37 results about "Sound perception" patented technology

An auditory neural interface device for sound perception by an individual that may be used as a hearing aid. The auditory neural interface device includes a receiver configured to receive sound signals, a processor operably connected to the receiver and configured to encode a received sound signal as a multi-channel neurostimulation signal, and a neurostimulation device operably connected to the processor and configured to apply the multi-channel neurostimulation signal to a neurostimulation electrode of the individual. The neurostimulation signal is configured to directly stimulate afferent sensory neurons of the central nervous system of the individual and thereby to elicit, for each channel of the neurostimulation signal, one or more non-auditory, preferably somatosensory, perceptions in a cortex area of the individual. Each channel of the neurostimulation signal is associated with a different non-auditory perception.

The invention discloses a two-stage voice noise reduction method and device based on enhanced spectral subtraction and Kalman filtering, and a storage medium. The method comprises the following steps: performing preliminary noise reduction on a voice signal in a frequency domain through enhanced spectral subtraction; speech signal state space model parameters are identified based on a linear predictive coding algorithm, and secondary noise reduction is performed on the sound signals in a time domain by using a Kalman filtering algorithm; and repeatedly carrying out multiple parameter identification and secondary noise reduction processes on the frame-by-frame signals, and then outputting noise-reduced voice. According to the method, the environmental noise can be effectively filtered in a complex noise environment, and the voice signal quality is improved. The method is suitable for single-microphone noise reduction of the artificial cochlea, efficient noise reduction can be achieved in the artificial cochlea with limited computing resources, and the sound perception ability of a wearer is improved.

The invention provides a quadruped robot terrain classification method and system based on sound feature and IMU information fusion, and relates to the field of terrain perception, and the method specifically comprises the steps: collecting an audio signal, processing the audio signal to obtain a Mel spectrogram, collecting an IMU signal, drawing a triaxial IMU signal time domain graph, dividing the time domain graph into a plurality of IMU information graphs, and obtaining a quadruped robot terrain classification result. The feature value of each time domain graph window is calculated, an IMU information graph corresponding to the Mel-frequency spectrogram in time relation can be established, then the Mel-frequency spectrogram and the IMU information graph are spliced according to the time sequence, and the spliced Mel-frequency spectrogram and IMU information graph are input into a neural network model for terrain classification; according to the method, the classification capability of the unstructured outdoor terrain is enhanced in a mode of fusing sound perception and ontology perception, and the spliced input image not only contains audio features, but also retains IMU information, so that a neural network model can learn from two different perception sources, terrain features can be comprehensively understood, and the classification efficiency of the unstructured outdoor terrain is improved. Therefore, the recognition capability of the complex environment is improved.

The invention relates to a vehicle automatic test method and system based on a body robot, and the method comprises the steps: obtaining a test task of the body robot, and the test task is a task for simulating the operation behavior of a user on a vehicle; decomposing the test task into an executable subtask sequence according to the test type and the environmental condition; and controlling the robot to execute the current subtask according to the priority of the subtask sequence, monitoring behavior actions of the vehicle when the robot executes the current subtask, and recording a task execution result of the robot. Therefore, the problems that a traditional automobile function testing method depends on manpower, is low in testing efficiency and hard to cover a dynamic scene, network testing is split in testing, and the man-machine cooperation efficiency is low are solved, the dependence of the testing on the manpower is reduced, the testing efficiency and the testing quality are improved, meanwhile, network-function integrated testing is guaranteed, and the testing efficiency is improved. Automatic testing of the automobile in a complex environment is realized by using the robot with the body based on vision, sound perception and information interaction cooperation.

