26 results about "Audio filter" patented technology

A media system and a method of using the media system to reproduce spatial audio based on head-to-torso orientation, are described. The method includes determining a head-to-source orientation and a head-to-torso orientation based on head orientation data generated by a head tracking device. Determining the head-to-torso orientation includes determining torso movements based on movements of the head. The torso can be determined to move when the head movements meet a head movement condition, such as a predetermined angle of movement or pattern of movement. A binaural audio filter that is based on a head-related transfer function corresponding to both the head-to-source orientation and the head-to-torso orientation is applied to an audio input signal to generate an audio output signal. The audio output signal is played to accurately recreate spatial audio having sounds emitted to the user by a sound source. Other aspects are also described and claimed.

A system for synchronizing and spatializing media, comprising client device and server device. A method for operation includes: tracking the real-time spatial coordinates of both devices via wireless sensors; synchronizing media playback using a timestamp-based protocol that compensates for network latency and clock offset; and applying directional audio filters, such as Head-Related Transfer Functions (HRTF), on the client device to render audio appearing to originate from server device's physical location. The method is further characterized by compensating for acoustic propagation and signal processing delays to ensure accurate spatiotemporal alignment. The system may be enhanced by a multimodal Al configured to perform operations such as real-time voice-preserving translation and the generation of synchronized, spatialized haptic feedback based on semantic event markers.

The present invention discloses a smart noise reduction device including a control device; an audio waveform pattern recognizer coupled to the control device for identifying an audio mixed signal including a regularity signal and a non-regularity signal; an audio waveform pattern database coupled to the control device, including at least one audio type, each having a plurality of preset second regularity signals; and an audio filter coupled to the control device to obtain the regularity signal.

A system and method for synchronizing and spatializing media between client device and server device. Client-side artificial intelligence application determines the position of server device by fusing data from at least two sources: visual data obtained from a camera and acoustic data obtained from a predetermined reference signal emitted by server device. This data fusion enables continuous spatial tracking, including during periods of visual occlusion. A timestamp-based protocol is used to synchronize media playback. Based on the tracked position, client device applies directional audio filters, such as Head-Related Impulse Response (HRIR), to render audio that appears to originate from server device's physical location. The method further compensates for acoustic propagation and signal processing delays to ensure accurate spatiotemporal alignment.

A computer-implemented method, when executed by data processing hardware, causes the data processing hardware to perform various operations. These operations include receiving an audio signal from a sensor array at a unified post-filter, converting the audio signal to a short time Fourier transform (STFT) domain via a conversion function, determining a speech presence probability based on the converted audio signal, and determining a noise smoothing factor based on the speech presence probability. The operations further include estimating, via the unified post-filter, a noise power spectral density based on the noise smoothing factor, estimating, via the unified post-filter, a steering vector of the desired source, and generating, via the unified post-filter, a directivity-based mask and a coherence-based mask. Operations further include generating a residual echo spectrum estimate based on the directivity-based mask and the coherence-based mask, and setting one or more spectrum shaping factors based on the residual echo spectrum estimate.

The application discloses a digital filtering reconstruction method for lossless audio, and relates to the field of audio filtering reconstruction. Firstly, the transient vibration intensity of the segmented audio frame is extracted in real time to obtain a transient index value, and the transient index value is mapped into a window asymmetry factor by using a nonlinear control curve. According to the factor, a front half cycle attenuation compression and a rear half cycle stretching are applied to a reference window function to generate a dynamic asymmetric window and further obtain dynamic filter coefficients. Finally, the audio is weighted and convoluted by using the dynamic coefficients, and a cross-fading splicing technology is combined to eliminate frame boundary artifacts caused by dynamic adjustment. In this way, dynamic reconstruction can be realized only by relying on time-domain point-by-point modulation of a single set of filters, and the storage of a large number of filter banks or complex offline conversion requirements are completely eliminated.

The application discloses an audio signal adjustment method, device, equipment, medium and program product, and belongs to the field of audio processing. The method is executed by a client, and the method comprises the following steps: sending a reference audio signal to an airborne device in a target vehicle; recording a recorded audio signal, the recorded audio signal being a signal recorded by the client in a cabin of the target vehicle after the airborne device plays the reference audio signal; adjusting an audio filter with the same target of the recorded audio signal and the reference audio signal; and filtering a first audio signal played subsequently through the audio filter to obtain a second audio signal. The method records the recorded audio signal, the recorded audio signal being an audio signal associated with the reference audio signal, adjusts the audio filter with the same target of the two audio signals, and thus can filter and optimize the first audio signal played subsequently, so that the second audio signal is more suitable for listening in the current cabin.

