147 results about "Acoustic frequency" patented technology

The invention discloses a fan blade diagnosis method and system based on voiceprint perception, and relates to the technical field of intelligent monitoring of wind power equipment, and the method comprises the steps: carrying out frequency domain compensation processing, stripping environment wind noise components, and generating a pure voiceprint signal based on a wind flow characteristic parameter set; based on the pure voiceprint signal, identifying a sensitive acoustic frequency band of the fan blade, exciting a sound wave phase synergistic effect in the sensitive acoustic frequency band, and generating an enhanced voiceprint signal; quantifying the internal damage depth of the fan blade material according to the enhanced voiceprint signal, and calculating a sound energy flow disorder degree index; according to the sound energy flow disorder degree index, the blade health state of the fan is judged through a multi-dimensional acoustic characteristic state space mapping mechanism, and a three-dimensional health assessment report is generated; through a physical level wind noise stripping technology, a transfer function matrix is generated based on vortex interference modeling and sound wave-airflow phase offset correction, frequency domain energy reweighted decoupling is realized, and environmental wind noise is accurately stripped in a strong turbulence environment.

The invention provides an abnormal blood sampling inspection data evaluation processing method and system of a blood sampling system. Wherein the diffusion track dynamic state of an anticoagulant-blood contact surface in a blood sampling tube is tracked in real time, dielectric response waveform distortion characteristics on the two sides are synchronously collected through a capacitance sensor array, and diffusion form parameters are generated; curvature sudden change is analyzed to trigger an acoustic fluid device to modulate audio frequency and flow velocity, and a composite disturbance field is formed; performing capacitance axial scanning on the disturbed mixed fluid, extracting phase angle offset and gradient abrupt change point coordinates, and constructing a dielectric anomaly three-dimensional map; matching a standard dielectric model, positioning a coordinate set of a concentration gradient imbalance area and a coordinate set of an eddy current attenuation area, and generating an anticoagulant abnormal index and a mixed defect matrix in combination with phase angle offset difference; and establishing a data anomaly degree evaluation function based on the anomaly index and the defect matrix, dynamically associating a clinical error threshold, and outputting a test evaluation result. According to the invention, anticoagulant diffusion can be monitored in real time, and the mixing quality error can be accurately evaluated.

The invention discloses a high-performance CPU-GPU (Central Processing Unit-Graphics Processing Unit) cooperative processing architecture of an audio frequency integrated signal processor, belonging to the technical field of audio frequency integrated signal processing, the architecture is based on a dynamic priority scheduling model and realizes efficient collaboration of a CPU and a GPU through hierarchical resource management and protocol level optimization, a hardware layer adopts a multi-GPU cluster and a distributed storage node, and the CPU-GPU cooperative processing architecture has the advantages that the multi-GPU cluster and the distributed storage node are integrated; high-concurrency task processing is supported; the transmission layer fuses RapidIO and an Ethernet protocol, and adapts to a short frame control signal and a long packet data stream respectively; and the application layer calculates task resource demands through dynamic priority weights, and ensures low time delay of key tasks in combination with a normalized allocation algorithm. According to the architecture, in an audio signal processing scene, the task scheduling efficiency is improved by 40%, the short frame transmission delay is as low as 0.5, the throughput of a long data stream reaches 100 Gbps, and the requirements for real-time performance and calculation precision in a complex acoustic environment can be met.

The invention provides a factory boundary noise online monitoring traceability system and method, and belongs to the technical field of noise monitoring. The system comprises a data acquisition module; the data processing module is used for judging whether factory boundary noise processing is carried out or not; when the boundary noise processing is determined to be carried out, determining a direction corresponding to the directional microphone with the maximum sound level as a noise source direction; based on the noise source direction, a data acquisition instruction is generated and sent to the data acquisition module, and audio frequency information and video information, collected in real time and fed back by the data acquisition module, in the noise source direction are recycled; and taking the audio frequency information and the video information in the noise source direction as input parameters, and based on a pre-established abnormal sound source positioning model and a pre-established sound feature recognition model, obtaining a noise source visual sound field cloud picture and a noise classification recognition result. The purposes of noise comprehensive response, noise orientation definition and noise accurate traceability are achieved, evidence is provided for factory boundary noise source definition, and disputes are effectively avoided.