The invention discloses an intelligent AI construction method and system for track and field event referees, particularly relates to the technical field of image recognition and behavior judgment, and is used for solving the problem that the track and field event referees have many misjudgments and disputes. Time synchronization of a starting area image sequence and a starting gun sound signal is carried out through an image acquisition device and a sound sensing device, a standardized starting response sequence is constructed, a lower limb key point track is extracted from the sequence, the starting moment of a starting action is analyzed in combination with displacement and speed change, whether a false start behavior exists or not is judged, and the judgment result is accurate. The extracted foot points are mapped to a unified reference plane, the shielding level is judged, the penalty confidence coefficient is constructed in combination with image definition, the penalty confidence coefficient and a penalty result jointly form a referee interaction frame set, the referee interaction frame set is presented in an auxiliary judgment interface to be rechecked and confirmed by a referee, and then referee modification behaviors serve as difference samples to be fed back. And through optimization of an incremental training mechanism, the controllability and continuous optimization capability of the penalty process are improved.

The invention provides an acousto-optic emergency communication device and equipment suitable for a weak communication scene, and the device and the equipment provide an acousto-optic communication full-modular hardware design, and have the characteristics of acousto-optic signal processing integrated design, acoustic communication, sensing and computing power separation design, high variability of a sensing module and the like. The hardware design of the invention effectively reduces the size required by the module and the computing power requirement on a single chip, and has the capabilities of rapid customization and multi-scene adaptation. The sound sensing module adopts a low-energy-consumption event driving sensing algorithm and an optical link quality prediction algorithm adaptive to the variable sensing module. The driving sensing algorithm is combined with a sensing signal through a sound signal sensing algorithm, flexible dormancy and rapid assessment of a sudden environment can be achieved, the method can be used in a low-computing-power platform, and energy consumption is effectively reduced. The prediction algorithm combines sound perception information and environment information, uses fuzzy logic to realize various input compatibility of various scenes, abstracts various environment information and sensor data, and has multi-scene applicability and high accuracy.

The invention discloses a sound sensing method, apparatus and device, and a computer readable storage medium. The method comprises the steps of obtaining first mixed signals obtained by reflection after a radar transmits first frequency modulation pulse signals; performing discrete Fourier transform on each first mixed signal, and extracting to obtain a first phase set corresponding to each first distance unit in the first phase matrix; extracting a first sound signal containing noise from each first mixed signal according to the first phase set corresponding to each first distance unit; performing compressed sensing on the first sound signal to obtain a first compressed signal; and performing sound sensing on the first compressed signal by using a target sound sensing model obtained based on generative adversarial network training. According to the method and the device, the processing capability of the target sound sensing model on the problems of baseline fluctuation, nonlinear mapping and the like existing in the original sound sensing signal is ensured, the calculation complexity of the model is reduced, and the robustness of the model is improved.

Presented herein are substantially automated techniques that enable an electro-acoustic or other hearing prosthesis implanted in a recipient to use objective measurements to determine when the recipient is likely experiencing sound perception changes. Once one or more perception changes are detected, the hearing prosthesis may initiate one or more remedial actions to, for example, address the perception changes. As described further below, the one or more remedial actions may include adjustments to the recipient's operational map to reverse the one or more perception changes.

The application discloses a kind of for track and field sports event judge intelligent AI construction method and system, specifically related to image recognition and behavior determination technical field, for solving the problem of multiple track and field event judge misjudgment dispute;The application carries out the time synchronization of starting area image sequence and starting pistol signal by image acquisition device and sound perception equipment, constructs standardization starting response sequence, extracts lower limb key point trajectory from the sequence, analyzes starting action starting time by combining displacement and speed change, judges whether there is sprinting behavior, and the foot point extracted is mapped to unified reference plane, judges shielding level, constructs penalty confidence in conjunction with image definition, penalty confidence and penalty result jointly form judge interactive frame set, present in auxiliary determination interface, for judge to review and confirm, and then judge modification behavior is used as difference sample and is fed back, is optimized by incremental training mechanism, improve the controllability and continuous optimization ability of penalty process.