A system for synchronizing and spatializing media, comprising client device and server device. A method for operation includes: tracking the real-time spatial coordinates of both devices via wireless sensors; synchronizing media playback using a timestamp-based protocol that compensates for network latency and clock offset; and applying directional audio filters, such as Head-Related Transfer Functions (HRTF), on the client device to render audio appearing to originate from server device's physical location. The method is further characterized by compensating for acoustic propagation and signal processing delays to ensure accurate spatiotemporal alignment. The system may be enhanced by a multimodal Al configured to perform operations such as real-time voice-preserving translation and the generation of synchronized, spatialized haptic feedback based on semantic event markers.

A computer-implemented method when executed by data processing hardware causes the data processing hardware to perform operations. The operations include receiving, from a sensor array, an audio signal at a unified post-filter, converting, via a conversion function, the audio signal into a Short-Time Fourier Transform (STFT) domain, determining, based on the converted audio signal, a speech-presence probability, and determining, based on the speech-presence probability, a noise smoothing factor. The operations also include estimating, via the unified post-filter, a noise power spectral density based on the noise smoothing factor, estimating, via the unified post-filter, a steering vector of a desired source, and generating, via the unified post-filter, a directionality-based mask and a coherence-based mask. The operations further include generating, based on the directionality-based mask and the coherence-based mask, a residual echo spectrum estimation and setting one or more spectral shaping factors based on the residual echo spectrum estimation.

This invention provides a speech echo cancellation system, relating to the field of audio signal processing technology. The system includes acquiring target audio data and reference audio data and importing them into an audio storage buffer area; reading the target audio data based on an FIR echo cancellation filter and performing convolutional noise cancellation processing using the audio filtering coefficients of the FIR echo cancellation filter to generate audio echo cancellation data; if the audio echo cancellation data meets preset filtering conditions, calculating the cancellation error between the audio echo cancellation data and the reference audio data; if the cancellation error meets preset update conditions, using an adaptive algorithm to calculate the audio filtering coefficient increment based on the cancellation error and updating the audio filtering coefficients; and performing echo component cancellation processing on the acquired current audio data using the FIR echo cancellation filter, outputting the current echo cancellation data to the playback end, thereby enabling accurate identification and cancellation of echo components in the audio signal.

An apparatus comprises means configured to: obtain respective two or more audio signals from two or more microphones; determining a first sound source direction parameter and a first sound source energy parameter in one or more frequency bands of the two or more audio signals based on the processing of the two or more audio signals; determining a second sound source direction parameter and a second sound source energy parameter in one or more frequency bands of the two or more audio signals based on the processing of the two or more audio signals; obtaining a region defining a direction and / or range for the filter; and generating a filter to be applied to the two or more audio signals, where a filter gain / attenuation parameter is generated based on a relationship of the region to the first sound source direction parameter, the first sound source energy parameter, the second sound source direction parameter, and the second sound source energy parameter.

An apparatus including circuitry configured to: obtain two or more audio signals from respective two or more microphones; determine, in one or more frequency band of the two or more audio signals, a first sound source direction parameter and first sound source energy parameter based on processing of the two or more audio signals; determine, in the one or more frequency band of the two or more audio signals, a second sound source direction parameter and second sound source energy parameter based on processing of the two or more audio signals; obtain a region defining a direction and / or range for a filter; and generate the filter to be applied to the two or more audio signals, wherein filter gain / attenuation parameters are generated based on the region in relation to the first sound source direction parameter, the first sound source energy parameter, the second sound source direction parameter and the second sound source energy parameter.

This disclosure presents a template-based intelligent video automatic synthesis method, system, device, and medium. The template-based intelligent video automatic synthesis method includes: automatically generating several segment information based on the original video and user-defined cover, title, main video, and back cover templates. These segment information includes cover, title, main video, and back cover information, and each segment is independently configured. The method also involves parallel processing of audio sources from these segment information using a constructed audio mixing pipeline, and obtaining mixed audio based on the audio filter corresponding to each segment and the processed audio sources. Finally, the method calls a target engine to process each segment of the segment information and the mixed audio, and automatically generates a synthesized video based on the resolution scaling strategy of each segment. This method enables efficient generation of structured videos in vertical domains, is simple to reuse, and has low cost.

