47 results about "Auditory perception" patented technology

The invention discloses an intelligent exoskeleton bone auxiliary conduction hearing aid system capable of being remotely controlled and having an electroencephalogram control function, and relates to the technical field of intelligent rehabilitation robots and hearing aid devices. The wearable mechanical part comprises a flexible actuator, an elastic fabric base material, an inertial measurement unit IMU, a plantar pressure sensor array, a surface myoelectricity EMG sensor and an electroencephalogram EEG sensor. And the information processing communication part comprises a central controller, a bone conduction hearing aid module, a multi-mode sensor, an embedded SoC, a DSP / AI accelerator, a 4G / 5G / Wi-Fi module and a power management unit. The flexible exoskeleton walking aid system and the bone conduction hearing aid module are integrated, the electroencephalogram EEG sensor is additionally arranged to achieve the electroencephalogram control function, and cooperation of the three functions of movement assistance, auditory perception and neural intention recognition is achieved. A user can directly control the exoskeleton action mode through electroencephalogram signals, meanwhile, intelligent assistance of lower limb joints is obtained in the walking process, and environment sounds and voice prompts are clearly received in a bone conduction mode. According to the system, the perception ability, the control flexibility and the social participation degree of old people or rehabilitation patients who are inconvenient to move and accompanied with hearing impairment in a complex environment are remarkably improved, and more natural and convenient man-machine interaction experience is provided for users.

This utility model discloses a popular science interactive display device. Key technical features include a display box with display windows on its periphery for observing the items inside. A vibration switch is installed on the inner side of the top cover of the display box. It also includes a sound module pre-stored with audio data, and the vibration switch controls the sound module to play the audio. This utility model allows the vibration switch to play pre-stored sounds of items by tapping the cover, combining auditory perception with physical interaction to enhance audience participation and exploration interest, and strengthen the immersive learning experience of scientific knowledge.

This invention discloses a music bandwidth expansion method based on auditory perception attention generative adversarial networks (GANs). The method comprises two parts: training and prediction. The prediction part uses the trained network model to complete the bandwidth expansion task. The training part includes the following steps: Step 1, data preprocessing: preprocessing the original music dataset to obtain high-frequency music signals and corresponding low-frequency music signals as training sample pairs; Step 2, model architecture design: training the training sample pairs from Step 1 to obtain a GAN model. The GAN model includes a generator for generating sample data and a multi-discriminator for determining the source of the input sample data. This invention incorporates a multi-discriminator into the network model, which to some extent avoids the problem of overly smooth high-frequency components in the expanded spectrogram.

Provided are an audio peak limiting system and method, which, by setting a moving maximum window to drive gain calculation, and in combination with matching a moving maximum window length to a delay duration of an audio input signal, suppress a risk of overshoot while enabling a user to flexibly adjust a suitable attack time, and result in a smoother gain curve and reduce distortion in dynamic range processing, thereby achieving a more natural auditory perception.

This application discloses a speech synthesis method, apparatus, device, and storage medium. The method involves analyzing the original text to be synthesized to obtain a phoneme sequence; inputting the phoneme sequence into a configured speech synthesis model to obtain synthesized speech output by the model. The speech synthesis model is a final speech synthesis model after parameter adjustment of the basic speech synthesis model, using the scoring results of multiple candidate speech samples corresponding to the input test text synthesized by the basic speech synthesis model as reward signals. The scoring results of each candidate speech sample conform to the user's auditory perception goals. This application adds user auditory feedback signals (i.e., the scoring results as reward signals) to the training process of the speech synthesis model, guiding the speech synthesis model to optimize model parameters in a direction that better conforms to the user's auditory perception, making the synthesized speech more in line with the user's auditory perception goals and improving the speech synthesis effect.

