature based on the current frame of the mixed voice and the gazing direction, and constructing an audio feature based on the current frame of the mixed voice; determining a current frame mask according to the direction features and the audio features; and determining a target enhanced voice of the current frame according to the current frame mask, the current frame of the mixed voice and the plurality of historical frames of the mixed voice. In the embodiment of the invention, the mask of the current frame is generated under the guidance of the gazing direction, so that the target voice can be accurately separated from the mixed voice. Besides, based on the current frame mask and the current frame of the mixed voice, the target voice enhancement is performed frame by frame from the overall characteristics of the mixed voice by referring to a plurality of historical frames, so that the accuracy of the target enhanced voice of the current frame can be effectively improved, and thus the accuracy of directional pickup is improved.

The invention relates to the technical field of directional pickup, and discloses a directional pickup method and device, computer equipment and a medium, and the method comprises the steps: obtaining time domain voice signals collected by at least two microphones, and carrying out the time-frequency conversion; calculating an observation phase difference of each frequency point, and determining a target theoretical phase difference according to a target pickup direction specified by a user and the geometric parameters of the microphone; encoding the target theoretical phase difference into a query vector, encoding the observation phase difference into a key vector, and generating a space confidence mask through a geometric cross attention mechanism; and filtering the frequency domain signal by using the mask, and outputting enhanced voice in a target direction through inverse time-frequency transformation. According to the invention, through an attention mechanism guided by physical prior, the problem of phase winding is effectively solved, and high-robustness and high-fidelity speech pickup in any direction is realized in a strong reverberation and low signal-to-noise ratio environment.

The invention belongs to the technical field of underwater welding, and discloses an underwater double-path ultrasonic synergistic laser-electric arc hybrid welding repair device and method. The device comprises a two-way ultrasonic synergistic TIG welding gun and a laser head which are both fixed on an external drainage cover, and sealing penetration pieces are arranged on the external drainage cover for the two-way ultrasonic synergistic TIG welding gun and the laser head; the double-path ultrasonic synergistic TIG welding gun comprises a tungsten electrode sound path and an end part sound path; the tungsten electrode sound path transmits ultrasonic energy to a welding gun tungsten electrode through a tungsten electrode ultrasonic transducer, the electric field at the root of the welding gun tungsten electrode and the micro-motion behavior of the welding gun tungsten electrode are affected, and therefore the electric arc is compressed, and the position of the root of the electric arc is finely adjusted. The end sound path acts on the end of the welding gun through the end ultrasonic transducers in an annular array, directional sound radiation pressure is applied, an electric arc column and the surface of a molten pool are adjusted, heat input is promoted to be evenly distributed, and the symmetry of the molten pool is improved. The welding quality and the process stability are remarkably improved.

An animal deterrent device is generally shown. The animal deterrent device utilizes smart technology to deter an animal from coming close to a person holding the device or breaking apart two animals that are fighting without having to get physically involved. The device includes a first shell coupled to a second shell via fasteners. The device also includes one or more transducers configured to emit a sound wave. The transducer is controlled by a processor that includes a signal processing module and an analytics machine, amongst other components. The processor is configured to optimize the sound wave emitted by the transducer to provide a directional sound wave of a particular frequency, ranging from 10 kHz to 45 kHz, to keep an animal away.

The invention discloses a directional radio receiving method, a directional radio receiving device and electronic equipment. The method comprises the following steps: acquiring multi-channel audio data acquired by a microphone array; sound source localization is carried out on the multi-channel audio data, a target localization result is obtained, and the target localization result at least comprises a sound source orientation determined based on a historical localization result; audio signals in multiple target directions corresponding to the multi-channel audio data are determined, and the audio signals are determined based on the target positioning result; and determining an output signal corresponding to the multi-channel audio data according to the audio signal. According to the invention, the technical problem of beam forming direction deviation caused by insufficient precision and poor stability of sound source positioning in noise and reverberation environments in the prior art is solved.