The invention relates to the technical field of oil-water detection equipment, and discloses an oil-water detector and method based on a liquid mass resonance measurement principle. The oil-water detector based on the liquid mass resonance measurement principle comprises a parameter sensing unit which is used for contacting an oil-water mixed medium in a pipeline and comprises a current carrying body with a measurement cavity, a measurement probe arranged in the measurement cavity and a resonance body arranged in the measurement probe; and the data processing unit is in signal connection with the parameter sensing unit and comprises a signal transmitting module which is used for transmitting an audio frequency sweep frequency signal to the resonant body to excite liquid column resonance and transmitting electromagnetic short waves with a preset frequency to an oil-water mixed medium at the same time. According to the invention, direct measurement of the density and the dielectric constant is fused, the phase state is identified by using an intelligent algorithm, and the model is switched, so that the problem of failure of a single principle technology in a specific phase state is solved, and high-precision measurement in a water-in-oil state or an oil-in-water state in a full range from pure water to pure oil is realized.

A method for detecting interference between a transducer of acoustic signals and a sensor having a mechanical resonance frequency with a frequency band that includes transmitting an acoustic signal within a known range of frequencies, in a sequence during a predetermined time window, monitoring the output signal from the sensor within said time window, comparing the transmitted signal with the sensor output signal and detecting deviations in the sensor output signal corresponding to frequencies in the acoustic signal, and determining the acoustic frequencies interfering with the sensor signal. A system for detecting interference including a transducer, configured to emit a sequence of acoustic signals, and a sensor configured to produce an output signal, an analysis unit adapted to monitor said output signal with the acoustic signal.

The embodiment of the invention discloses a ring main unit aging state monitoring method and device, electronic equipment and a readable medium. A specific embodiment of the method comprises the following steps: acquiring an in-cabinet gas concentration information sequence, an in-cabinet audio signal, an in-cabinet mechanical signal and temperature and humidity information; performing gas feature extraction on the in-cabinet gas concentration information sequence to generate gas feature information; carrying out audio frequency feature extraction on the in-cabinet audio frequency signal to generate audio frequency feature information; performing mechanical characteristic extraction processing on the in-cabinet mechanical signal to generate mechanical characteristic information; performing multi-modal feature fusion on the gas feature information, the audio frequency feature information and the mechanical feature information to generate joint feature information; generating a prediction result of the health degree and the aged mechanical part of the ring main unit; and updating the monitoring period condition, and carrying out monitoring and early warning. According to the embodiment, the detection rate of the aging state of the ring main unit can be improved, so that the safety of power distribution equipment is improved.

The invention relates to the technical field of pipeline safety monitoring, in particular to an intelligent pipeline leakage monitoring system and method based on audio frequency, and the system comprises an audio frequency signal collection module, a noise filtering and feature extraction module, a leakage recognition and positioning module, and a state evaluation and alarm module. Wherein the audio signal acquisition module is used for acquiring pipeline audio signals and outputting original audio signal data; the noise filtering and feature extraction module is used for carrying out filtering processing to suppress environmental noise and extracting feature vectors related to leakage; the leakage identifying and positioning module is used for identifying whether a leakage event exists or not and calculating the position of a leakage point relative to an adjacent sensor; and the state evaluation and alarm module is used for generating a leakage state evaluation result. According to the invention, by constructing a closed-loop monitoring process from audio frequency acquisition to alarm output, accurate identification, spatial positioning and graded evaluation of a pipeline leakage event are realized, and the response efficiency and practicability of the monitoring system are significantly improved.

The invention discloses a health management method for a GPU computing board card of an audio-frequency integrated signal processor, and belongs to the technical field of audio-frequency integrated signal processing. Multi-dimensional data of a GPU core, a video memory and a power supply module are collected in real time through a sensor, a three-dimensional temperature field is constructed by adopting an inverse distance weighted interpolation algorithm, and a thermal coupling area is accurately positioned; thermal field evolution is predicted based on an LSTM model, and a high-density instruction is dynamically scheduled to an NUMA core with sufficient heat dissipation allowance; aiming at sudden reading and writing of a video memory, a micro piezoelectric fan array is adopted to form vertical airflow (the wind speed is greater than or equal to 4m / s), and dynamic voltage reduction and graded heat dissipation strategies (phase change heat-conducting fins are pre-cooled to reduce the temperature by 8-10 DEG C, and the attack angle of centrifugal fan blades is 45 degrees) are combined. According to the scheme, the heat source recognition precision is improved by 40%, the heat dissipation delay is smaller than or equal to 45 microseconds, the calculation power loss is smaller than or equal to 0.8%, the video memory error rate is smaller than or equal to 1E-6, and high-density calculation heat management is remarkably optimized.