The invention relates to the technical field of intelligent auditory enhancement and digital signal processing, in particular to an intelligent hearing aid mode switching system and method, and the system comprises a panoramic sound field sensing unit which is used for calculating a sound field uncertainty index; the body motion intention capturing unit is used for resolving gaze point transfer intensity and a real-time motion vector; the heterogeneous feature decoupling and fusion unit is used for being connected with the capturing unit; when the sound field uncertainty index is greater than a preset sound field uncertainty threshold value and the fixation point transfer intensity is greater than a preset fixation point transfer intensity threshold value, generating a parameter freezing signal; the parameter freezing signal is used for calculating a beam lead compensation angle; the wave beam pointing is driven to perform same-direction advanced deflection; the auditory perception feedback optimization unit is used for generating a correction feedback signal when the definition index is reduced; according to the method, the problem of frequent mistaken switching in a high-dynamic complex environment is solved, and the continuity and the stability of auditory perception of a user in a sound source searching process are ensured.

The invention discloses an intelligent coal gangue identification method based on transfer learning and machine auditory spectrum features, which comprises the following steps: acquiring test bed and underground sound signals, extracting CASP advanced auditory perception features, and constructing a cross-domain transfer convolutional neural network model optimized by maximum mean difference, domain adversarial and covariance joint loss, rich laboratory data is effectively utilized to solve the problem of scarcity of underground samples, and cross-working-condition high-precision coal gangue identification is realized.

This invention relates to an intelligent method for identifying abnormal motor noises based on time-frequency features and auditory adaptation, belonging to the field of motor fault detection technology. The method includes: real-time acquisition of motor operating sound signals through a multi-directional acoustic signal acquisition array, followed by signal preprocessing and dynamic framing; generation of a time-frequency spectrum using short-time sliding window time-frequency conversion, establishing an auditory baseline for normal operation sound using auditory perception adaptation dynamic weighting technology, and performing hierarchical weighting processing on the time-frequency spectrum to generate fused time-frequency weighted features; construction of a time-frequency weighted feature-enhanced residual network model, achieving abnormal feature extraction and identification through cross-dimensional fusion mechanisms, fault feature transfer learning mechanisms, and fault feature attention mechanisms; and completion of status identification and alarm response using a dynamic adaptation inference mechanism and a hierarchical linkage alarm system. This invention effectively improves the accuracy and real-time performance of motor abnormal noise identification and is suitable for motor status monitoring in complex industrial environments.

This application provides a virtual playback simulation method, apparatus, device, and medium, relating to the fields of audio signal processing and audio playback device simulation technology. The method includes: acquiring an input audio signal and complex frequency response data of a target audio playback device, the response data including amplitude frequency response data and phase frequency response data; adaptively selecting a target algorithm from multiple preset virtual playback simulation algorithms according to preset application constraints; the multiple preset algorithms have different delay characteristics, accuracy levels, and computational complexity, and at least one algorithm adopts a frequency resolution processing method matching the characteristics of human auditory perception; using the target algorithm, processing the input audio signal based on the complex frequency response data to generate an output audio signal simulating the playback effect of the target audio playback device. This application improves the flexibility, accuracy, real-time performance, and perception optimization effect of virtual simulation through the organic combination of adaptive algorithm selection and auditory perception optimization.

The application relates to the field of hearing aids, in particular to a hearing aid sound compensation method, which comprises a system architecture module, the system architecture module is internally provided with an implementation module, an innovation module and a processing module, and the implementation module, the innovation module and the processing module are mutually electrically connected; the implementation module is internally provided with a data acquisition module, a sound compensation model module, a digital signal processing module and a sound output module, hearing data of a user is acquired, a targeted sound compensation model is constructed, and a digital signal processing technology is adopted to realize accurate compensation on a sound signal output by the hearing aid. Experimental results show that the method has obvious advantages in improving the auditory perception quality of the user, provides a more intelligent and personalized hearing solution for the hearing impaired, and can effectively increase the hand-on performance and self-updating performance of the user through individual training and a self-updating module, so that the user can conveniently use the hearing aid.