The invention relates to the technical field of wind tower disease recognition, and discloses a wind tower disease image recognition system based on deep learning. The method comprises a bionic scanning layer, a sound wave feature extraction layer, a multi-source fusion module, an intelligent diagnosis module and an iterative optimization layer. The bionic scanning layer obtains a multispectral wind tower surface image, a surface damage distribution diagram is generated through wavelet decomposition, and an abnormal region boundary is recognized; the acoustic wave feature extraction layer deploys a directional acoustic wave sensor array according to the abnormal region, and generates an internal three-dimensional defect topological graph through a reflected signal; the multi-source fusion module establishes a space mapping relation, and after timestamps are synchronized, surface and internal data are fused by using a gating chart neural network to generate defect fusion confidence; the intelligent diagnosis module converts the confidence into a maintenance operation instruction sequence based on deep reinforcement learning and transmits the maintenance operation instruction sequence to the execution terminal; and the iterative optimization layer monitors the state change of the tower drum, calculates a deviation value to generate an efficiency index, and dynamically adjusts a multispectral scanning parameter.

The invention discloses a self-adaptive directional sound control method and system based on a multi-loudspeaker array. The method comprises the following steps: constructing an acoustic array by utilizing a plurality of loudspeakers distributed in different directions in the mobile terminal, performing single side band up-conversion processing on an audio signal, performing digital beam forming according to a target direction, and generating a plurality of paths of driving signals with phase difference and time delay difference, thereby forming a high-directivity sound field in a space. The system collects sound field feedback signals through a built-in microphone, and adopts a minimum mean square algorithm to adjust beam parameters in real time so as to compensate for terminal attitude, shielding and environmental noise changes and realize stable directional output of a sound field. The system further comprises a parameter library and sensor fusion module which supports adaptive calibration and multi-beam output of different devices. According to the invention, programmable directional sound transmission is realized without hardware modification, and the method has high privacy, low power consumption and strong robustness, and is suitable for private communication of an intelligent terminal and a multi-user audio partition playing scene.

The invention relates to the technical field of equipment operation state monitoring, in particular to a transformer substation main transformer equipment operation state monitoring system based on voiceprint recognition. Comprising a voiceprint collection module, a data preprocessing module, a voiceprint analysis module, a state evaluation module, a cooperative monitoring module, an interaction early warning module, a block chain evidence storage module and an operation and maintenance optimization module. According to the invention, the directional acoustic sensor collects voiceprint signals of key components, synchronously collects multi-dimensional operation parameters, and combines a wavelet threshold noise reduction algorithm to filter environmental noise and timestamp synchronization algorithm associated data, thereby achieving the effects of eliminating environmental interference and ensuring the integrity and accuracy of monitoring data. A normal voiceprint baseline library is constructed through historical voiceprint data and a deep learning model, current voiceprint signals are compared in real time, the operation state is judged in combination with multi-dimensional parameters, a time sequence model is used for deducing the fault trend, and the effects of accurately recognizing the fault type, accurately dividing the equipment state and conducting early warning in advance are achieved.

1. The name of the design product: directional sound device (1). 2. The use of the design product: for playing sound directionally. 3. The design points of the design product: in the combination of shape and pattern. 4. The picture or photo that best shows the design points: perspective view.

1. The name of the designed product: loud directional broadcast speaker. 2. The use of the designed product: long-distance directional sound wave emitting equipment. 3. The design points of the designed product: the combination of shape and color. 4. The picture or photo that best shows the design points: perspective view. 5. The design contains colors.

The invention discloses a conference privacy protection system and method based on visual sound field fusion. The conference privacy protection system comprises a visual acquisition module, an audio acquisition module, an audio playing module and a processing control module, wherein the visual acquisition module transmits mouth shape area three-dimensional coordinates, ear area three-dimensional coordinates and mouth motion states of participants to the processing control module; the processing control module generates a directional pickup instruction based on the mouth shape area three-dimensional coordinates, and sends the directional pickup instruction to the audio acquisition module to control the audio acquisition module to focus mouth shape area pickup; and meanwhile, a directional playback instruction is generated based on the three-dimensional coordinates of the ear region and is sent to the audio playing module to control the audio playing module to project sound beams to ears. Through visual guidance directional pickup, ultrasonic directional playback and audio and video fusion optimization, the risk of audio diffusion is reduced, so that the conference privacy protection effect is improved.

