31 results about "Sound masking" patented technology

A sound masking apparatus and method mask conversation noise in a vehicle. The sound masking apparatus includes a microphone in a vehicle and a processor connected to the microphone. The processor may detect conversation noise using the microphone, may modulate the conversation noise to generate a masking sound source, and may mask the conversation noise by playing the masking sound source.

The invention discloses an audio power amplifier starting-up sonic boom suppression method based on a sound masking effect, and belongs to the technical field of power amplifiers, and the method comprises the following steps: S1, presetting a voltage reference value for audio detection; s2, correspondingly outputting a suppression signal or a working signal according to the comparison between the input voltage value and the voltage reference value; s3, generating a PWM signal, and connecting the PWM signal to a switch module through an AND gate and a buffer; s4, when the suppression signal is generated, it is judged that the audio input signal has sonic boom at the moment, and the output end of the power amplifier does not generate an impact signal; and when the working signal is generated, the output end of the power amplifier generates an impact signal containing a suppression effect. According to the invention, through input signal threshold detection, the composite sound superposed with the preset switch music signal is generated, and the method has the advantages of solving the bottleneck of response lag during shock-wave suppression of the D-type power amplifier and promoting the D-type power amplifier to be miniaturized.

The invention relates to an audio processing method, electronic equipment and a storage medium, and the method comprises the steps: obtaining a noise source signal in a vehicle driving process; determining a sound masking curve according to the noise source signal, wherein the sound masking curve is used for representing the frequency band distribution of the noise source and the intensity of each frequency band; and dynamically adjusting the energy of the target frequency band of the target audio based on the sound masking curve. According to the technical scheme, the sound masking curve is established based on the noise source signal, the energy of the target audio is dynamically adjusted in the driving process, and the use effect of the audio can be improved.

The invention discloses an in-vehicle call privacy control method and device, equipment and a medium. The in-vehicle call privacy control method comprises the steps of obtaining a pure voice signal of a target call user; performing framing windowing processing and short-time Fourier transform on the pure voice signal to obtain a time-frequency domain signal; performing time reversal processing on the time-frequency domain signal to obtain a time-frequency domain masking signal; performing inverse short-time Fourier transform on the time-frequency domain masking signal, and converting the time-frequency domain masking signal into a time domain masking signal; and driving a loudspeaker array in the non-target call user area to output a time domain masking signal. According to the embodiment of the invention, the intelligibility of the leaked voice signal in the non-target call user area can be reduced, the sound masking effect is improved, and the call content privacy security of the target call user is improved.

The invention discloses a refrigerator and a noise reduction method thereof.The refrigerator comprises a refrigerator body, a refrigerating system, a sound pressure sensor, a loudspeaker and a controller, and the refrigerating system is arranged in the refrigerator body and comprises a compressor, a condenser, an evaporator and a fan; the sound pressure sensor is arranged at a preset position outside the box body and is used for detecting sound pressure at the preset position; the loudspeaker is arranged on the box body and is used for playing masking sound to reduce noise; the controller is configured to acquire sound pressure data, detected by the sound pressure sensor, at a preset position during the automatic door opening and closing operation period of the refrigerator; and analyzing the sound pressure data, generating a target masking sound according to a frequency band where a sound pressure maximum value is located, and controlling the loudspeaker to play the target masking sound. The environment sound pressure data is considered based on the sound masking technology, the masking sound is generated according to the frequency band where the maximum value of the environment sound pressure is located for sound masking, and therefore noise generated when the door of the refrigerator is automatically opened and closed is reduced, and user experience is effectively improved.

The application discloses a kind of audio power amplifier booting pop noise suppression methods based on sound masking effect, belong to power amplifier technical field, this method includes: step S1: preset voltage reference reference value for audio detection;Step S2: according to the comparison of input voltage value and voltage reference reference value, corresponding output suppression signal or working signal;Step S3: generate PWM signal, through and buffer connection to switch module;Step S4: when generating suppression signal, it is judged that audio input signal exists pop noise at this time, and power amplifier output end does not generate impact signal;When generating working signal, power amplifier output end generates impact signal containing suppression effect.The present application generates composite sound by input signal threshold detection, which is superimposed with preset switch music signal, has the advantages of solving the response lag bottleneck when D-class power amplifier pop noise suppression and promoting D-class power amplifier to miniaturization.

