52 results about "Active noise control system" patented technology

Automated attention handling techniques are described herein for use with wearable audio components with active noise control (ANC) to suppress ambient sound. A name embedding model is trained automatically to convert name audio samples into acoustic segments based on a knowledge distillation model. The name embedding model is used to generate reference embeddings for each of a user-enrolled set of names, and a relation network and a false rejection network are also trained. In real-time operation, the name embedding model converts real-time audio samples to real-time embeddings, the relation network compared the real-time embeddings to the reference embeddings to look for candidate matches, and the false rejection network validates the candidate matches to detect when one of the user-enrolled names has been invoked. Detecting such an invocation automatically triggers the ANC to switch to a conversation mode.

Automated attention handling techniques are described herein for use with wearable audio components with active noise control (ANC) to suppress ambient sound. A name embedding model is trained automatically to convert name audio samples into linguistically distinct name classifications and / or unified audio samples. The name embedding model is used to generate reference embeddings for each of a user-enrolled set of names, and a relation network and a false rejection network are also trained. In real-time operation, the name embedding model converts real-time audio samples to real-time embeddings, the relation network compared the real-time embeddings to the reference embeddings to look for candidate matches, and the false rejection network validates the candidate matches to detect when one of the user-enrolled names has been invoked. Detecting such an invocation automatically triggers the ANC to switch to a conversation mode.

Automated attention handling techniques are described herein for use with wearable audio components with active noise control (ANC) to suppress ambient sound. A name embedding model is trained automatically to convert name audio samples into linguistically distinct name classifications and / or unified audio samples. The name embedding model is used to generate reference embeddings for each of a user-enrolled set of names, and a relation network and a false rejection network are also trained. In real-time operation, the name embedding model converts real-time audio samples to real-time embeddings, the relation network compared the real-time embeddings to the reference embeddings to look for candidate matches, and the false rejection network validates the candidate matches to detect when one of the user-enrolled names has been invoked. Detecting such an invocation automatically triggers the ANC to switch to a conversation mode.

Automated attention handling techniques are described herein for use with wearable audio components with active noise control (ANC) to suppress ambient sound. A name embedding model is trained automatically to convert name audio samples into acoustic segments based on a knowledge distillation model. The name embedding model is used to generate reference embeddings for each of a user-enrolled set of names, and a relation network and a false rejection network are also trained. In real-time operation, the name embedding model converts real-time audio samples to real-time embeddings, the relation network compared the real-time embeddings to the reference embeddings to look for candidate matches, and the false rejection network validates the candidate matches to detect when one of the user-enrolled names has been invoked. Detecting such an invocation automatically triggers the ANC to switch to a conversation mode.

The invention discloses an online modeling and control method for a narrowband active noise control system, which comprises the following steps of: (1) performing frequency estimation on a signal picked up by a reference microphone by using a triangular cascade adaptive notch filter algorithm, and calculating an online estimated value of a signal-to-noise ratio by using energy of an input signal and an output signal of a notch filter; (2) when the online estimated value of the signal-to-noise ratio is larger than a preset value, modeling and control are started, a reference signal and auxiliary noise are generated based on the estimated frequency, and a control signal is calculated; (3) estimating auxiliary secondary sound by using the auxiliary noise; (4) estimating the sum of the primary sound and the secondary sound of the error signal at the noise frequency by using the reference signal; (5) updating the estimation of the frequency response of the secondary path at the auxiliary noise frequency and the frequency response of the auxiliary filter at the narrow-band noise frequency; (6) obtaining the estimation of the frequency response of the secondary path at the narrowband noise frequency in an interpolation mode; (7) updating the filter coefficient of the controller; and (8) outputting a control signal to drive a secondary source loudspeaker to produce sound, propagating the sound through a secondary path, and coherently superposing the sound with the initial noise signal at the error microphone to realize a noise reduction function. According to the method, the secondary path can be accurately modeled online, compared with an existing algorithm, the auxiliary noise energy is low, the convergence speed is high, the noise reduction effect is good, meanwhile, the problem that the same parameter operation results are different in a traditional auxiliary white noise online modeling algorithm is solved, and the algorithm stability is better.

The application provides a kind of multi-channel active noise control method, system, terminal and storage medium, and noise control method includes the following steps: establishing distributed wave domain ANC network model;The global cost function of wave domain ANC problem is split into local cost function and the form of the sum, and a distributed optimization problem is established;Multi-channel distributed wave domain ANC problem is solved using diffusion LMS algorithm, to obtain the estimation of loudspeaker weight;Secondary sound field is generated and residual noise signal is cancelled out.The application also provides a kind of multi-channel active noise control system, terminal and computer readable storage medium.The application uses diffusion strategy to obtain multi-channel distributed wave domain ANC algorithm, so that the calculation burden is dispersed among nodes, compared with centralized scheme, the application makes the expansibility of wave domain ANC system stronger, more robust, more suitable for large-scale application occasions.