The invention discloses an acoustic simulation method and system based on a low-frequency waveguide digital grid and geometric modeling, and relates to the technical field of acoustic simulation. A three-dimensional scene model composed of triangular patches is imported, and sound source parameters and the position of a receiver are initialized; based on the three-dimensional scene model, the sound source parameters and the receiver position, multiple sound field propagation paths are obtained through geometric acoustic pre-analysis, and initial perception importance parameters are calculated for each sound field propagation path. And distributing each sound field propagation path to a first calculation strategy or a second calculation strategy for processing according to the initial perception importance parameter. According to the method, through geometric acoustic pre-analysis and real-time dynamic evaluation, a high-precision calculation strategy is only allocated to a key sound field propagation path with high perceptual contribution degree, and an efficient geometric method is adopted for a large number of secondary paths. According to the resource scheduling strategy based on auditory perception, computing resources are highly focused, and meaningless consumption of secondary components is avoided.

The invention is suitable for the technical field of audio signal processing, and provides a sparse auditory pulse coding method and device fusing a masking effect and a dynamic threshold. According to the auditory rarefaction method provided by the embodiment of the invention, a human auditory perception mechanism can be combined, and the threshold group characteristics are utilized to realize time sequence pulse coding, so that the audio signal can directly adapt to the pulse neural network model, the coding efficiency and fidelity are improved, and meanwhile, the data redundancy is reduced. While the perception quality is ensured, the number of pulse events can be remarkably reduced, the energy efficiency and accuracy of a recognition task are improved, and the method is naturally adaptive to brain-like hardware and a pulse neural network. According to the embodiment of the invention, the masking effect of psychoacoustics is fused into the pulse coding process for the first time, and is highly consistent with the feeling and processing mode of organisms on sound signals. The biological reasonability is relatively high.

An in-ear audio transducer such as a single earphone or a pair of earphones produces audio which accounts for frequency detected hearing impairment and auditory masking conditions spanning frequencies expected to be encountered by the user, thereby improving auditory perception without having to increase overall volume as much as in the prior art. The audio transducer(s) communicates with an audio base unit configured to output modified multichannel digital audio data. The in-ear audio transducer element has a processing unit, a plurality of transducer amplifiers and a plurality of acoustic elements.

This invention discloses a multi-labeled sound recognition method for birds, including a training phase and an inference phase. The training phase includes the following steps: inputting audio data labeled with multiple tags, and extracting three complementary acoustic representations in parallel through a multi-view feature extraction module. This application uses parallel configuration of Mel spectrogram extraction submodules, CQT spectrogram extraction submodules, and CWT spectrogram extraction submodules to capture complementary features in the audio signal related to human auditory perception, such as energy distribution, pitch and harmonic structure, transients, and sharp calls. Furthermore, the three acoustic representations are aligned in the time dimension to form a comprehensive multi-view feature representation. Compared to existing technologies using fixed view combinations or single feature extraction methods, this design effectively avoids the problem of single-view failure due to noise or occlusion, providing a rich and reliable feature foundation for subsequent recognition tasks and significantly improving feature adaptation capabilities in complex soundscape environments.

The invention relates to the technical field of pipeline water leakage detection and fire fighting equipment, and discloses a fire hydrant device and method for intelligent detection of pipeline water leakage. In order to solve the problems of limited operation time, high experience dependency, environmental noise interference and the like in the traditional manual detection technology, the invention provides an integrated solution that an embedded control unit, a broadband underwater sound sensing module and a solar energy supply system are arranged on a fire hydrant base body, and pipeline sound wave signals are collected in real time. After the preprocessing of pre-emphasis, 43-dimensional feature vectors are extracted from three aspects of time domain, frequency domain and auditory perception, and leakage probability and confidence coefficient prediction is realized in combination with a pre-trained SVM classification model, so that the detection efficiency and the confidence coefficient are improved; and the cloud platform receives the data based on the MQTT protocol and judges whether an early warning mechanism is triggered or not. The device supports long-term unattended operation, significantly reduces the manual inspection cost through a confidence threshold and a trigger alarm mechanism, is suitable for intelligent monitoring and early leakage early warning of a municipal water supply network, and is suitable for popularization and application.