The invention relates to adaptive signal processing for human voice control and acoustic feedback management. More particularly, it concerns a system and method for detecting and cancelling a person's own voice, as may be perceived through airborne, bone, and soft-tissue conduction. The invention also covers related calibration, adaptive filtering, and neural-network implementations for such systems. The present invention represents a system and method for cancelling a perception of a user's own voice as perceived through airborne, bone, and soft-tissue conduction paths. The suggested solution may operate with minimal latency, adapt to individual anatomical and environmental conditions, and maintain transparency to external sounds. Furthermore, the solution incorporates calibration routines to accurately model the transmission characteristics of these paths. It also allows to employ adaptive or machine-learning techniques to refine cancellation performance in real time.

The present invention provides a sound reproduction system and method for enhancing spatial auditory perception, including: an information input and definition layer: including speakers, microphones, distance tracking devices, and processors, which complete sampling of the spatial sound field and real-time distance tracking, and then input sound source information, environmental information, and listener information into the spatial sound modulation layer; a spatial sound modulation layer: including a spatial sound modulator, the spatial sound modulator contains pixel blocks arranged in an array for spatio-temporally modulating the amplitude, phase, and directivity of sound waves; the modulated sound waves are input to the listener sound perception layer; a listener sound perception layer: the human ear auditory system realizes the localization of the sound source direction, the perception of the sound source distance, and the comprehensive perception of the sound scene. The present invention can be used in cooperation with existing reproduction systems for creating spatial auditory perception, and can significantly reduce the number of speakers arranged and the space occupied in a precise reproduction system of a physical sound field.

The application discloses a vehicle exterior sound reconstruction method and device for in-vehicle partition perception and electronic equipment, and mainly has the following design concept: sound pickup and filtering and noise reduction processing are performed by a sound pickup device in a vehicle exterior area, and further, multi-dimensional monitoring of the vehicle exterior environment can be performed by coupling vehicle exterior visual information to guide identification and type judgment of the required external environment sound information for reconstruction; then, different reconstruction modes are distinguished by user instructions, and in an automatic reconstruction scene, the reconstruction sound effects that can be independently perceived are output to each in-vehicle partition, and in a scene with user intervention, the user instructions and user portraits are integrated to realize targeted pushing of the required vehicle exterior environment sound to the target driver and passenger in different in-vehicle partitions, so that the in-vehicle driver and passenger can have a vehicle exterior sound restoration and reproduction effect closer to their daily needs and experience habits, and the high-degree-of-freedom sound perception experience of the driver and passenger and the vehicle safety are improved.

The application discloses a self-adaptive environmental sound emotion recognition method and device, and the method comprises the following steps: collecting environmental sound by using crowd-sourcing audio data and a mobile device, and labeling the environmental sound to construct an environmental sound sample library; performing self-adaptive segmentation on sound data in the sample library through audio signal energy change to obtain sound data of different lengths; extracting sound perception features based on the perception characteristics of human ears for the sound data of different lengths obtained through segmentation; taking the sound perception features as input, performing environmental sound emotion training through a recurrent neural network method of a long short-term memory network, and performing emotion prediction on actually collected environmental sound data by using the trained model.

The invention relates to the technical field of intelligent adjustment of audio equipment, and discloses a system for automatically adjusting loudspeaker volume and sound effect according to wind sound volume, which comprises a wind noise acquisition module, an audio processing module, a main control module and a loudspeaker module, and is characterized in that the modules are sequentially in signal transmission connection. The loudspeaker volume and the sound effect type are dynamically adjusted according to the wind noise level, the wind noise is not counteracted to retain environment sound perception, and the problems that an existing noise reduction scheme is not real, influences safety and is not adaptive to the wind noise adjustment sound effect are solved. According to the invention, the wind noise acquisition module adopts a loudspeaker periphery distributed microphone layout, and captures a wind noise and environmental noise mixed signal near a loudspeaker at 360 degrees, thereby avoiding irrelevant noise interference; the audio processing module separates and recognizes the wind noise through a special DSP algorithm, and accurately judges the wind noise level by combining with the comparison of a wind noise feature database, thereby providing a reliable basis for adjustment, and overcoming the defects of inaccurate collection and fuzzy recognition of traditional equipment.