The utility model discloses a sound wave soot blower for electrostatic precipitator, it includes the casing, one end fixed mounting of casing has compressed gas source, one side of compressed gas source is provided with main gas pipe, be provided with a plurality of different length's branch gas pipe on main gas pipe, one end of a plurality of branch gas pipe all is fixedly installed with intelligent control valve all to the shell and is all downward, the lower end fixed mounting of intelligent control valve has variable frequency formula resonant cavity sound wave generator, the lower end fixed connection of variable frequency formula resonant cavity sound wave generator has directional sound wave sound signal horn, directional sound wave sound signal horn is located the top of dust collecting electrode, through the branch gas pipe of different length to directional sound wave sound signal horn and variable frequency formula resonant cavity sound wave generator form asymmetric interval distribution, effectively reduced the sound wave interference between each electric field.

The invention relates to the technical field of pile foundation detection, in particular to a pile foundation detection counter-force device which comprises a support, a first clamping rod is fixedly connected to the support, a second clamping rod is arranged on the side, close to the first clamping rod, of the support, a detector is fixedly connected to one side of the second clamping rod, and a conical block is fixedly connected to the lower side of the support. A connecting plate is arranged on the outer side of the bracket; the inner side of the connecting plate is fixedly connected with a sound absorption piece. The connecting plate and the support are quickly limited together through the mounting mechanism, so that the sound absorption parts are neatly arranged around the support in a surrounding mode, directional sound absorption space can be formed when the sound absorption parts are neatly arranged outside the support in a surrounding mode, noise of a specific frequency is absorbed through the sound absorption materials, superposition with excitation signals is reduced, misjudgment of the sensor is avoided, and the detection accuracy is improved. The technical problems that the pile foundation detection counter-force device is affected by surrounding noise sources in the construction peak period, sound insulation protection is not conducted on a detection composite head, surrounding noise is prone to being overlapped with excitation signals, and misjudgment of a sensor is prone to being caused are solved.

The application relates to the technical field of virtual engine and discloses an immersive directional sound effect simulation optimization method and system based on a virtual engine. The method submits an acoustic ray tracing task to a hardware light tracing unit of a graphic processor at an acoustic solving rate lower than a graphic frame rate, accesses the same level of a bounding box acceleration structure as a graphic light tracing task, solves an effective sound propagation path according to a graphic material identification of a hit triangular facet, generates a path signature according to a sound source and the hit triangular facets successively passed through, and packs the path signature into an acoustic state snapshot for output; an audio rendering thread runs at an audio block rate higher than the acoustic solving rate, matches the snapshot and an active path set according to the signature, distinguishes a continuous path, a newborn path and a dying path, and respectively performs smoothing, fading in and fading out, and performs binauralization rendering on a sound source signal to obtain output binaural signals. The application solves the acoustic by reusing the graphic side acceleration structure, and continuously presents the directional sound effect without artifacts at a lower solving rate.

The utility model provides an earphone head and a bluetooth earphone, the earphone head comprises a main housing and a sound production assembly, the main housing comprises an inner side wall, an outer side wall and an annular side wall, and the inner side wall, the outer side wall and the annular side wall are enclosed to form an accommodating cavity; the sound production assembly is provided with a sound production surface, the sound production assembly is arranged in the accommodating cavity in a manner that the sound production surface faces the inner side wall, and an inner sound cavity is formed by a cavity between the sound production surface and the inner side wall; the annular side wall is provided with a directional sound guide hole communicated with the inner sound cavity, and the earphone head is worn on a human body in a manner that the inner side wall is attached to the face of the human body and the directional sound guide hole faces the auricle of the human body; the edge, away from the inner side wall, of the directional sound guide hole is provided with a sound guide plate protruding out of the face where an outlet of the directional sound guide hole is located. The earphone head of the utility model does not need to be plugged into the ear canal and cover the external ear, and does not need to press the skull, so that better sound playing quality can be achieved.

Embodiments of this disclosure provide a control method, apparatus, device, computer program product, and computer-readable storage medium. The method determines contextual information, including location information, of at least one user based on sound data within a space, and controls an audio-visual system to emit directional sound and light signals towards the location of at least one user based on this contextual information. This provides targeted and personalized audio-visual signals to users sharing the same space, ensuring that different users do not interfere with each other and greatly improving the user experience. Furthermore, by determining contextual information including location information based on sound information, user privacy can be significantly protected from disclosure.

