103 results about "Acoustic processing" patented technology

The invention provides a low-delay streaming voice interaction system with an interruption processing function, and relates to the technical field of artificial intelligence. Necessary preprocessing and acoustic feature extraction are performed through a real-time acoustic processing module, and distortion and complex environmental noise introduced by an interaction channel are resisted through a robustness enhancement technology; the streaming acoustic decoding module performs acoustic modeling, language model application and decoding in real time in parallel, and outputs an ultra-low-delay text transfer result stream; the real-time acoustic processing module is combined with a signal processing technology and is responsible for detecting user voice activity in a high-precision and ultra-low-delay manner, and particularly judging the real-time voice activity state of a user through the user voice activity in an AI voice playing period; an efficient and low-delay bidirectional streaming network transmission mode is adopted between modules of the system and between the modules and a communication platform, and it is ensured that audio streams, acoustic feature streams, text streams and control signals can be transmitted and processed in real time with extremely low end-to-end delay.

The invention discloses an open architecture system for an underwater acoustic signal processor, and belongs to the technical field of underwater acoustic signal processors. The system comprises a hardware resource pool, a standardized algorithm container group, a visual processing link construction module, a containerized deployment and scheduling platform and a data processing and communication plane. According to the system, special hardware resources are pooled, an underwater sound processing algorithm is packaged into a standardized container, a user is allowed to arrange a processing flow in a graphical mode, an intelligent scheduling platform dynamically deploys the algorithm container to matched hardware for execution according to real-time resource conditions, and meanwhile, an efficient and reliable data communication channel is provided. According to the method, the problems that a traditional system is closed, poor in expansibility and low in resource utilization rate are solved, elastic sharing of hardware resources, agile deployment of an algorithm and flexible construction of a flow are achieved, and openness, flexibility and overall efficiency of an underwater acoustic signal processing system are remarkably improved.

The invention provides an impedance combined type broadband silencer based on a sound wave black hole gradient structure and a design method, and belongs to the technical field of noise control and environmental protection engineering, the whole impedance combined type broadband silencer is of an axisymmetric cylindrical structure, and the impedance combined type broadband silencer is composed of an inlet and outlet channel and a middle-section expanding type acoustic processing area; the expanded acoustic processing area comprises an inlet and outlet side expansion cavity, a composite impedance gradient perforation section and a porous sound absorption material layer. According to the sound wave black hole type multi-stage perforated ring structure, the sound wave black hole type multi-stage perforated ring structure composed of an axial uniform-parameter perforated ring belt and a radial gradient perforated ring belt is sequentially constructed in the silencer, so that the thickness of a perforated ring and the aperture and the perforation rate of the perforated ring belt are arranged on a propagation path according to a parameter gradient rule; porous materials are filled among the annular bands to form a gradient impedance composite dissipation system, so that sound waves are sequentially subjected to focusing and dissipation caused by geometric gradual shrinkage and viscosity and heat dissipation of porous media in the propagation process, and low-frequency enhanced absorption and wide-frequency-band continuous sound absorption are achieved.

Provided is an acoustic processing apparatus in which a microelectromechanical systems (MEMS) device is effectively arranged. The acoustic processing apparatus includes an enclosure, a sound duct extending from the enclosure, and a MEMS device housed in the sound duct.

The present disclosure provides a speech processing method, apparatus, device and storage medium, which relate to the field of artificial intelligence, and in particular to the field of speech technology. The specific implementation scheme is: based on the parameter characteristics of the streaming acoustic processing module in the acoustic model, an acoustic processing filling block is obtained; the acoustic processing filling block is added to the i-th data block to be acoustically processed to obtain the i-th target acoustic processing data block; wherein the i-th data block to be acoustically processed is obtained by slicing the data to be processed into n data blocks to be acoustically processed; the i is a natural number not greater than n, and the n is a natural number not less than 2; the i-th target acoustic processing data block is input into the streaming acoustic processing module in the acoustic model for streaming acoustic processing to obtain the i-th streaming acoustic processing result.