This invention discloses a low-frequency noise reduction and sound insulation device for industrial applications, belonging to the field of noise control technology. The device includes an outer soundproof cover, an inner composite sound-absorbing structure, and an active noise control system. The outer soundproof cover is constructed of high-density board. The inner composite sound-absorbing structure is located on the inner wall of the outer soundproof cover and includes an acoustic metamaterial layer and a micro-perforated plate layer, which are spaced apart to form a first resonant cavity. The active noise control system includes: an error microphone embedded in the inner wall of the outer soundproof cover; a controller electrically connected to the error microphone; and a secondary sound source electrically connected to the controller and installed on the inner wall of the outer soundproof cover. This invention achieves broadband passive sound absorption through the composite structure of acoustic metamaterial and micro-perforated plate, providing a high signal-to-noise ratio environment for the active control system. Furthermore, the active control system based on the FxLMS algorithm precisely cancels residual low-frequency line spectra, achieving efficient and stable low-frequency noise reduction.

An apparatus for cancelling a noise signal may comprise a sensor configured to detect noise outside a vehicle and generate the noise signal associated with the detected noise. The apparatus may further comprise a first noise cancellation circuit to generate a first noise cancellation signal for a first frequency band and a second noise cancellation circuit to generate a second noise cancellation signal for a second frequency band. One or more processors, along with memory storing instructions, may control the first noise cancellation circuit to perform noise cancellation on the first noise signal in the first frequency band. Upon determining that the vehicle has entered an enclosed space, the second noise cancellation circuit may perform a second noise cancellation operation on the second noise signal in the second frequency band. The second frequency band corresponds to noise generated while the vehicle is within the enclosed space.

The invention discloses a range hood pipeline noise active control device and a noise reduction method thereof. The active control device of the extractor hood comprises a rotating speed sensor mounted on a turbofan of the extractor hood, a noise pickup microphone mounted under an air inlet of the extractor hood, and a reference microphone mounted at an air inlet grille of the extractor hood, the loudspeaker is mounted on the inner side of an air inlet cover of the range hood; and the controller is mounted on the right side wall of the range hood. The invention further discloses a wide-narrow-band hybrid active noise control method and a step length optimization method, the performance of the narrow-band controller in the wide-narrow-band hybrid active noise control system for coping with the target noise narrow-band component is improved, and therefore the stability and convergence of the whole system are improved.

The present invention discloses a full-band silencer system and a silencer method thereof, comprising: a silencer outer shell connected to a pipeline, the silencer outer shell comprising an air inlet pipe and an air outlet pipe; an inner guide seat, the guide seat being fixedly mounted inside the silencer outer shell; a silencer structure, the silencer structure comprising a plurality of reference sensors, a secondary sound source located on the right side of the reference sensor and connected to the inner guide seat, an error sensor arranged on the side of the inner guide seat close to the air outlet pipe, an active control system is adopted to reduce the noise value in the pipeline, and the active noise control algorithm for suppressing secondary sound feedback proposed in this case adopts a dual-reference microphone array method to indirectly estimate the actual reference signal after suppressing the feedback sound signal, thereby providing more accurate noise information for the active noise control system, and stimulating the secondary sound source arranged in the pipeline to achieve a more superior noise reduction effect at the error point.

The invention provides an active noise control system for a vehicle exhaust system and a working method.The active noise control system comprises a control unit, a sound source emitter and an error microphone, the control unit obtains the real-time rotating speed of an engine through a vehicle CAN bus, the sound source emitter is arranged in a pipeline of the exhaust system, and the error microphone is arranged in the pipeline of the exhaust system; the sound source emitter is arranged in the engine and is in communication connection with the control unit, and the sound wave transmission direction of the sound source emitter is opposite to the noise transmission direction of the engine; and the error microphone is arranged in the exhaust pipeline at the downstream of the sound source emitter and is in communication connection with the control unit. The problems that an existing silencer is large in size, and the space and the silencing effect cannot be considered at the same time are solved.