The invention provides an acoustic modal test method and device, electronic equipment and a storage medium, and the method comprises the steps: controlling at least one sound source device to output a preset audio signal at the same time; acquiring response signals detected by the plurality of sensors; the plurality of sensors are used for respectively executing sound detection at a plurality of detection positions in a compartment area; establishing a geometric model based on the audio signal, the detection position and a response signal detected by the sensor; and analyzing the geometric model to obtain an acoustic modal test result. According to the embodiment of the invention, the acoustic modal test result measured by the method is beneficial to improving the riding experience of passengers.

The invention provides an online comprehensive detection, analysis and evaluation method and system for a power equipment bearing, and the method comprises the steps: obtaining four-dimensional operation parameters of the bearing in real time, including a temperature and vibration value, an audio frequency spectrum feature, a dynamic maintenance period parameter and a bearing load rate parameter; establishing a correlation model of specific frequency band energy change and vibration value fluctuation in the audio frequency spectrum characteristics through space-time correlation analysis, injecting a dynamic maintenance period parameter as a time domain attenuation factor into the correlation model, and dynamically weighting based on a bearing load rate parameter to generate a health degradation index; when the health degradation index exceeds a dynamic threshold value, generating a pre-maintenance instruction, and outputting a maintenance strategy containing a fault positioning map; a pre-maintenance instruction and a maintenance strategy are packaged according to an industrial communication protocol, and a correlation analysis view and an early warning window are dynamically embedded in a distributed control system interface, so that the accuracy of bearing online monitoring is effectively improved.

An ultrasonic dust removal device, comprising: positive pressure cavities (10) and air blowing cavities (20) which are sequentially arranged in a first direction, wherein each air blowing cavity (20) comprises a communicating flow channel and at least two ultrasonic generating cavities (21) connected in series by means of the communicating flow channel, the air blowing cavity (20) is communicated with the corresponding positive pressure cavity (10) by means of the communicating flow channel, the portion of the communicating flow channel distant from the positive pressure cavity (10) forms an air blowing flow channel (22) capable of blowing air to the outside, and the ultrasonic generating cavities (21) expand outward with respect to the communicating flow channel in a second direction; and a negative pressure cavity (30) and an air suction hole (40) which are communicated with each other, wherein the air suction hole (40) and the air blowing flow channels (22) are located at the same end of the ultrasonic dust removal device in the first direction; the cavity wall of at least one ultrasonic generating cavity (21) comprised in each air blowing cavity (20) is recessed inward to form at least one first groove (50), and the positive pressure cavities (10), the air blowing cavities (20) and the first grooves (50) all extend in a third direction; and a first cross section of each first groove (50) is arc-shaped. The arc-shaped grooves in the ultrasonic generating cavities (21) are conducive to the movement of sound waves, reducing the sound wave energy loss caused by agitation, improving sound frequency effect, and thus saving gas flow.

The invention provides a special gas box for a multifunctional audio-frequency environment-friendly drilling machine, which comprises a gas outlet end assembly and a gas inlet end assembly, the gas outlet end assembly comprises a gas outlet end mandrel and a gas outlet end mandrel jacket, the gas outlet end mandrel is provided with a through upper central gas passage, and the gas outlet end mandrel jacket is provided with a gas outlet communicated with the upper central gas passage; the air inlet end assembly comprises an air inlet end mandrel and an air inlet end mandrel outer sleeve, a double-wall inner pipe is arranged in the center of the air inlet end mandrel, and the double-wall inner pipe is provided with a lower center air channel and an annular air channel. The air inlet end mandrel outer sleeve is provided with an air inlet communicated with the annular air channel. The top of the air inlet end mandrel is connected with the bottom of the air outlet end mandrel; the air outlet end mandrel outer sleeve and the air inlet end mandrel outer sleeve are connected through a connecting piece. After the air box is installed on the multifunctional audio frequency environment-friendly drilling machine, the reverse circulation down-the-hole hammer can be used on the multifunctional audio frequency environment-friendly drilling machine.