The invention discloses an acoustic processing method for directionally generating, grouping and managing sound frequency bands and eliminating and counteracting the sound frequency bands, which comprises the following steps of: S1, carrying out AD (Analog to Digital) sampling on analog sound signals to be processed to obtain digital sound signals to be processed; s2, performing dynamic frequency band division on the to-be-processed digital sound signal to obtain a plurality of frequency band signals; s3, mapping the plurality of frequency band signals into a plurality of sound source groups; s4, each sound source group generates a directive sound signal pointing to the target area by using the sound radiation unit of the sound source group, and after the directive sound signal is synchronously transmitted to the target area, an actual mixed sound signal is formed; and S5, detecting, eliminating and counteracting a sound wave counteracting effect generated by the actual mixed sound signal in the target area. According to the method, high-quality accurate directional propagation can be realized, and the adaptability to a complex environment is enhanced.

The invention provides a low-noise mounting device and a noise reduction structure design method thereof, and relates to the technical field of aviation noise control. The design method of the noise reduction structure of the low-noise installation device comprises the steps of obtaining unsteady pressure pulsation data of the surface of a calculation model; wherein the calculation model has main body structure characteristics of the low-noise mounting device; obtaining the maximum position of the unsteady pressure pulsation amplitude on the surface of the calculation model according to the unsteady pressure pulsation data, and dividing a plurality of acoustic processing areas by taking the maximum position as the center in an outward expansion manner; calculating each acoustic processing area to obtain a corresponding target frequency; the acoustic impedance matching structure is selected according to the target frequency, so that acoustic structures with specific frequency characteristics can be designed for different acoustic processing areas, accurate control over multi-band noise by the mounting device is achieved, and the effect noise of machine body mounting is facilitated. Especially, the ideal noise reduction effect is achieved on the installation effect noise of the open type rotor engine.

Furniture such as desks and other items are provided with sound absorbing features consisting of micro-perforations extending through structures having vertical surfaces. The micro-perforations are formed using a LASER cutting tool or a punch and are either cylindrical or frustoconical. The micro-perforations are formed in drawer facings, doors, support structures, and free-standing objects and storage devices having vertical surfaces. The micro-perforations have diameters in the range of 0.20 to 0.70 mm. The micro-perforations have been found to increase sound absorption of a desk by as much as 4 Sabins within the frequency range of 100 to 5,000 Hz. Structural panels consisting of front and rear micro-perforated panels surrounding a porous central core may be employed in such furniture.

The invention discloses a tomography and targeted energy thermal therapy system and method based on an acousto-optic coupling functional film layer, and relates to the technical field of noninvasive medical diagnosis and treatment. The system comprises an intelligent processing carrier, an acousto-optic coupling function film layer, a scanning mechanism, an energy treatment module and a processing and temperature control module. The intelligent processing carrier at least comprises a 20Hz-20kHz audio unit, a pickup unit, an optical signal unit and a processor; the acousto-optic coupling functional film layer is of a single physical structure and is inseparable, acoustic frequency conversion focusing imaging and targeted warm delivery at 42-47 DEG C are achieved in the same physical area in a time-sharing mode, the acoustic processing layer achieves 1000-8000 frequency doubling through a multi-stage resonance microcavity array, and the echo signal-to-noise ratio is larger than or equal to 15 dB; the scanning mechanism comprises a plurality of modes such as rotation, translation, multi-device array, human body movement, local limb movement, human body bearing support device movement and the like; the energy forms cover all types of light, electromagnetism, radio frequency and the like capable of generating a warm effect, including but not limited to non-contact or contact energy delivery modes. The traditional Chinese medicine composition is suitable for tumors, infections, inflammations, and all lesions sensitive to temperature of 42-47 DEG C including nervous system lesions such as amyotrophic lateral sclerosis, Alzheimer's disease, Parkinson's disease, multiple sclerosis and the like, is low in cost, free of radiation and easy to popularize, and has extremely high creativity and practical value.

An acoustic aural development system. A medical device is worn by an infant while the infant is in a neonatal intensive care unit (NICU) and is in communication with an acoustic processing station. The device and station protect the child's hearing by active acoustic filtering, while, at the same time, provides aural stimulation for development. Acoustic filtering is done at the acoustic processing station to reduce power and electronics required by the wearable medical device.

A method for optimizing acoustic performance in listening spaces addresses limitations in room acoustics for music production and reproduction. The method comprises two optimization steps: a multi-objective room optimization method applicable to any room shape and a multi-objective treatment optimization method that iteratively searches a library of potential acoustical treatments to determine optimal solutions for each accessible area. The method utilizes a multi-objective search engine to simultaneously optimize several critical acoustic metrics, including low-frequency response, spatial variation around listening positions, early reflections, modal temporal decay, and mid-to-high-frequency reverberation time. The integration of both optimization methods provides comprehensive acoustic control across the entire audible spectrum.