The utility model provides a kind of directional sound used in exhibition hall, it is related to directional sound technical field, including directional sound main part, four corners in the inside of directional sound main part are respectively equipped with spiral aluminium pipe, double-layer frame is provided in the inside of directional sound main part, the part of backplate of directional sound main part is set in top end position and is provided with radiating fin;Airflow path is extended using oblique spiral aluminium pipe, heat air is discharged in combination with taper structure to accelerate, heat dissipation efficiency is significantly improved, power amplifier chip temperature is reduced by more than 30%, avoid the deterioration of sound quality or equipment damage due to overheating, heat pipe is directly attached power amplifier chip, branch heat pipe quickly conducts heat to fin and spiral aluminium pipe, realize multi-path collaborative heat dissipation, ensure that still can work stably under high temperature environment, adjust fin angle by micro steering gear simultaneously, optimize airflow direction, further improve heat dissipation performance, avoid noise interference simultaneously.

The disclosure relates to the technical field of sound-electricity conversion, and discloses a speaker assembly, a seat, and an electronic device, which can realize directional sound emission of audio and has a simple structure. The speaker assembly includes a mounting body, a plurality of dipole speaker units, and a control unit. The plurality of dipole speaker units are disposed inside the mounting body and are configured to form a dipole sound source to achieve directional sound emission. The control unit is electrically connected with each dipole speaker unit of the plurality of dipole speaker units and configured to control at least one control parameter for the dipole speaker unit of the plurality of dipole speaker units to adjust a sound field of the dipole speaker unit in a preset region.

1. The name of the design product: directional sound. 2. The use of the design product: for directional sound. 3. The design points of the design product: in shape. 4. The picture or photo that best shows the design points: combined state perspective view 1. 5. Other components that need to be explained: component 1 is a directional sound speaker, component 2 is a drive box. Wherein the component 1 perspective view A part is transparent or opaque.

The invention discloses a directional pickup method for a conference machine, related equipment and a computer program product, and the method comprises the steps: obtaining an angle code of a designated spokesman, and transmitting the angle code and an original audio signal collected by a microphone module into a speech enhancement neural network model; the model takes an audio signal which carries an angle coding label and contains noise as a training sample in advance, and takes a clean audio signal of a corresponding angle of the angle coding label as a sample label for training. The model processes an input audio signal, extracts an audio intermediate feature, maps an angle code to an angle code feature matched with the audio intermediate feature in dimension, fuses the angle code feature and the audio intermediate feature, continues reasoning based on the fused feature, and outputs an enhanced audio signal of a target angle. Through the fusion of the neural network model and the angle information, the directional pickup effect can be improved by means of the input and output mapping capability learned by the neural network model on training data, and the adaptability to complex scenes is higher.

The application discloses a directional sound pickup method and device and electronic equipment, and the method comprises the following steps: in step S1, a microphone frequency domain signal phase difference is calculated according to a target sound source azimuth angle, and the phase is compensated; in step S2, the compensated microphone signals are summed to obtain a first enhanced signal of a target signal. The application can break through the limitation of a sampling rate by linearly compensating the microphone phase in the frequency domain, so that the phases of the two microphone signals of the target direction are completely consistent, and the effect of a delay and sum algorithm is improved.

The application provides a desktop intelligent multi-direction sound pickup method and system, relates to the technical field of sound pickup, and comprises the following steps: obtaining a starting trigger signal of a microphone; obtaining a sound source direction parameter based on the starting trigger signal; determining a sound pickup microphone serial number and a corresponding sound source range direction parameter according to the sound source direction parameter and the sound pickup microphone relationship; the sound source range direction parameter comprises a sound source range direction distance and a sound source range direction angle; analyzing the sound source range direction parameter and the sound pickup microphone serial number to determine a horizontal adjustment parameter of the microphone; controlling the microphone to perform horizontal adjustment according to the horizontal adjustment parameter and the sound pickup microphone serial number; obtaining a sound pickup range image based on the sound pickup microphone serial number; analyzing the sound source range direction parameter and the sound pickup range image to determine a vertical adjustment parameter of the microphone; and controlling the microphone to perform vertical adjustment according to the vertical adjustment parameter and the sound pickup microphone serial number. The application has the effect of guaranteeing good sound pickup effect of the microphone.