The application relates to the technical field of automobile detection, in particular to an abnormality detection method based on auditory perception. The method comprises the following steps: S1, performing Mel band analysis on an audio signal to obtain a Mel spectrogram; S2, setting a frequency range of interest, calculating the total energy of the Mel spectrum in the frequency range of interest, and performing smoothing processing on the total energy; S3, calculating the mean value and the standard deviation according to the smoothed energy, and setting a dynamic detection threshold based on the mean value and the standard deviation; S4, monitoring the time point at which the energy exceeds the dynamic detection threshold as a preliminary abnormal point, calculating the frequency band energy difference between the preliminary abnormal point and the previous and subsequent time points, and identifying an energy prominent frequency band according to the difference; S5, verifying whether the energy prominent frequency band is continuous and whether the length of the continuous frequency band reaches a preset minimum value, and if yes, determining that the preliminary abnormal point is an effective abnormal point; and S6, outputting the time, the center frequency, the frequency range and the bandwidth information of the effective abnormal point.

This application relates to a speech encoding method performed by a computer device the method, including: performing subband decomposition on a target speech signal to obtain a plurality of subband excitation signals; obtaining an auditory perception representational value that corresponds to each subband excitation signal; determining at least one first subband excitation signal and at least one second subband excitation signal from the at least two subband excitation signals; obtaining a gain of each of the at least one first subband excitation signal relative to a preset reference excitation signal as an encoding parameter that corresponds to the first subband excitation signal; obtaining a corresponding encoding parameter that is obtained by quantizing each of the at least one second subband excitation signal; and performing encoding on each subband excitation signal based on the encoding parameter corresponding to the subband excitation signal.

The application discloses a speech enhancement model training method and system based on a subband loss function, a terminal and a medium, and relates to the technical field of speech enhancement. The method comprises the following steps: obtaining noisy speech and clean speech, and determining the logarithmic power spectrum of the enhanced speech and the logarithmic power spectrum of the target speech respectively; based on the mel scale, the logarithmic power spectrum of the enhanced speech and the logarithmic power spectrum of the target speech are segmented respectively to obtain the subband of the enhanced speech and the subband of the target speech; the subband loss value between each enhanced speech subband and the corresponding target speech subband is determined; a perceptual weight is assigned to each subband loss value, and the overall loss value is determined to guide the speech enhancement model training. The application can guide the speech enhancement model to exhibit differentiated learning behavior for different frequencies, so as to make the speech enhancement model output speech that is more in line with the human auditory perception law, and significantly improve the listening comfort after speech enhancement.

The application provides a brain electrical response deep learning classification and identification method based on underwater acoustic signal stimulation, which is based on brain electrical signals and combines deep learning to classify and identify underwater acoustic target signals. The method fully utilizes the differences in the subjective sensitivity of people to underwater noise and underwater acoustic signals, the rapid auditory perception of the human brain to different types of underwater acoustic signals and the differences in the conscious information extraction, takes the brain electrical signals as the main input signals, and classifies and identifies the underwater acoustic signals after corresponding processing of the brain electrical signals. The application plays the "filtering characteristics" of the human brain which is more advanced and more targeted than computers, and the characteristics of more accurate classification and identification, and can improve the poor target recognition effect in a low signal-to-noise ratio environment in the traditional underwater acoustic target classification method.

This disclosure relates to the field of electroencephalogram (EEG) signal processing technology, specifically to a method, device, system, and electronic device for synchronous feedback of proprioceptive brainwave audio auditory perception. The method receives EEG signals from an EEG acquisition device online via a host computer, acquires EEG signals of a specified frequency band, extracts corresponding EEG features, and, based on a specified audio representation and audio generation method, segments the specified frequency band EEG signals into multiple EEG segments according to the EEG features or preset rhythm parameters. Multiple audio representations corresponding to these segments are then generated. The feature parameters of the audio representations are determined based on the EEG features of the corresponding EEG segments. Brainwave audio representation data is generated based on the audio representations corresponding to one or more specified frequency band EEG signals, and brainwave audio is obtained from the brainwave audio representation data. This simultaneously satisfies the physiological adaptability of neural modulation and the artistic expressiveness of audio generation, achieving an organic unity between neural modulation and audio generation.