A fluid dispensing system includes a dispenser that includes a nozzle configured to dispense a fluid material to form an initial fluid portion for placement in and / or on a dispense location; and an acoustic processing system configured to manipulate the initial fluid portion to form a modified fluid material and / or a displaced fluid material. The fluid dispensing system moreover includes where the dispenser and / or the acoustic processing system are configured to place the modified fluid material and / or a displaced fluid material at the dispense location and form a deposited fluid material and / or to form a distributed fluid portion.

The present disclosure relates to an acoustic processing device that can suppress the occurrence of excessive atmospheric pressure changes in the eardrums of a user. Provided is an acoustic processing device comprising: a driver unit having a diaphragm; and a housing in which the driver unit is housed. The diaphragm has a vent hole that communicates a first space on a first surface side of the driver unit in the housing and a second space on a second surface side on the reverse side of the first surface. The present disclosure can be applied to, for example, an earphone device.

Provided is an acoustic processing device worn on the body of a user, the acoustic processing device being provided with: a sound collection unit that acquires ambient sound around the user; a receiving unit that receives feature information for a specific speech included in the speech output from the acoustic output device to the user; a processing unit that performs, on the basis of the feature information, acoustic processing on the ambient sound around the user collected by the sound collection unit; and the output unit outputs the environment sound processed by the processing unit to a user.

The invention is suitable for the technical field of acoustic processing, and provides a voice propagation method capable of absorbing and reflecting, used equipment comprises a panel installed in a recording studio, the panel is provided with a plurality of conversion grooves arranged in a rectangular array, and the conversion grooves are internally provided with conversion assemblies capable of converting between a sound absorption mode and a reflection mode. A driving assembly for controlling the conversion assemblies to operate is arranged on the outer side of the panel, and the operation steps include S1, when pure'dry sound 'needs to be recorded in the recording studio, the driving assembly is started, the driving assembly drives the conversion assemblies in all the conversion grooves to operate, and the conversion assemblies are converted into sound absorption modes, and S2, when mixed sound needs to be recorded, the driving assembly is started, and the driving assembly drives the conversion assemblies in all the conversion grooves to operate. According to the sound processing method, the static state is converted into the dynamic state, one-key switching of acoustic scenes is achieved, and seamless conversion between the sound absorption mode and the reflection mode can be achieved in the same physical space according to actual requirements.

To adjust the sound quality depending on how the sound is transmitted.SOLUTION: An ear device 100 includes a control unit 110 that performs acoustic processing on the basis of humidity data acquired by a humidity acquisition unit 150 when performing acoustic processing on the surrounding sound acquired by a sound acquisition unit 130 and outputting it from a sound output unit 140.SELECTED DRAWING: Figure 5

Title: Acoustic treatment device for a vehicle cooling system. Acoustic treatment device (1) intended to equip a cooling system of a vehicle and comprising at least one wall (4) participating in delimiting a duct (2) for the circulation of an airflow, the acoustic treatment device (1) comprising at least one network of resonators (16) formed by one or more rows (18) of resonators (16) arranged around the duct (2) perpendicular to an axis of elongation (A) of the duct, each resonator (16) of a row (18) of resonators (16) comprising at least one cavity (20) disposed in the wall (4) and a neck (22) connecting said cavity (20) to the duct (2), characterized in that, at least for a given dimension of the cavity (20) or of the neck (22), at least one resonator (16) of the row (18) has a value different from the value of the corresponding dimension of the other resonators (16) of the row (18). (Figure 3)

The embodiment of the application relates to the technical field of robot control, and particularly relates to a robot multi-cavity sound production device.The device comprises a control module and at least one sound production module; the control module comprises a processor and a signal driver; the sound production module comprises a vibration module and an acoustic cavity in communication with the vibration module; the sound production module is in communication connection with the signal driver of the control module through a cable or a wireless communication module, the vibration module is arranged to be driven by the control module to generate an initial sound wave, the acoustic cavity is arranged to acoustically process the initial sound wave, and when the sound production module is multiple, the multiple sound production modules are arranged at different positions of a head, a neck or a trunk of a robot body respectively.The device can simulate the spatial listening of human sound production and the sound characteristics of the common sound production of multiple positions, enhances the authenticity of robot sound production, makes the robot output have natural human voice characteristics, enhances the immersion and naturalness of human-computer interaction, and improves the interaction experience.