The invention discloses an animal binaural sound source perception model construction method, system and application. Relates to the technical field of sound source model construction. According to the scheme, the method is improved on the basis of the prior art, a sound simulation experiment is carried out in a target scene, and an animal head transfer function is constructed; obtaining a position relationship between a target animal and a sound source in a target scene, and solving a binaural virtual sound signal with orientation in the target scene by combining the left ear transfer function and the right ear transfer function; establishing a binaural sound sensing relation model of a sound source signal at a specific position and a specific animal object under a specific pose; meanwhile, the invention further provides an application method of the animal binaural sound source sensing model, remote animal behavior intervention is achieved based on binaural virtual sound signals, and a foundation is laid for the intelligent breeding and grazing technology.

The invention relates to the field of smart parking lots, and discloses a vehicle behavior monitoring management platform for a smart parking lot, which comprises a sound sensing module, a sound source positioning module, a candidate area limiting module, a behavior period visual analysis module, a responsibility judgment module and an information output module, the system collects environment sound in real time through a sound sensing module, and extracts characteristic audio data and triggers an analysis process after detecting a friction type high-frequency signal with a rubbing characteristic; spatial azimuth information of a rubbing sound source is determined through a sound source positioning module, and a suspected rubbing area and a rubbed vehicle are limited; recognizing the approaching vehicle and extracting the track path of the approaching vehicle by combining the image track and the dynamic behavior characteristics in the behavior period; and the responsibility judgment module outputs a suspected responsibility vehicle according to the matching relationship among the trajectory, the approaching time and the sound source direction in combination with a scoring model. The system is non-intrusive, has high robustness, and is suitable for the intelligent judgment capability of the rubbing behavior of non-cooperative vehicle recognition.

The application discloses a sound perception-based electronic pet behavior triggering method, and relates to the technical field of intelligent interaction.The method comprises the following steps: collecting environmental sound signals through a microphone array and constructing a sound feature vector, determining sound intensity levels, sound source directions, and user voice classes, environmental event sound classes, and third-party biological sound classes; analyzing different sound classes to obtain user instruction intentions, user emotion labels, and sound event types; dynamically updating in combination with current emotion parameters and energy parameters of the electronic pet; generating priority behavior instructions based on the above information and sending the priority behavior instructions to an action execution module; and monitoring the short-term energy of the electronic pet in real time during the execution process and performing self-noise control.The technical problems of single sound processing, rigid state updating, serious self-noise interference, and lack of continuity of behavior response in the life state of the existing electronic pet are solved.

The invention belongs to the technical field of smart home and health monitoring, and particularly relates to an intelligent sleep regulation system integrating light hypnosis and infrared-sound perception, which comprises a data acquisition module, an intelligent analysis processing module, an environment regulation and control system and a photocatalytic hypnosis module, according to the photocatalytic hypnosis device, the photocatalytic hypnosis module actively catalyzes and decomposes organic volatile matters in indoor air through a photocatalytic reaction device with a specific wavelength, and a specific-wavelength secondary light source capable of promoting natural synthesis of human body melatonin is generated in situ in the process. In the process, the multi-mode sensor collects physiological data and environment data of the user in real time, comprehensive analysis is conducted through the intelligent analysis processing module, environment parameters are dynamically adjusted, starting and stopping, intensity and spectrum output of the photocatalytic reaction can be accurately controlled, and active and non-intrusive adjustment of the circadian rhythm of the user is achieved. According to the invention, the crossing from environmental regulation to active physiological intervention is realized, and the sleep induction and maintenance effect is obviously improved.

In a sound reproduction method in which a user (99) is caused to perceive a first sound as a sound arriving from a first position (P1) on a three-dimensional sound field and is caused to perceive a second sound as a sound arriving from a second position (P2) different from the first position (P1), the method includes: a step (S102) of acquiring a moving speed of a head of the user (99); and a step of generating an output sound signal for causing the user to perceive a sound arriving from a prescribed position on the three-dimensional sound field, in which, in a case where the acquired moving speed is greater than a first threshold value, an output sound signal for causing the user (99) to perceive the first sound and the second sound as sounds arriving from a third position (P3) between the first position (P1) and the second position (P2) is generated.