The application discloses an active noise reduction control system and method of a smart phone, comprising an environmental sound acquisition module, a motion state sensing module, a deep learning processing module, a noise reduction signal generation module, a noise reduction execution module, a user preference setting module, a scene recognition module and a power management module; the environmental sound acquisition module collects signals in all directions through a multi-microphone spatial array, and wide frequency response and high sampling rate ensure data quality; the motion state sensing module monitors phone motion parameters in real time to provide a basis for noise reduction strategy adjustment; the deep learning processing module adopts a hybrid model architecture combined with GPU acceleration to accurately analyze noise characteristics; the noise reduction signal generation module can generate adaptive noise reduction signals according to analysis results; and the noise reduction execution module adopts active feedback control and multi-mode sound generation strategies; the application significantly improves the accuracy, adaptability and intelligent level of noise reduction, and greatly improves the auditory experience of users when using the phone in different scenarios.

The invention provides a hybrid active noise control method of a new variable step size LMS algorithm based on a piecewise function, and the method comprises the steps: 1, collecting original data through an acoustic sensor, and carrying out the preprocessing of the collected original data through MATLAB, and obtaining a reference signal; 2, dividing the convergence process of the LMS algorithm into an initial stage, a transition stage and a steady-state stage on the basis of the difference between the expected response signal and the filtered output signal, designing a corresponding step length function for each stage to obtain a segmented step length function, and obtaining a new variable step length LMS algorithm based on the segmented step length function; 3, verifying the convergence speed, the steady-state precision and the steady-state stability of the new variable step size LMS algorithm based on a mean square error (MSE); and step 4, realizing actual noise control of the industrial workshop based on the hybrid active noise control system fused with the new variable step size LMS algorithm. According to the method, the algorithm is rapidly converged, meanwhile, the high-steady-state noise reduction precision is guaranteed, and the noise suppression effect continuously approaches to the optimal effect.

The present application discloses a hearing device with active noise cancellation, comprising: a microphone system comprising two microphones disposed outside the ear canal of a wearer when the hearing device is worn, where the microphone system is configured to capture audio and to generate an audio signal based on the captured audio; an ambient sound detector configured to receive the audio signals, the ambient sound detector further configured to determine a classification of an ambient sound environment based on the audio signals, where the classification includes determining a coherence metric between at least two audio signals; and an active noise control system configured to receive the audio signal, the active noise control system configured to generate a feed-forward compensation signal based on the audio signal; wherein the hearing device is configured to mix an audio signal with a proportion of the generated feed-forward compensation signal according to a determined classification of the ambient sound environment.

The present invention discloses an active noise control system and method based on a convolutional recurrent neural network. The system consists of a preprocessing module, a convolutional recurrent neural network, a signal reconstruction module, and a network loss module. The preprocessing module is used to preprocess a reference signal and a sound signal and extract corresponding features. The convolutional recurrent neural network consists of two convolution modules, a recurrent neural network, and two deconvolution modules. The reference signal features and the sound signal features are used as network inputs to predict the elimination signal features. The signal reconstruction module is used to reconstruct the elimination signal features in the frequency domain into an elimination signal in the time domain. The elimination signal is played through a loudspeaker to achieve the purpose of noise control. The network loss module consists of a psychoacoustic model and a loss calculation module. The masking threshold is obtained through the psychoacoustic model, and the total network loss is calculated. The gradient is back-propagated and used to update the weights of the network module.

An active noise control system capable of canceling noise independently of displacement of a user's head is provided. In a first system signal processing section (111), adaptive filters (1111-1114) generate noise canceling sounds, a first system selector (1117) selects an output of a first system auxiliary filter corresponding to a noise canceling position matching a detected position of the user's right ear, out of outputs of a plurality of first system auxiliary filters (1116) corresponding to different noise canceling positions, respectively, a first system subtracter (1115) subtracts the selected output from an output of a first microphone (13), and outputs the result as an error signal to the first system adaptive filters and second system adaptive filters of a second system signal processing section (112). The noise canceling positions corresponding to the plurality of first system auxiliary filters are arranged at prescribed intervals only within a space in which the user seated on a seat can move the right ear by turning, laterally bending the head within a prescribed range in the up-down and front-back directions.

Provided is an active noise control system capable of well canceling noise regardless of displacement of a user's ear. In a first system signal processing section (111), a first system auxiliary filter (1116) generates a correction signal that corrects an error signal from a noise signal, a first system subtracter (1115) subtracts the correction signal from an output of a first microphone (13) as the error signal, adaptive filters (1111-1114) perform adaptive operation using the error signal, and generate a canceling sound to be output from a first speaker (12). A DMS (18) detects a position of the user's ear. If the position of the user's ear moves, a controller (16) stops the adaptive operation, updates a transfer function of the first system auxiliary filter to a transfer function corresponding to a noise canceling position that matches the position of the user's ear, then gradually changes a transfer function of the adaptive filter to a transfer function corresponding to the matching noise canceling position, and resumes the adaptive operation after the change is completed.