To provide an edge and the like that improve sound quality. The edge includes an edge-shaped portion that is formed from an inner peripheral portion to an outer peripheral portion, and a groove portion that is formed in the edge-shaped portion and has a peak portion and a valley portion, wherein a ridge line of the valley portion of the groove portion extends from a start point on the inner peripheral portion side to an end point on the outer peripheral portion side so as to draw a continuously changing curve.

This application discloses a noise control method and a near-ear open-back audio device, relating to the field of acoustic processing technology. The noise control method is applied to a near-ear open-back audio device, which includes at least two first microphones. The noise control method includes: acquiring ambient noise signals collected by each first microphone; performing noise pattern recognition based on the ambient noise signals to obtain a target noise pattern; performing noise localization based on the ambient noise signals to obtain a target noise direction; selecting a target noise reduction controller from a plurality of preset noise reduction controllers that corresponds to the target noise pattern and target noise direction; and performing active noise control based on the target noise reduction controller. This application provides a solution for applying active noise control in a near-ear open-back audio device and improving the noise control effect.

To maintain volume heard by a user constant, even when the user of a spot-sound-reproduction chair moves his / her head. To this end, a sound emission device according to the disclosed technology emits sound such that only an area in the immediate vicinity of the user becomes an audible region, the sound emission device including a speaker sound-reproduction unit, a sensor signal acquisition unit, and an acoustic processing unit. The speaker sound-reproduction unit makes a first speaker and a second speaker emit acoustic signals that are approximately opposite in phase to each other. The sensor signal acquisition unit acquires movement of at least part of the head of the user. The acoustic processing unit determines a gain of acoustic signals emitted from the first speaker and the second speaker on the basis of the movement. Here, acoustic signals emitted from the first speaker and acoustic signals emitted from the second speaker make up one audible region for the user.

The invention provides a speech synthesis method, a speech synthesis model and electronic equipment. The method comprises the following steps: acquiring speech synthesis data; processing the speech synthesis data to obtain a sequence unit; adjusting the index value of the sequence unit to obtain an adjusted sequence unit; the adjusted index values of the original text sequence unit and the reference text sequence unit are in an index range of a text matrix block of a unified embedding layer, and the adjusted index value of the reference audio sequence unit is in an index range of an audio matrix block of the unified embedding layer; inputting the adjusted sequence units into a unified embedding layer for feature embedding processing to obtain embedding vectors of the sequence units; and performing acoustic processing on the embedded vector to obtain a target audio sequence unit corresponding to the original text. According to the technical scheme, the uniform embedding layer of the speech synthesis model is used for carrying out feature embedding on the sequence units of different modes at the same time, and the bottleneck of multi-mode speech synthesis in the aspects of calculation efficiency and memory efficiency is solved.

The application provides a low-delay streaming voice interaction system with a breaking processing function, and relates to the technical field of artificial intelligence.The application carries out necessary preprocessing and acoustic feature extraction through a real-time acoustic processing module, and uses robustness enhancement technology to resist distortion and complex environmental noise introduced by an interaction channel.A streaming acoustic decoding module carries out acoustic modeling, language model application and decoding in real time and in parallel, and outputs an ultralow-delay text transcription result stream.The real-time acoustic processing module is responsible for high-precision and ultralow-delay detection of user voice activity, especially user voice activity during AI playback of voice, to determine the real-time voice activity state of the user.The system uses an efficient and low-delay bidirectional streaming network transmission mode between modules and between the system and a communication platform, so that audio streams, acoustic feature streams, text streams and control signals can be transmitted and processed in real time with extremely low end-to-end delay.