A multi-mode hearing stimulation method for stimulating the perception of hearing in a subject. The method includes generating, based on sound signals representative of multi-channel sound, two or more of multi-channel electrical stimulation signals, bone conduction stimulation signals, and audio stimulation signals. The electrical stimulation signals are configured to cause electrical stimulation of hearing perception, including lateralization of hearing perception. The bone conduction stimulation signals are configured to produce vibrations causing bone conduction stimulation of hearing perception. The audio stimulation signals are configured to produce air conducted pressure wave sound. Embodiments comprise obtaining compensation information for use in connection with a multi-mode hearing stimulation system. The compensation information may be obtained by concurrently applying the electrical stimulation, bone stimulation or pressure wave sound to the subject, and receiving and storing as compensation information, information representative of a direction from which the subject perceived the resulting perceptions of sound.

The application discloses an in-vehicle user sub-area sound perception method and device and electronic equipment. The main idea of the application is as follows: obtaining a user subjective transmission intention according to a voice interaction of a plurality of sub-areas in a vehicle or triggering real-time sound pickup of a corresponding outside area based on automatic control logic, and outputting sound pickup data outside the vehicle to a speaker involved in the sub-area in the vehicle according to a preset mixing logic, so that users at different positions in the vehicle can independently perceive the sound of the outside environment, and the overall vehicle experience of passengers in the vehicle is improved. Compared with the prior art, the application effectively and directionally feeds back the sound pickup data outside the vehicle to the passengers in the corresponding area in the vehicle, so that the users in different spaces in the vehicle can independently perceive the sound information of the specific outside area required by the user, and the user intention is combined with intelligent decision-making to create a higher degree of freedom in the vehicle.

The present invention belongs to the field of facial expression recognition technology, and specifically relates to a facial expression recognition method and system based on sound perception. The method uses acoustic signals as a sensing medium, utilizes a microphone array to capture sound reflection signals, and generates a spectrogram containing facial features through signal processing. Features are extracted from the spectrogram, and a deep learning network is used to classify facial expressions to achieve expression recognition. The facial expression recognition method provided by the present invention can effectively achieve facial expression recognition even with relatively small amounts of data, without relying on expensive hardware equipment, utilizing commercially available speakers and microphone arrays.

This application provides a sound perception and localization method for humanoid robots, relating to the field of robotics. It constructs a basic three-dimensional sampling array by scientifically arranging four microphones, employing high-precision omnidirectional condenser microphones to achieve distortion-free acquisition of environmental sound signals. Simultaneously, it outputs raw sound signal data, precise sound pressure amplitude data, and related identification information. The raw sound signal is preprocessed using A-weighted sound levels that conform to human hearing characteristics, while filtering out DC components and high-frequency interference noise to output a human-like sound signal. Then, based on the theory of pulsating spherical source radiation sound field and a point source approximation model, combined with the human-like sound pressure data acquired by the microphone array and preset coordinates, the three-dimensional spatial coordinates of the sound source are accurately calculated. Multiple sound source coordinate results are obtained through multi-microphone array combination calculations, thereby achieving accurate judgment and high-precision localization of the environmental sound source and its location.

This invention relates to a control method and system for a movie theater massage chair based on sound perception. The method includes the following steps: acquiring raw sound during movie projection and preprocessing it; extracting features from the preprocessed raw sound to form a sound feature sequence, and inputting it into a sound recognition model for scene recognition, outputting the scene category and corresponding confidence score; matching a basic massage mode from a massage mode library based on the scene category; adaptively adjusting the basic massage mode based on the confidence score to generate a final massage mode; and controlling the massage chair to perform massage actions based on the final massage mode. This invention can identify the movie projection status and control the massage chair without relying on external interfaces, achieving a natural linkage between the massage rhythm and the movie rhythm, enhancing the immersive movie-watching experience.