The present application relates to the field of sound field measurement of medical ultrasonic diagnostic equipment, and particularly relates to a sound mask for limiting square area sound power measurement and a preparation method thereof. The sound mask comprises: a first absorbing layer, a reflecting layer, an intermediate layer and a second absorbing layer which are sequentially stacked from top to bottom; the reflecting layer is located at the central region of the first absorbing layer, the intermediate layer and the second absorbing layer, and a square sound transmission hole penetrating through the thickness of the reflecting layer is formed on the reflecting layer; the first absorbing layer, the reflecting layer, the intermediate layer and the second absorbing layer are tightly adhered through a pouring process to form an integral plate structure. The present application reasonably arranges the mask structure of the sound mask by establishing a theoretical model of sound wave vertical incidence multi-layer medium, so that the sound beam can be constrained, and the performance of the sound mask can strictly meet the technical requirements of the industry standard YY / T1084-2015.

The present disclosure relates to an audio-visual speech separation method and device, electronic equipment and storage medium, video information including target object sound and at least one reference object sound is acquired, and an image frame sequence composed of target object lip image frames in the video information and mixed audio are extracted, and the video feature and the audio feature corresponding to the target object are obtained by encoding respectively. The video feature and the audio feature are input into a trained multi-modal separation network, and the sound mask corresponding to the target object is obtained after multiple feature fusions. The multi-modal separation network includes a top module, a middle module and a bottom module for three times of feature fusion. The target audio recording the target object sound is determined according to the sound mask and the audio feature. The present disclosure fuses the information of two levels of vision and hearing multiple times through three modules, enhances the intra-modal context information, improves the audio-visual separation performance, and obtains an accurate audio separation result.

The invention belongs to the technical field of smart cities and environment regulation, solves the problem of how to enable sound and light to be associated and to be more fused with the surrounding environment, and relates to an urban public space sound scene and illumination intelligent collaboration device, which comprises a collection device configured to collect environmental parameters; the database is used for storing a natural sound source for sound masking; a speaker configured to play a natural sound; the lighting equipment is used for lighting; and the controller is configured to select a natural sound source from the database according to the environmental parameters, generate playing parameters, perform fast Fourier transform on the natural sound source, convert a time domain signal into a frequency domain signal, extract energy intensity of each frequency band and generate control parameters of the lighting equipment in combination with the environmental parameters. The invention also provides an urban public space sound scene and illumination intelligent cooperation method.

Embodiments relate to devices, systems, and methods for creating highly localized, remote audible zones or noise control zones by utilizing nonlinear interactions of ultrasonic beams. Ultrasonic sources may produce inaudible, straight or curved trajectories that can bypass obstacles, such as human heads or barriers or follow direct paths in open space. When intersecting at a designated target zone, the nonlinear acoustic interaction generates an audible difference-frequency wave within the human audible range, delivering targeted sound content without disturbing surrounding areas. Alternatively, the ultrasonic sources may produce beams to control and / or cancel audible content in a designated zone. These approaches enable precise, scalable, and obstacle-agnostic spatial audio and noise control with broad bandwidth, compact size, and high robustness even in reverberant environments, expanding possibilities in private communication, immersive audio, sound masking, and environmental noise mitigation.

This application discloses a sound masking method and apparatus, and a terminal device. When the terminal device uses a receiver as an output end of an audio signal, the terminal device determines, based on the audio signal, a masking sound signal, and then transmits the masking sound signal by using a speaker. The masking sound signal is determined based on the audio signal, and a difference between a distance from the speaker to a far field and a distance from the receiver to the far field is small. Therefore, the masking sound signal can better mask a leaked sound of the receiver and prevent information leakage in a call sound.