The embodiment of the invention discloses a fault detection method for a self-adaptive noise reduction system of a range hood and the range hood. The fault detection method comprises the following steps: controlling a plurality of loudspeakers to sound in sequence; respectively acquiring a plurality of reference microphone sound pressure distribution signals acquired by each reference microphone when each loudspeaker sounds and a plurality of error microphone sound pressure distribution signals acquired by each error microphone when each loudspeaker sounds; and according to the plurality of reference microphone sound pressure distribution signals and the plurality of error microphone sound pressure distribution signals, whether each loudspeaker, each reference microphone and each error microphone have a function fault is judged. According to the embodiment of the invention, the fault source can be accurately positioned by combining test signal excitation and sound pressure analysis, the problem that the microphone type cannot be distinguished due to the fact that a traditional detection method only depends on a single physical signal is solved, and the method is particularly suitable for a multi-microphone and multi-loudspeaker self-adaptive complex active noise control system and has a wide application prospect. Accurate fault detection of the self-adaptive noise reduction system in the range hood is realized.

The present disclosure provides systems and methods for adjusting the audio output of a wearable device based on a user's audio gain profile. The wearable device may receive an audiogram indicating one or more frequency ranges associated with hearing loss. The wearable device may determine the audio gain profile based on the audiogram. The wearable device may use one or more adjustment modules to determine a gain to apply to the audio output based on the audio gain profile. The adjustment modules may include an active noise control module, a hearing aid module, and a transparency control module. The wearable device may use a least mean square algorithm and / or a machine learning model to determine the amount of gain to apply.

Disclosed herein are embodiments of a method of operating a hearing aid with an active noise control system. The method can utilize an ambient sound detector for classification of an ambient sound environment, such as a coherence measure between audio signals. The method can further include mixing audio signals with a feed-forward compensating signal in dependence on the particular classification of the sound environment.

A method and apparatus for remote active noise control (ANC) of a vehicle is provided. The method includes: receiving one or more local signals from a vehicle, wherein each local signal includes a reference signal, a noise control signal, an error signal, or a virtual error signal; updating the adaptive filter using the one or more local signals; and transmitting the updated adaptive filter to the vehicle.

The invention relates to the technical field of intelligent control, in particular to a compressor unit working noise control system based on data analysis. The compressor unit working noise control system based on data analysis comprises a sound pressure segmentation demarcation module, a frequency band change extraction module, a sound energy concentration drifting module, a target frequency band locking module and an absorption execution triggering module. According to the method, fine division of a sound pressure trend in operation is realized by constructing a sound pressure change boundary, a frequency abrupt change region is extracted, a drift path with concentrated sound energy is captured, a target frequency position is screened according to frequency change direction consistency and time continuity, and a focusing frequency is further accurately corresponding to a control frequency band; the shielded area is adjusted in a linkage mode to achieve directional intervention and coverage control over a key noise propagation path, the frequency locking precision, the energy focusing stability, the dynamic response sensitivity and the synergistic effect efficiency of sound absorption shielding are improved, and therefore an active noise control system based on the characteristic evolution trend is established.

The invention discloses a method and a system for judging an iteration state of an active noise control system, and belongs to the technical field of active noise control. The method aims at solving the problems that an existing method depends on error signals for judgment, so that the judgment standard is fuzzy, and the accuracy is insufficient. According to the core scheme, monitoring of external error signals is abandoned, and essential analysis is conducted on the internal state of the algorithm. The method specifically comprises the steps of obtaining weight coefficients of all control filters of a system in real time; calculating the norm as a characteristic quantity; performing sliding window processing on the characteristic quantity; state indexes such as slope, variance and mean value change are calculated based on window data; and finally, judging whether the system is in a convergence or divergence state according to the indexes, and triggering stabilization operation during divergence. According to the method, the judgment standard is clearer and more accurate, and system hardware damage can be effectively prevented.

The application discloses a kind of vehicle active noise control systems and fusion method thereof, system includes acceleration sensor, microphone, speaker and controller, acceleration sensor, microphone and controller access vehicle A2B bus, controller also accesses vehicle CAN bus, controller includes engine noise active controller and road noise active controller, the sound signal picked up by microphone is output as error signal to engine noise active controller and road noise active controller respectively;Road noise active controller and engine noise active controller generate first excitation signal and second excitation signal using signal respectively, and controller outputs two excitation signals to corresponding speaker after fusion and runs.The vehicle active noise control system and fusion method thereof provided by the application realize the fusion of car ENC algorithm and RNC algorithm, reduce the consumption of computing power, and reduce the number and cost of vehicle microphones by sharing the same set of microphones.