An apparatus includes components configured to perform the following operations: acquiring two or more corresponding audio signals from two or more microphones; determining a first sound source direction parameter and a first sound source energy parameter in one or more frequency bands of the two or more audio signals based on processing of the two or more audio signals; determining a second sound source direction parameter and a second sound source energy parameter in one or more frequency bands of the two or more audio signals based on processing of the two or more audio signals; obtaining a region defining the direction and / or range for a filter; and generating a filter to be applied to the two or more audio signals, wherein filter gain / attenuation parameters are generated based on the relationship between the region and the first sound source direction parameter, the first sound source energy parameter, the second sound source direction parameter, and the second sound source energy parameter.

The invention discloses an audio data processing method and apparatus, and a storage medium. The method comprises the steps of obtaining a to-be-debugged audio and a calibration signal; adjusting the volume of the audio and the volume of the calibration signal respectively, and determining a first volume value of the calibration signal after the volume is adjusted; determining a target index value for performing compensation gain on the audio data based on the first volume value; inputting the target index value and the adjusted audio into an audio filter; and controlling the audio filter to carry out gain compensation on the adjusted audio according to the target index value, and obtaining a target audio output by the audio filter and corresponding to the adjusted audio. According to the scheme, the target index value for adjusting the audio filter is obtained through the standard signal, the corresponding compensation values of the low-frequency gain and the high-frequency gain can be automatically obtained under different volume conditions, the high-frequency gain and the low-frequency gain do not need to be calibrated by spending a large amount of time and labor, and the audio adjusting efficiency is improved.

A computer-implemented procedure, when executed by data processing hardware, causes the data processing hardware to perform operations. These operations include receiving an audio signal from a sensor array at a unified post-filter, converting the audio signal into a short-time Fourier transform (STFT) domain using a conversion function, determining a speech presence probability based on the converted audio signal, and determining a noise smoothing factor based on the speech presence probability. The operations also include estimating a spectral noise power density based on the noise smoothing factor across the unified post-filter, estimating a control vector of a desired source across the unified post-filter, and generating a direction-based mask and a coherence-based mask across the unified post-filter.The operations also include generating a residual echo spectrum estimate based on the direction-based mask and the coherence-based mask, and setting one or more spectral shaping factors based on the residual echo spectrum estimate.

Systems and methods of the present disclosure enable authentication and / or anomaly detection using machine learning-based modelling. Audio recordings that represent audio from a forced cough vocalizations are received from a user device. One or more audio filters extract forced cough vocalization recordings from the audio recordings and signal data signatures representative of the forced cough vocalization recordings are generated. Gaussian mixture models are produced for each unique combination of the signal data signatures, where each unique combination include a group of model baselines and a test match baseline. Each Gaussian mixture model is used to produce a match value for the associated test match baseline based on the associated model baselines, and a statistical score is determined for each match value. One or more baseline Gaussian mixture models are determined based on the statistical score and stored in a user profile.

Disclosed are systems and methods for rendering personal sound zones (PSZs) with head tracking using multiple loudspeakers, utilizing a Spatially Adaptive Neural Network (SANN) to dynamically generate and update audio filters that create acoustically bright and dark zones based on the listener head positions. First, the SANN encodes listener head coordinates and outputs corresponding PSZ filters as either time-domain impulse responses or frequency domain complex -valued coefficients. Then, acoustic transfer functions (ATFs) corresponding to the rendering loudspeakers and control points within PSZs are simulated at random room acoustics conditions and optionally measured in a specific rendering environment. The combined ATFs along with a unified loss function that incorporates multiple PSZ design objectives, are utilized in training the SANN for randomly sampled listener positions within the rendering area. Finally, the trained SANN is used for generating PSZ filters in real-time given a stream of head position data from a head tracking device.

The present application discloses a blade fault diagnosis method, apparatus and system, and a storage medium, the method includes: acquiring a blade rotation audio collected by an audio collection device during operation of a wind turbine generator system; preprocessing the blade rotation audio based on a wind noise filtering algorithm to obtain a blade rotation audio filtered out of wind noise; dividing the blade rotation audio filtered out of wind noise to obtain audio segments corresponding to blades of the wind turbine generator system respectively; diagnosing, based on the audio segments, whether the blades each corresponding to one of the audio segments are faulty. The present application can diagnose whether a corresponding blade is faulty respectively according to the audio segments of different blades, which improves the accuracy of the diagnosis results.

This invention provides an audio processing circuit and an audio processing method. The audio processing circuit includes at least one audio filter, at least one adaptive non-active noise reduction filter, and a leak detection circuit. The at least one audio filter is used to control an output signal for an audio function. The at least one adaptive non-active noise reduction filter is used to generate at least one non-noise-cancelled signal based on an audio playback signal. The leak detection circuit is used to perform leak detection based on a first input signal and a second input signal, and to adjust the at least one adaptive non-active noise reduction filter based on a leak detection result, wherein the first input signal indicates noise signal characteristics, and the second input signal originates from an error signal obtained by an error microphone picking up residual noise generated by the audio function.