The utility model discloses tinnitus treatment equipment based on red light, low-frequency electrotherapy and bone conduction, and relates to the technical field of medical auxiliary instruments. Comprising a connecting piece, a control bin and an auxiliary bin, the control bin and the auxiliary bin are located at the two ends of the connecting piece respectively, ear hooks and bone conduction earphone vibrators located at the tail ends of the ear hooks are arranged on the front sides of the control bin and the auxiliary bin, red light physiotherapy assemblies are installed on the control bin and the auxiliary bin, and an electrode physiotherapy assembly is installed on the auxiliary bin. According to the equipment, when the electrode tip is plugged into the ear canal for low-frequency electrotherapy, the electrode tip can emit red light to irradiate the interior of the ear canal, and sound can be shielded in a bone conduction mode under the condition that the ear canal is blocked by the electrode tip, so that the influence of tinnitus on a patient is reduced; the device is very humanized in design, convenient to use and remarkable in treatment effect.

A method performed by an electronic apparatus, an electronic apparatus and a storage medium, which involves the field of artificial intelligence are provided. The method includes obtaining target sound masks of a target in a first video at respective moments, based on image-related information of the target, a first audio signal corresponding to the first video, and direction information of the first audio signal, and obtaining a second audio signal in which a sound related to the target is excluded, based on the target sound masks of the target at the respective moments and the first audio signal.

The embodiment of the invention provides a sound masking method, system and device, a storage medium and a program product. The method comprises the steps that external environment sound of a sound masking space where a target object is located is rearranged, a rearranged masking voice signal is obtained, and the difference between the frequency spectrum characteristics of the rearranged masking voice signal and the frequency spectrum characteristics of the external environment sound is smaller than or equal to a preset threshold value. And performing sound masking processing on the target object based on the rearranged masking voice signal. The method is used for achieving the effect of improving information confidentiality protection.

The application provides an oil fume exhaustor abnormal sound masking method and system based on an audio injection method, which is applied to an oil fume exhaustor control system and comprises the following steps: acquiring audio data of the oil fume exhaustor during operation; judging whether the oil fume exhaustor has abnormal sound during operation based on a comparison result of the audio data and preset audio data in a target dimension; the target dimension comprises a single frequency peak value difference, a frequency band deviation and an overall sound pressure level difference; if the oil fume exhaustor has abnormal sound, performing parameter optimization on parameters of a preset control sound based on the comparison result and a annoyance degree prediction model to obtain an optimized control sound; the parameters of the preset control sound comprise a frequency component, a frequency band range and a sound pressure level; and masking the abnormal sound of the oil fume exhaustor during operation based on the optimized control sound. The application alleviates the technical problem that the abnormal sound during actual operation cannot be effectively improved in the prior art.

The invention discloses a refrigerator and a noise reduction method thereof.The refrigerator comprises a refrigerator body, a refrigerating system, an environment temperature sensor, a loudspeaker and a controller, and the refrigerating system is arranged in the refrigerator body and comprises a compressor, a condenser, an evaporator and a fan; the environment temperature sensor is arranged on the box body and is used for detecting the environment temperature; the loudspeaker is arranged on the box body and is used for playing masking sound to reduce noise; the controller is configured to obtain the running state of the refrigerator and the environment temperature detected by the environment temperature sensor during the automatic door opening and closing running period of the refrigerator. And selecting a target masking sound from a plurality of preset masking sounds according to the running state and the environment temperature, and controlling a loudspeaker to play the target masking sound. The operation state of the refrigerator is considered on the basis of the sound masking technology, sound masking is conducted on the automatic door opening and closing conditions under different operation states and environment temperatures, and therefore noise generated when the door of the refrigerator is automatically opened and closed is reduced, and user experience is effectively improved.

A system and method are provided for dynamic sound mask adjustment. A sound mask is used for obtaining an impulse response measurement that adjusts a generated sound mask dynamically based on real-time ambient noise parameters, while maintaining echo canceller calibration performance. The system includes a dynamic sound mask generator that includes a noise accumulator and monitor that includes a processor and memory including instructions executed by the processor for performing the dynamic sound mask adjustment. If the sound mask is not in the hysteresis range, the current sound mask level and iteration update rate are adjusted. if the sound mask is in the hysteresis range, the current sound mask level and iteration update rate are maintained.