In order to adapt the frequency response of headphones, various filters are used, including shelving or frequency-shelving filters. However, these are usually implemented electronically. In the case of wired headphones without their own voltage supply, however, no electronic signal processing is possible. In order to realise an acoustic shelving filter, an acoustic damping element (DD) having a flat, acoustically effective damping material, which has a defined specific acoustic resistance, is placed in front of the radiating surface of the sound transducer at a small distance (d) in relation to the diameter of the acoustic damping element. It thus forms a flat air gap (AG), which is open at the edge, with respect to the radiating surface of the transducer. Acoustic properties of the shelving filter can be controlled by the size and material of the damping element (DD) and its distance from the sound panel (SW) or from the transducer (W).

The invention provides a sound wave optical cable positioning method and system, and relates to the technical field of deep learning, and the method comprises the steps: uniformly arranging vibration sensors on a sensing optical cable, demodulating a back scattering light signal to obtain a differential phase signal, and constructing a self-correlation loss function. Preprocessing sound source data, extracting an audio frequency semantic feature vector, and calculating a dot product of a frequency spectrum centroid and frequency spectrum flatness to obtain a frequency spectrum loss function; and a phase change loss function is obtained by combining the ratio and the refractive index of the strained optical fiber and the non-strained optical fiber. And weighting the three loss functions to form a fusion loss function. And constructing a sound wave positioning model, and training the model to be optimal based on the fusion loss function. And finally, segmenting and enhancing audio data, and inputting the audio data into the trained model to obtain a positioning result. According to the method, the positioning model is trained by fusing multiple different types of loss functions, so that the positioning precision of sound waves in the optical cable is improved.

The present invention relates to the technical field of pest control, and specifically discloses a vibration interference device for piercing-sucking pests and an ultrasonic audio directional system thereof, comprising an upper fixed plate and a lower fixed plate in an arc-shaped structure, between which a vibration interferer is fixedly installed. The vibration interference device for piercing-sucking pests and the ultrasonic audio directional system thereof modulate a low-frequency interference signal with an ultrasonic carrier signal based on the spectral characteristics of the interference signal of the target pest, and emits a modulated ultrasonic signal through a transducer (i.e., a directional player) inside the vibration interferer. The ultrasonic wave self-demodulates a highly directional interference signal in the air, and accurately transmits the interference signal to the edge of the field or an irregular blind spot, thereby preventing the interference signal of the omnidirectional player inside the field from being attenuated to ineffectiveness when reaching the edge of the field or in the blind spot. The use of two players in combination does not require a significant increase in the power of the internal omnidirectional player, thus avoiding noise pollution.

The application provides a ball and socket type rope coring drill tool suitable for an audio frequency drilling machine, which comprises an outer pipe assembly for downward drilling and an inner pipe assembly for sampling, the inner pipe is arranged in the hollow inner cavity of the outer pipe, and the top of the inner pipe is provided with a ball and socket mechanism and a fishing spear, the ball and socket mechanism is used for realizing the clamping or separation between the inner pipe assembly and the outer pipe assembly when the inner pipe assembly is moved into position relative to the outer pipe assembly. The whole drill tool has simple structure, high outer pipe thread strength, can achieve waterless drilling, the ball and socket mechanism has accurate positioning, reliable locking and easy unlocking, and the drill tool can improve the comprehensive drilling efficiency and greatly reduce the labor intensity.

There is disclosed a thermoacoustic system. The system comprises a thermocouple junction and an electronic signal generator for generating an acoustic frequency driving signal across the junction, which causes the system to generate an acoustic wave via the Peltier effect.

The invention relates to an ear sound production instrument, a detection method, a medium and computer equipment, and the instrument comprises an ear canal detection probe which is suitable for being inserted into an ear canal of a tested object and forms sealing fit with the wall of the ear canal, and the ear canal detection probe comprises an acoustic output unit which transmits an audio signal to the ear canal, the acoustic input unit is used for receiving a reflected wave of the audio signal in an ear canal; the sound insulation cover is arranged outside the auditory meatus detection probe in a sleeving mode and covers the auditory meatus detection probe and an auditory meatus opening so as to weaken noise and improve the signal-to-noise ratio of reflected waves, otoacoustic emission detection can be carried out without depending on a special sound insulation room environment, and the accuracy and clinical applicability of a detection result are guaranteed.