The invention provides an attendance recognition management method and system, a readable storage medium and a computer. The method comprises the following steps: respectively carrying out data processing on face video stream data and short voice audio data of employees to obtain a key frame image sequence and an audio spectrogram; introducing a multi-scale space attention mechanism and a competitive multi-scale fusion algorithm into the expression recognition network model to obtain an expression recognition optimization model; performing multi-scale training on the audio filter, and optimizing the audio filter after the multi-scale training through a weighted fusion strategy to obtain an audio recognition optimization model; performing adaptive weighted fusion on the expression recognition optimization model and the audio recognition optimization model to obtain an attendance recognition model, and introducing an attendance rule into the attendance recognition model to obtain an attendance management model; and respectively inputting the key frame image sequence and the audio spectrogram into an attendance management model so as to realize attendance management of the employees. The system supports a plurality of attendance systems, and realizes personalized and intelligent attendance management.

To provide a method for generating a substitute frame for a lost audio frame of an audio signal, which can be advantageously applied to a low frequency effect (LFE) channel of a multi-channel audio signal.SOLUTION: The method comprises determining an audio filter based on samples of a valid audio frame preceding a lost audio frame, and generating a substitute frame based on the audio filter and the samples of the valid audio frame preceding the lost audio frame.SELECTED DRAWING: Figure 1

The application discloses a preparation method of a high-dissipation fatigue-resistant elastic body with low-frequency damping characteristics. By introducing polyvinylpyrrolidone and silica nanoparticles, and uniformly mixing two monomers of acrylic acid and 2-methoxyethyl acrylate, a simple free radical copolymerization reaction is carried out to obtain a high-dissipation fatigue-resistant elastic body with good mechanical properties and effective filtering of low-frequency noise. The elastic body can collect high-quality signals for a long time without mechanical fatigue risk. In the fatigue resistance test, the tear energy of the elastic body can reach 45008.93 J / m 2 , and it is not easy to be damaged itself. Under low-frequency (25, 50 Hz) signals, the elastic body shows a significant audio filtering effect compared with metal, polyurethane, PMMA and sponge with the same material thickness. The elastic body can prevent the influence of external stimuli (impact, friction and bending) during use, and different target products with different shapes can be prepared according to different required scenes. It is suitable for flexible electronic wearable fields.

The present application relates to the field of audio processing, and discloses an audio signal adjustment method and apparatus, a device, a medium, and a program product. The method is performed by a client. The method comprises: sending a reference audio signal to an on-board device in a target vehicle (310); obtaining a recorded audio signal by means of recording, the recorded audio signal being a signal recorded by the client in a cabin of the target vehicle after the on-board device plays the reference audio signal (320); with the goal of the recorded audio signal and the reference audio signal being identical, adjusting an audio filter (330); and filtering a subsequently played first audio signal by means of the audio filter, to obtain a second audio signal (340).

This disclosure provides an audio playback method and device. The method includes: receiving a rate adjustment instruction to adjust the audio playback rate from a first multiple of a preset standard rate to a second multiple of the preset standard rate; creating a second audio filter at the second multiple; invoking the second audio filter to perform a second multiple speed adjustment on second audio data in a first buffer to obtain third audio data, wherein the second audio data is obtained after the first audio filter performs a first processing on the first audio data, the first processing including at least one of the following: audio decoding, format conversion, sampling, and channel conversion; and playing the third audio data. This disclosure improves the smoothness of audio data playback by the player.

The embodiment of the application provides a kind of vehicle ambient sound synthesis method, device, electronic equipment and storage medium, by collecting ambient sound around vehicle, to obtain the sound frequency of all the sound signals, according to preset basic audio filtering rule and the actual needs of user, determine the corresponding sound frequency of the sound signal with louder sound or the longest duration as ambient base audio;Again according to preset and sound filtering rule, determine the odd harmonic of basic audio as ambient and sound frequency, and preset ambient tempo speed, according to preset ambient tempo speed, ambient and sound frequency and ambient base audio, generate vehicle ambient sound.The embodiment of the application generates vehicle ambient sound by collecting ambient sound, without external source and communication network.At the same time, ambient noise is used as a part of ambient sound, to achieve noise reduction without making users feel bad mood, diversified and sound generation mode also meets the personalized needs of users.