A method performed by an electronic apparatus, an electronic apparatus and a storage medium, which involves the field of artificial intelligence are provided. The method includes obtaining target sound masks of a target in a first video at respective moments, based on image-related information of the target, a first audio signal corresponding to the first video, and direction information of the first audio signal, and obtaining a second audio signal in which a sound related to the target is excluded, based on the target sound masks of the target at the respective moments and the first audio signal.

This application provides a video recording method and an electronic device. In a video recording process of the electronic device, if a user considers that a photographed picture involves privacy, a picture masking button on a photographing interface displayed on the electronic device may be triggered. In response to the triggering operation, the electronic device removes privacy content from a preview image collected by a camera. In this case, the electronic device still keeps a recording state. If the user considers that a sound collected by a microphone involves privacy, a sound masking button on the photographing interface may be triggered. In response to the triggering operation, the electronic device removes privacy content from the sound collected by the microphone. Therefore, in the video recording process, the electronic device can directly remove privacy information involved in recorded content, which does not affect the recording state.

A reminding method, system, and apparatus, a vehicle, a computer-readable storage medium, and a computer program product, which relate to the field of intelligent vehicles. According to the reminding method, a masking result of a sound masking system on a target sound at a sound masking location is determined, and the masking result is displayed to a user, so that user confidence in using the sound masking system can be improved. The reminding method further provides a plurality of modes for receiving user instructions and a plurality of modes for presenting reminder information to the user, so that various possible situations can be promptly and effectively fed back to the user, thereby improving user confidence in using the sound masking system, and further improving the usability of the sound masking system.

The present application relates to the technical field of sound processing, and provides a sound signal separation method and device, electronic equipment and a storage medium, wherein the method comprises the following steps: determining the short-time energy of ambient sound based on the short-time energy of each channel signal and the cross-correlation coefficient between the channel signals, wherein the ambient sound of each channel has the same short-time energy; determining the ambient sound mask of each channel based on the short-time energy of the ambient sound and the short-time energy of each channel signal; and determining the ambient sound and coherent sound of each channel based on the ambient sound mask of each channel and the channel signals. The ambient sound and coherent sound can be effectively separated by using the ambient sound mask of each channel, the separation effect is improved, and the method can be applied to various stereo sound scenes.

The invention, which relates to the technical field of the sound masking system, discloses a sound masking conference system comprising a microphone, an acoustic acquisition processor, a sound box, an active noise reduction earphone and an anti-recording audio processor. According to the invention, the microphone acquires the original voice of the conference personnel, the original voice is processed by the acoustic acquisition processor to generate the original sound and the interference sound, the original sound is played to each conference personnel through the earphone, the interference sound is played in the whole conference room through the sound box, and the conference personnel can clearly hear the sound of the conference personnel through the earphone. The sound recording device receives superposition of original sound and interference sound of conference personnel, the purpose that the original sound cannot be restored is achieved, the acoustic acquisition processor can generate the interference sound with the same voiceprint as the speaker, and after the interference noise and the original sound are recorded by the sound recorder, human ears and a computer cannot be separated completely and cannot be understood completely. Therefore, the sound masking effect is achieved.

The embodiment of the invention provides a method executed by electronic equipment, the electronic equipment and a storage medium, and relates to the field of artificial intelligence. The method comprises the following steps: obtaining a target sound mask of a target at each moment based on image-related information of the target in a first video, a first audio signal corresponding to the first video and direction information of the first audio signal; and based on the target sound mask of the target at each moment and the first audio signal, a second audio signal is obtained, and the second audio signal does not include sound related to the target. Optionally, the method performed by the electronic device may be performed using an artificial intelligence model.