A sound reproduction apparatus comprising a plurality of spaced-apart sound sources, and the sound sources providing multiple arrays comprising a first array arranged to emit at least a first acoustic frequency range and a second array arranged to emit at least a second acoustic frequency range; and wherein the first array is arranged to emit a sound frequency range which is higher than the frequency range emitted by the second array, and further wherein a lateral extent of the first array is less than a lateral extent of the second array, and yet further wherein the lateral extent of each of the multiple arrays decreases as the frequency band output by an array increases.

The invention discloses a piano tuning auxiliary positioning system, belongs to the technical field of musical instrument tuning, and aims to solve the problem of positioning deviation caused by neglecting string tension dynamic evolution and environmental disturbance in the prior art. The system comprises a tuning peg state sensing module, a string tension evolution monitoring module, a central cooperative controller, a man-machine interaction guide module and an audio feedback verification module. Through fusion of triple information of tuning peg angular displacement, tension steady state discrimination and acoustic frequency feedback, staged accurate guidance and dynamic decision are realized. The system rapidly approaches the target in the coarse tuning stage, premature termination is avoided in the fine tuning stage according to the tension steady state, the tuning accuracy is ensured through audio closed-loop verification, and the tuning precision, efficiency and robustness are remarkably improved.

The invention discloses a two-dimensional acoustic crystal based on a microstructure. A functional material layer of the two-dimensional acoustic crystal comprises square acoustic cells which are periodically arranged in an xy plane according to a square lattice; a scatterer in the acoustic cell has rotational symmetry and is composed of a cross structure and four identical semicircles, the cross structure is composed of two identical rectangular strips in an orthogonal mode, the diameter of the semicircle is collinear with the short edge of the rectangular strip at the tail end where the semicircle is located, and the diameter of the semicircle is larger than the length of the short edge of the rectangular strip. The rotation angle of the scatterer is matched with the geometric parameter of the scatterer, so that the physical energy band structure of the two-dimensional acoustic crystal generates a triple degeneracy point formed by the first three physical energy bands at the M point of the Brillouin region, and further a stable boundary state with global characteristics is realized. Furthermore, an acoustic frequency beam splitter is constructed on the basis of the boundary state, and sound waves of different frequency bands are split to form included angles of 180 degrees and 90 degrees.

A combustor for a turbine engine includes a wall defining a combustion chamber, and an acoustic damper. The acoustic damper includes a housing in fluid communication with the combustion chamber through an opening provided in the wall, the housing defining a cavity and having one or more neck holes in fluid communication with the combustion chamber, and a mechanism configured to vary a damping acoustic frequency of the acoustic damper so as to vary the damping acoustic frequency of the acoustic damper to align with an acoustic frequency of acoustic vibrations generated in the combustion chamber to attenuate an acoustic instability within the combustion chamber.

The application provides a simulation sound production method and a simulation sound production device.The simulation sound production method comprises the following steps: providing a sound production driving signal, wherein the sound production driving signal is a high-frequency carrier signal; obtaining a target audio signal, and generating a microswitch driving signal based on the positive and negative of the target audio signal at different time points; controlling the microswitch to be turned on at different time points through the microswitch driving signal, outputting the positive pulse or the negative pulse of the corresponding period of the sound production driving signal, and realizing the demodulation of the target audio signal.Through the simulation sound production method and the simulation sound production device, the problem that the audio frequency band cannot be fully covered and the sound volume is low in the existing simulation micro loudspeaker is solved, and the effect of full-band high-fidelity and high-sound-pressure sound production is realized.

The utility model discloses microphone equipment with a double-sound-cavity structure. The microphone equipment comprises a microphone assembly, a microphone main body and a handle assembly which are installed in sequence, the microphone main body comprises a microphone mounting part, a main body shell and a power supply mounting part, the main body shell comprises a first shell and a second shell which are mutually covered, the middle part of the first shell is provided with a control assembly, the middle part of the second shell is provided with an alto loudspeaker, and the left side and the right side of the alto loudspeaker are respectively provided with a loudspeaker assembly; a plastic spacer is arranged in the second shell, so that an alto sound cavity is formed among the alto loudspeaker, the main body shell and the plastic spacer, and a main body sound cavity is formed between the main body shell and the plastic spacer; one end of the sound cavity air channel is communicated with the outside, and the other end of the sound cavity air channel is communicated with the alto sound cavity. According to the utility model, the main body housing is divided into the alto sound cavity and the main body sound cavity through the plastic spacer, so that different audio frequencies of human voices are respectively output, and the immediacy of central channels of left and right sound fields is improved.