The invention discloses a multi-mode interaction method, system and device of an intelligent driving alarm system, and relates to the technical field of intelligent driving assistance, and the method comprises the following steps: reading a user configuration file, and determining a preference coefficient; collecting data to generate an alarm feature vector; aiming at the active and passive security functions, generating a directional audio instruction by utilizing a spatial audio engine; aiming at a cruise auxiliary function, combining a preference coefficient and an emergency level, and generating an activation mode set by utilizing self-adaptive grading logic; performing hierarchical arbitration on the visual request by using a Z-Order mechanism, and executing visual interference suppression for an instrument screen; and monitoring the media volume to execute audio dodging, and synchronously outputting each instruction. According to the method, spatial auditory perception and non-interfering visual presentation of the alarm information are realized through equal-power sound image positioning, gating modal decoupling and differential display rendering strategies, the alarm intensity and user preference are balanced, and the driving risk caused by information shielding is effectively avoided.

The invention provides a neuromorphic auditory sense processing system and auditory sense sensing equipment based on a sensing and calculation integrated framework. According to the system, a whole processing task is divided into a processing system PS end and a programmable logic PL end; the ARM kernel located at the PS end of the processing system is responsible for advanced task scheduling and external storage control, and all high-load neuromorphic processing tasks are unloaded to the PL end; the PL end serves as a core computing unit and integrates a parallel bionic cochlea model and a pulse neural network engine; the parallel bionic cochlea model communicates with the pulse neural network engine through a high-speed AXI-Stream bus, and seamless transmission of a pulse event flow between a sensing front end and a calculation rear end is ensured. According to the method, through simulating a complete process of a biological auditory path, efficient integration from original audio perception to pulse feature extraction to classification decision is realized.

The present invention provides a fan control device that can control the fan speed so that it is less likely to be perceived as noise by people inside the vehicle. [Solution] A fan control device equipped with a processor controls a fan that cools an object to be cooled inside a vehicle, wherein the processor acquires ambient sound inside the vehicle picked up by a microphone installed inside the vehicle, performs frequency analysis on the acquired ambient sound to derive first analysis data, obtains second analysis data which varies depending on the fan rotation speed and is obtained by frequency analysis of the sound generated when the fan rotates, and determines an upper limit of the fan rotation speed based on the first analysis data and the second analysis data such that a first index, which is an index related to auditory perception of the ambient sound, satisfies a predetermined first condition.

The invention discloses a vehicle-mounted broadcast service following seamless switching method and a vehicle-mounted broadcast system.The switching method is applied to the vehicle-mounted broadcast system and comprises the following steps that S1, DAB frequency band signals and / or FM frequency band signals are received at the same time through double antennas, the current DAB or FM service is played through a foreground channel of a DAB module, and the DAB frequency band signals and the FM frequency band signals are received through double antennas; the background channel searches a DAB replaceable service and / or an FM replaceable service corresponding to the same program; s2, the DAB module carries out audio phase and amplitude synchronization processing on the current service and the replaceable service searched in the background, so that audio parameters of the current service and the replaceable service are consistent; s3, collecting the signal quality of the current service and the replaceable service in real time; and S4, judging whether to execute non-delay switching according to the signal quality index. According to the invention, seamless switching of three scenes of DAB-DAB, DAB-FM and FM-DAB is realized, a user does not have any auditory perception, the audio frequency is not abnormal in the switching process, bidirectional switching of analog FM and digital DAB is realized, and the method is suitable for vehicle-mounted broadcast application scenes at home and abroad and is wider in applicability.

The application discloses a kind of multi-channel speech enhancement method and system based on near-field beam forming, belong to speech enhancement field.The application generates the single-channel enhanced signal of beam forming to original multi-channel speech signal;The real part and the imaginary part of complex spectrum are extracted as network input characteristics by short-time Fourier transform;By constructing auditory perception neural network, introduce the cost function based on human ear masking effect;By training to minimize the cost function, guide the network to optimize between suppressing noise and recovering clean speech, output clean single-channel speech signal containing high-quality amplitude and phase information, complete speech enhancement task.The application can solve the problem of near-field multi-channel speech enhancement under complex noise scene.