The present invention provides an acoustic treatment device comprising a decorative painting layer, a sound-absorbing panel, and a first housing. The decorative painting layer and the sound-absorbing panel are disposed on a first side of the first housing, with the sound-absorbing panel disposed between the decorative painting layer and the first housing. The first housing and the sound-absorbing panel form a cavity. A first sound-absorbing layer, a second sound-absorbing layer, and a speaker are disposed within the cavity. The first sound-absorbing layer surrounds the speaker, and the second sound-absorbing layer is disposed on a second side of the first sound-absorbing layer. The speaker comprises a low-frequency speaker array, a mid-frequency speaker, and a high-frequency speaker. The mid-frequency speaker and the high-frequency speaker are disposed facing the decorative painting layer, and the diaphragms of the low-frequency speakers along the low-frequency speaker array are disposed toward the sidewall of the first housing. The sound-absorbing panel is provided with multiple sound-absorbing perforations. This device achieves sound absorption and amplification while ensuring a reduced volume and preventing vibration of the decorative painting layer.

Provided is an acoustic processing device comprising: an acquisition unit that acquires an outside acoustic signal that is a signal derived from acoustics propagating outside the external auditory canal of a user and an inside acoustic signal that is a signal derived from acoustics propagating inside the external auditory canal; a hearing aid processing unit that adjusts the sound volume of the outside acoustic signal on the basis of the auditory characteristics of the user measured in advance; an adjustment unit that, on the basis of the adjustment amount of the sound volume of the outside acoustic signal by the hearing aid processing unit, adjusts an occlusion cancellation amount for attenuating an occlusion that causes the sound volume of the inside acoustic signal to be amplified due to wearing of an acoustic device on an ear of the user; and an output unit that outputs, to the user, an output sound with which the sound volume of the outside acoustic signal and the occlusion cancellation amount have been adjusted by the hearing aid processing unit and the adjustment unit.

The application provides a low-noise mounting device and a noise reduction structure design method thereof, and relates to the technical field of aviation noise control. The low-noise mounting device noise reduction structure design method comprises the following steps: obtaining unsteady pressure fluctuation data of a calculation model surface; wherein the calculation model has the main structure characteristics of the low-noise mounting device; obtaining the maximum unsteady pressure fluctuation amplitude position of the calculation model surface according to the unsteady pressure fluctuation data, and expanding and dividing multiple acoustic processing areas from the maximum position as the center; calculating each acoustic processing area to obtain the corresponding target frequency; and selecting an acoustic impedance matching structure according to the target frequency, so that the acoustic structure with specific frequency characteristics can be designed for different acoustic processing areas, thereby realizing the precise control of the mounting device on multi-frequency noise, and further helping to achieve the ideal noise reduction effect on the body mounting effect noise, especially the mounting effect noise of the open rotor engine.

An acoustic treatment for use in an acoustic treatment for a gas turbine engine includes a sheath having a plurality of perforations. A plurality of cell structures extends from the sheath such that the sheath and the cell structures are a monolithic component. The plurality of perforations of the sheath are formed by filaments of a first material that define a first dimension of the perforations having a linear edge and filaments of a second material crossing the filaments of the first material that define a second dimension of the perforations having a linear edge. Such perforations have a non-cylindrical shape defined by the linear edges of the filaments of the first material and the filaments of the second material. A gas turbine engine is also disclosed.

The invention provides a voice processing method and system, the system comprises an initial voice processing link composed of a plurality of voice processing modules, and the method comprises the steps: obtaining a to-be-processed audio signal, and extracting multi-modal feature information for representing a current acoustic scene based on the audio signal; determining an acoustic processing mode corresponding to the current acoustic scene based on the multi-modal feature information; adjusting the start-stop state and / or processing parameters of a voice processing module in the initial voice processing link based on the acoustic processing mode to obtain a target voice processing link; and performing voice enhancement processing on the audio signal by using the target voice processing link to obtain an enhanced voice signal. According to the invention, flexible speech enhancement processing for different acoustic scenes can be realized.

A first electronic device used by a first user can determine whether a second electronic device that is being used by a second user is located within a threshold distance of the first electronic device. The first electronic device may be presenting a first extended reality (XR) environment to the first user and the second electronic device may be presenting a second XR environment to the second user. The first electronic device, in response to the second electronic device being located within the threshold distance, can perform acoustics processing for nearby spatial audio. For example, the first electronic device can play a voice of the second user with a sound adjustment. Other aspects are also described and claimed.

The present acoustic processing method includes a search step for searching for a path of a sound from a sound source to a sound receiving point in a virtual space, an identification step for identifying a reflection position of the sound on the path, and a processing step for performing processing on the sound at the sound receiving point based on a result of a wave motion acoustic simulation regarding the reflection of the sound with a surrounding area of ​​the reflection position as a calculation area.