The invention discloses an immersive exhibition hall sound field control system, and relates to the field of sound field control. The system comprises an acoustic sensing module which is used for collecting all-domain audio signals of an exhibition hall in real time; the global analysis module is in signal connection with the acoustic sensing module and is used for processing the collected audio signals; the sound field execution module is used for receiving the sound field control strategy generated by the global analysis module; and the central control platform is used for coordinating the work of each module, managing the audio content and providing a man-machine interaction interface. According to the system, crossing from indifference broadcast to partition directional sound field is realized, immersive personalized auditory experience is created, and the system has the capabilities of dynamically sensing and optimizing acoustic environment: the system can position a noise source in real time and evaluate reverberation, so that the problems of mutual crosstalk and loud noise of different explanation contents in a traditional system are avoided, and the system is suitable for popularization and application. And a plurality of exhibition areas are allowed to synchronously carry out clear and non-interfering explanation.

The invention relates to the technical field of intelligent sound boxes, and discloses an audio playing control method and system for an intelligent sound box and a storage medium, and the audio playing control method comprises the steps: obtaining environment information and user information; performing environment state recognition based on the environment information; performing emotional state analysis based on the user information; according to the environment state and the emotional state, generating an audio playing control parameter; according to the audio playing control method and device, the audio playing parameters are adaptively adjusted through real-time environment sound analysis, the space sound field control technology is adopted, directional sound release is achieved, smooth transition of the audio parameters is achieved when the environment changes, the user experience is improved, and therefore the problem of environment noise interference is solved.

1. The name of the designed product: directional broadcast speaker. 2. The use of the designed product: long-distance directional sound wave emitting equipment. 3. The design points of the designed product: the combination of shape and color. 4. The picture or photo that best shows the design points: perspective view. 5. The design contains colors.

1. Name of the product in this design: Outdoor Beam Adjustable Directional Broadcast Speaker. 2. Purpose of this design: For audio playback, with directional sound amplification function, which can effectively reduce sound diffusion. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: a 3D model.

1. Name of the product in this design: Tunnel Broadcast Plane Wave Directional Loudspeaker. 2. Application of this design: Long-distance directional sound wave emission device. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: a 3D model. 5. The design for which protection is sought includes color.

The invention discloses a directional private voice transmission mobile phone shell with close-range ear positioning and a method, and relates to the field of mobile communication terminal accessories. According to the invention, the built-in camera of the mobile phone is reused to realize ear positioning, the rear camera is adopted to complete target ear aiming during outward directional transmission, and the front camera is adopted to realize face and ear real-time tracking during private listening; the mobile phone shell is provided with a control module and a directional sound production unit, a hardware solidification beam forming algorithm unit is arranged in the control module, the sound production unit is driven to form a narrow beam sound field, voice is accurately focused on a close-distance ear region, and directional private voice transmission is achieved. The mobile phone shell can be connected with a mobile phone in a wired or wireless mode, a matched APP can achieve text-to-voice, positioning aiming, mode switching and global audio capture and forwarding of a mobile phone system, and the mobile phone shell is easy to use.

The utility model relates to the technical field of monitoring devices, and discloses a construction noise prevention monitoring device which comprises a base, a connecting cover is fixedly installed in the middle of the top of the base, and a movable rod is movably installed in the connecting cover. The noise monitor in the fixed cover can monitor noise on the outer side, a supervisor can be informed when the noise exceeds the standard, the supervisor can start the servo motor to drive the gear to rotate, the gear and the tooth groove are meshed to drive the rotating cover to rotate, and the rotating cover can drive the camera and the sound amplification groove to rotate. The surrounding environment can be monitored through the camera, a noise source can be found conveniently, after the noise source is determined, the directional loudspeaker in the sound amplification groove is started, high-decibel directional sound waves can be emitted through the directional loudspeaker to remind people in a designated area, the influence on surrounding people can be avoided, and the noise source can be found conveniently. Therefore, the effects that the construction team can be reminded accurately when the noise is generated, and the influence on surrounding people is avoided are achieved.