The invention provides an emotional self-adaptive multi-mode piano teaching training system and method, and relates to the technical field of intelligent education systems.By integrating a physiological signal monitoring module, heart rate variability and skin electroreaction data of a player are collected in real time, and the emotional state (such as excitation, tension or calm) of the player is analyzed; generating an emotion-skill mapping model; based on the model, the intensity distribution of tactile path guidance and the rhythm compensation constraint of auditory perception regulation are dynamically adjusted, so that guidance signals (such as tactile vibration frequency and rhythm pulse) are adapted to the emotion fluctuation of a player in real time, and the uniformity of skill execution and emotion expression is synchronously improved in training. Finally, the system generates an emotion-enhanced playing manifold through multi-modal fusion, and projects the emotion-enhanced playing manifold to the surface of the key, thereby enhancing the music expressive force adaptability of the learner.

The invention provides a tone-constraint-based tone height correction method and computer equipment, and the method comprises the steps: determining a monaural audio and an accompaniment audio from preset song audios, carrying out the tone recognition of the monaural audio, obtaining the tone recognition information, and carrying out the tone height correction of the monaural audio according to the tone recognition information through employing a preset tone constraint condition, and carrying out tone height correction on the monaural voice audio to obtain a target voice audio, and generating a target song audio according to the target voice audio and the accompaniment audio. Therefore, tone height correction is carried out according to the tone identification information, the mismatch probability is reduced, the consistency of the overall tonality color and style of the song is ensured, and the auditory feeling is further improved.

The invention discloses an LED light bar rhythm control method based on audio frequency spectrum analysis, and relates to the technical field of LED light rhythm control, and the method comprises the steps: 1, collecting an original audio signal through a microphone at a preset sampling frequency, dividing the original audio signal into a plurality of short-time audio frames with a preset frame length, performing windowing processing, normalization processing and fast Fourier transform on each short-time audio frame in sequence to obtain an amplitude spectrum corresponding to each short-time audio frame; by adopting the non-uniform frequency band division based on the barker scale, the light response is more in line with the auditory perception of human ears; half-wave rectification spectrum flux is combined with an adaptive threshold to realize high-precision transient detection, rhythm impact such as drumbeat can be sensitively captured, and light brightness can be adaptively enhanced according to transient intensity; through spatial mapping of one-to-one correspondence of frequency bands and light bar areas and color distribution of low-frequency warm colors and high-frequency cold colors, light expression is more layered.

There is provided an audio signal authenticator (200) comprising a block boundary detector and a block divider (205) configured to receive an audio signal (171) and to output a sequence of a plurality of audio blocks (201) having embedded authentication information or having embedded authentication access information (212, 162), the authentication access information is related to where the authentication information can be retrieved. The authentication information (141) comprises an audio feature (151) belonging to the current audio block (201). The audio signal authenticator (200) comprises a perceptual similarity analyzer (240) configured to: compare an audio block (201) of the received audio signal (171) with an audio feature (151) of the extracted or retrieved authentication information (141), or comparing the audio feature extracted from the audio block (201) of the received audio signal (171) and the audio feature (151) of the extracted or retrieved authentication information (141) with each other, thereby providing a similarity result (241). The audio feature is a human auditory perception audio feature related to human auditory perception.

The invention provides an engine sound quality evaluation method, system and device and a medium, and belongs to the technical field of engines. The method comprises the steps that firstly, multichannel noise signals of an engine under multiple working conditions are collected, acoustic parameters such as loudness, sharpness, roughness and fluctuation of the noise signals are calculated, and comprehensive acoustic parameter vectors of all the working conditions are obtained after synthesis; meanwhile, reference scores of the corresponding noise signals are obtained based on an expert audition test and synthesized into a comprehensive reference score; and then, taking the comprehensive acoustic parameter vector as input, taking the comprehensive reference score as a target, and training a neural network to construct a sound quality evaluation model. And finally, for a to-be-evaluated working condition, a score can be output by the model only by inputting the comprehensive acoustic parameter vector of the to-be-evaluated working condition. According to the method, the neural network model based on objective acoustic parameters and standardized subjective scoring is constructed, so that the beneficial effect of efficiently, stably, automatically and objectively evaluating the sound quality of the engine, which is highly consistent with human auditory perception, is achieved.