The invention provides a noise reduction method and device and a vehicle, and relates to the technical field of noise control, the method comprises the steps that a first noise signal and a second noise signal are acquired, the first noise signal is related to real-time noise outside a first environment, and the second noise signal is real-time noise in the first environment; the first noise signal and the second noise signal are divided and downsampled, M first sub-band noise signals and M second sub-band noise signals are determined, and M is an integer greater than 1; according to the M first sub-band noise signals and the M second sub-band noise signals, a first optimal filter is determined, the first optimal filter is used for determining a first secondary sound source signal, and the first secondary sound source signal is used for offsetting the second noise signal. Based on the scheme, the noise reduction performance of the active noise control system and the response speed to noise change are guaranteed at the same time. The scheme can be applied to new energy automobiles.

Automated attention handling techniques are described herein for use with wearable audio components with active noise control (ANC) to suppress ambient sound. A name embedding model is trained automatically to convert name audio samples into acoustic segments based on a knowledge distillation model. The name embedding model is used to generate reference embeddings for each of a user-enrolled set of names, and a relation network and a false rejection network are also trained. In real-time operation, the name embedding model converts real-time audio samples to real-time embeddings, the relation network compared the real-time embeddings to the reference embeddings to look for candidate matches, and the false rejection network validates the candidate matches to detect when one of the user-enrolled names has been invoked. Detecting such an invocation automatically triggers the ANC to switch to a conversation mode.

A loudspeaker (10) includes a radiation surface (15). The radiation surface (15) has a first region (15a), a second region (15b), and a third region (15c), wherein the third region (15c) is a region between the first region (15a) and the second region (15b). When an axis passing through the third region (15c) and extending away from the radiation surface (15) is defined as a reference axis (10X), the loudspeaker (10) forms a first wavefront (16a) that propagates from the first region (15a) toward the reference axis (10X) and a second wavefront (16b) that propagates from the second region (15b) toward the reference axis (10X).

The invention discloses a feed-forward active noise control system and method based on a synchronous identification strategy. The system comprises a secondary sound source synthesis subsystem, a sound feedback channel online identification subsystem, a secondary channel online identification subsystem, a first auxiliary filtering subsystem and a second auxiliary filtering subsystem. Meanwhile, by utilizing the first auxiliary filtering subsystem, the independence between the secondary sound source synthesis subsystem and the secondary channel online identification subsystem is improved, and user parameter selection and system implementation are facilitated; a residual noise component which is separated by the first auxiliary filtering subsystem and is related to a reference signal is used as input of a global auxiliary noise amplitude adjustment module, so that the contribution of introduced global auxiliary noise to residual noise is effectively reduced, and the overall noise reduction performance of the system is improved; according to the method, a synchronous identification strategy of the sound feedback channel and the secondary channel is adopted, complex time-varying characteristics of the sound feedback channel and the secondary channel in an actual environment can be effectively dealt with, and the noise reduction application level of the system is improved.

An active noise control system includes an error adder that generates an error signal by adding an output of a left-seat left microphone and an output of a left-seat right microphone, an adaptive filter that generates a noise canceling sound from a reference signal by performing an adaptive operation using the reference signal and the error signal, a left channel gain adjustment section that adjusts a gain of the noise canceling sound to be output to a left-seat left speaker, and a right channel gain adjustment section that adjusts a gain of the noise canceling sound to be output to the left-seat right speaker. A ratio between the gains of the left channel gain adjustment section and the right channel gain adjustment section matches a ratio between loudness levels of noise transmitted to the output of the left-seat left microphone and the output of the left-seat right microphone.

A noise active control system, an active noise control method, and an engineering vehicle. The active noise control method is used for noise control in a noise suppression area of ​​an engineering vehicle, comprising: obtaining at least two groups of original noise data from different sources of the engineering vehicle based on a current working mode of the engineering vehicle; performing partial coherence analysis on each group of original noise data based on the at least two groups of original noise data to obtain groups of decoupled noise data after removing the influence of other groups of original noise data; generating active noise reduction signals corresponding to each group of decoupled noise data; generating sound-generating device driving signals based on the active noise reduction signals corresponding to each group of decoupled noise data; and sending the sound-generating device driving signals to a noise suppression sound-generating device located in or near the noise suppression area based on the current working mode, so that the noise suppression sound-generating device emits sound waves that suppress the noise in the noise suppression area.