The invention provides a composite layer structure for supporting micro-acoustic frequency tuning and a resonator. The composite layer structure comprises a piezoelectric layer, a semiconductor layer and an insulating substrate, the piezoelectric layer and the semiconductor layer are stacked to form a piezoelectric semiconductor composite structure; the piezoelectric semiconductor composite structure is arranged on the insulating substrate to form a composite layer structure capable of adjusting the frequency of the resonator; the composite layer structure is further provided with an interdigital transducer and an electrode, a frequency-adjustable surface acoustic wave resonator can be formed, direct-current unbalance loading voltage or current is applied to the semiconductor layer through the electrode, a micro-acoustic electric field and a carrier generate a giant acoustoelectric effect, remarkable change of the micro-acoustic wave velocity is caused, and the acoustic wave velocity is changed. The resonant frequency of the resonator is changed in a wide frequency range. Based on a composite layer structure formed by piezoelectricity, a semiconductor and an insulating substrate, the composite layer structure is applied to the resonator, resonant frequency tuning within the range of 5% or above can be achieved through volt-level voltage, and meanwhile the gain characteristic of the acoustoelectric effect can compensate the Q value of the resonator.

The present application relates to the technical field of flexible wearable diagnosis and treatment equipment, and discloses a pasting type human body audio acquisition device and a human body audio acquisition and analysis system. The device comprises: a flexible encapsulated contact type vibration sensor, which is used for acquiring human body audio signals; a flexible circuit connected with the contact type vibration sensor; the flexible circuit comprises a noise reduction module and a wireless transmission module, wherein the noise reduction module is used for performing preliminary noise reduction processing on the human body audio signals acquired by the contact type vibration sensor and converting the signals into digital signals; and the wireless transmission module is used for transmitting the digital signals to a processing module or a server. The device can be attached to uneven skin surfaces to be measured, can continuously acquire sound data of a user for a long time, and can realize high-quality sound signal extraction, noise reduction processing and data uploading through an intelligent analysis system.

A combustor for a turbine engine includes a wall defining a combustion chamber and an acoustic damper. An acoustic damper includes a housing in fluid communication with a combustion chamber through an opening provided in a wall, the housing defining a cavity and having one or more neck apertures in fluid communication with the combustion chamber; and a mechanism configured to vary a damping acoustic frequency of the acoustic damper, thereby varying the damping acoustic frequency of the acoustic damper to align with an acoustic frequency of acoustic vibrations generated in the combustion chamber to attenuate acoustic instability within the combustion chamber.

This application discloses a method and system for dynamic mapping of partial discharge audio signals based on multimodal intelligent sensing, relating to the field of signal processing. The method includes: acquiring ambient audio signals and partial discharge signals; performing frequency domain conversion on the ambient audio signals to obtain a frequency domain energy distribution; calculating the masking sound pressure level based on the frequency domain energy distribution and constructing a global masking threshold curve; traversing the global masking threshold curve to extract the center frequency of the frequency band, and determining the center frequency of the frequency band with the lowest value as the dynamic carrier frequency; extracting the discharge pulse amplitude and pulse rise time characteristics from the partial discharge signal; mapping the inverse ratio of the pulse rise time characteristics to the modulation frequency, and mapping the direct ratio of the discharge pulse amplitude to the frequency modulation index; generating a synthesized audio stream; and outputting the synthesized audio stream to external headphones. This application can effectively sense and identify the converted partial discharge audio signal in complex noise backgrounds.

There is provided a respiratory support device for providing pressurized air to a subject. The respiratory support device comprises a conduit, an acoustic generator, and an acoustic sensor. The conduit is for conveying an airflow. The conduit has an opening. The acoustic generator is adapted to generate an acoustic signal in the conduit at an acoustic frequency. The acoustic sensor is arranged outside the conduit. The acoustic sensor is adapted to generate a sensor signal representative of the acoustic signal. The respiratory support device comprises a membrane arranged to cover the opening to separate the acoustic sensor and the airflow from each other. The membrane is adapted to resonate at the acoustic frequency.