The invention relates to the technical field of sound processing, and provides a sound signal separation method and device, electronic equipment and a storage medium, and the method comprises the steps: determining the short-time energy of environment sound based on the short-time energy of each channel signal and the cross correlation coefficient between the channel signals, and enabling the environment sound of each channel to have the same short-time energy; determining an environmental sound mask of each channel based on the short-time energy of the environmental sound and the short-time energy of each channel signal; and determining the environment sound and the coherent sound of each channel based on the environment sound mask of each channel and the signal of each channel. According to the invention, the environment sound and the coherent sound can be effectively separated by using the environment sound mask of each channel, the separation effect is improved, and the method can be suitable for various stereo scenes.

The invention discloses an audio playback method and device and a computer readable storage medium, the audio playback method is applied to an audio playback system, and the audio playback system comprises an intelligent musical instrument and an open earphone; the method comprises an intelligent musical instrument and an open earphone. The audio playback method comprises the following steps: the intelligent musical instrument generates an audio signal according to a pressure signal, and sends the audio signal to the open earphone; the open earphone plays the audio signal, and analyzes the main frequency band of sound leakage of the open earphone; and the intelligent musical instrument outputs a sound masking signal strongly related to the audio signal according to the sound leakage main frequency band. The intelligent musical instrument and the open type earphone work cooperatively, the loudspeaker of the intelligent musical instrument compensates for the deficiency of the earphone in the aspect of low frequency, and the open type earphone compensates for the problem of insufficient details of high-frequency playback of the intelligent musical instrument, thereby effectively making up the advantages and disadvantages of the two products, and ensuring high-fidelity output and spatial perception of audio.

To provide a speaker device which can provide a comfortable online meeting.SOLUTION: A speaker device (1) includes: an online meeting speaker (11) for outputting voice of an online meeting; a first sound reflection member (12) arranged above the online meeting speaker, the first sound reflection member having a first reflection surface (121) for reflecting sound output from the online meeting speaker downward; and a speaker (13) for sound masking provided above the first sound reflection member.SELECTED DRAWING: Figure 1

1. The name of the product of this design: Airborne sound masking system control host. 2. The purpose of this design product: to take masking and protection measures for the sounds in important confidential areas (important offices, conference rooms, etc.) to prevent eavesdroppers from stealing sound information. 3. The design key point of this appearance design product lies in the shape. 4. The picture or photo that best illustrates the key points of the design: main view.

An embodiment of the present application provides a sound masking method, system, device, storage medium and program product. The method includes performing rearrangement processing on the external environmental sound in the sound masking space where the target object is located to obtain a rearranged masking speech signal, and the difference between the rearranged masking speech signal and the spectral characteristics of the external environmental sound is less than or equal to a preset threshold. Based on the rearranged masking speech signal, sound masking processing is performed on the target object. The method is used to achieve the effect of improving information security protection.

The invention discloses a personalized snore masking audio synthesis system and method, and belongs to the technical field of audio signal processing, and the system comprises a snore feature extraction module, a psychoacoustic analysis module, an audio generation module and a dynamic adjustment module. The system recognizes snore segments in environment audio and extracts spectrum features, critical frequency band distribution is analyzed based on a psychoacoustic model, a masking energy threshold value is calculated, personalized masking audio is synthesized in real time through a generative adversarial network in combination with user preference information, snore changes are dynamically monitored, and generation parameters are adjusted in real time. According to the method, the best masking effect is achieved with the minimum volume, the volume requirement is reduced by 35% under the same subjective effect, the user satisfaction degree is improved by 62%, the snore interference problem is effectively solved, and the user experience is improved.

The application discloses a reminding method, system and device, vehicle, computer readable storage medium and computer program product, and relates to the field of intelligent vehicles. The reminding method can improve the confidence of a user in using a sound masking system by determining a masking result of the sound masking system on target sound at a sound masking position and displaying the masking result to the user. The reminding method also provides multiple ways of receiving user instructions and multiple ways of prompting the user with reminder information, can timely and effectively feed back various possible situations to the user, thereby improving the confidence of the user in using the sound masking system, and further improving the practicability of the sound masking system.