The invention belongs to the technical field of facial expression recognition, and particularly relates to a facial expression recognition method and system based on sound perception. According to the method, an acoustic signal is used as a sensing medium, a microphone array is used for capturing a sound reflection signal, a spectrogram containing facial features is generated through signal processing, features are extracted from the spectrogram, facial expressions are classified through a deep learning network, and expression recognition is achieved. According to the facial expression recognition method provided by the invention, the facial expression recognition can be effectively realized by utilizing a commercial loudspeaker and a microphone array without depending on expensive hardware equipment even under the condition that the data volume is relatively small.

A multi-mode hearing stimulation method for stimulating the perception of hearing in a subject. The method includes generating, based on sound signals representative of multi-channel sound, two or more of multi-channel electrical stimulation signals, bone conduction stimulation signals, and audio stimulation signals. The electrical stimulation signals are configured to cause electrical stimulation of hearing perception, including lateralization of hearing perception. The bone conduction stimulation signals are configured to produce vibrations causing bone conduction stimulation of hearing perception. The audio stimulation signals are configured to produce air conducted pressure wave sound. Embodiments comprise obtaining compensation information for use in connection with a multi-mode hearing stimulation system. The compensation information may be obtained by concurrently applying the electrical stimulation, bone stimulation or pressure wave sound to the subject, and receiving and storing as compensation information, information representative of a direction from which the subject perceived the resulting perceptions of sound.

The present invention discloses a two-stage speech noise reduction method based on enhanced spectral subtraction and Kalman filtering, as well as its device and storage medium. The method comprises the following steps: performing preliminary noise reduction on the speech signal in the frequency domain by using enhanced spectral subtraction; identifying the state space model parameters of the speech signal based on a linear predictive coding algorithm, and performing secondary noise reduction on the sound signal in the time domain by using a Kalman filter algorithm; and outputting noise-reduced speech after repeating the parameter identification and secondary noise reduction process on the frame-by-frame signal multiple times. The method of the present invention can effectively filter out environmental noise in a complex noise environment and improve the quality of the speech signal. The method is suitable for single-microphone noise reduction of a cochlear implant and can achieve efficient noise reduction in a cochlear implant with limited computing resources, thereby improving the wearer's sound perception ability.

Presented herein are substantially automated techniques that enable an electro-acoustic or other hearing prosthesis implanted in a recipient to use objective measurements to determine when the recipient is likely experiencing sound perception changes. Once one or more perception changes are detected, the hearing prosthesis may initiate one or more remedial actions to, for example, address the perception changes. As described further below, the one or more remedial actions may include adjustments to the recipient's operational map to reverse the one or more perception changes.

A computer-implemented method and system for predicting device location includes recording a sound record using a microphone on a first device; processing the sound record to extract a feature corresponding to a multipath version of a sound sample played by a second device; based on the extracted features, classifying the physical location of the second device into one of (i) the second device is located in the same space as the first device or (ii) the second device is not located in the same space as the first device; an operation is performed on the first device based on the classification.

The utility model discloses an open type earphone, which comprises a first cabin body, a loudspeaker single body, a second cabin body and a connecting part, and is characterized in that the first cabin body is provided with a sound outlet hole; the loudspeaker single body is accommodated in the first bin body and divides the space in the first bin body into a front cavity and a rear cavity, and the front cavity is communicated with the sound outlet hole; a Helmholtz resonant cavity is formed in the second bin body; two ends of a connecting part are respectively connected with the first bin body and the second bin body, a Helmholtz channel is arranged in the connecting part, one end of the Helmholtz channel is communicated with the front cavity, and the other end of the Helmholtz channel is communicated with the Helmholtz resonant cavity. According to the technical scheme, the technical problem that an open type earphone is poor in hearing feeling can be solved.