Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

22results about How to "Clear voice" patented technology

Open type earphone audio optimization method based on adaptive compensation algorithm

The invention provides an open earphone audio optimization method based on a self-adaptive compensation algorithm, and aims to improve the audio auditory experience of a user. The method comprises the following steps: firstly, acquiring an environmental noise signal through an earphone microphone, receiving a target audio signal, analyzing auditory perception of a user in a current environment by combining an ISO226 loudness curve and the like, and determining auditory sensitivity of the user to different frequency bands (including high frequency, intermediate frequency and low frequency); and then, enhancing the high-frequency part, deepening the low-frequency part and performing smooth transition compensation on the intermediate-frequency part by using a self-adaptive compensation algorithm. And then, dynamically adjusting the low-frequency part by using a hyperbolic filter, generating an adjusted audio signal, and generating a harmonic signal based on the amplitude and frequency characteristics to further optimize the tone quality. Finally, the optimized audio signal and the generated harmonic signal are provided for a user together, and the effects of automatically optimizing audio output in different environments and enhancing tone quality performance are achieved.
Owner:GUANGDONG MINGYANG SMART TECH CO LTD

Mental health monitoring system based on large model

The invention provides a psychological health monitoring system based on a large model, and relates to the technical field of data processing, and the method comprises the steps: collecting multi-modal data of a user, and preprocessing the multi-modal data to obtain voice data, video data and text data; processing the voice data to obtain transient high-frequency noise data, processing the video data to obtain picture fuzzy data, and obtaining voice emotion features and behavior emotion features according to the frequency domain voice data and the video data; processing the transient high-frequency noise data to obtain voice restoration emotion features, and restoring the picture fuzzy data to obtain behavior restoration emotion features; and fusing the voice emotion features, the behavior emotion features, the voice restoration emotion features and the behavior restoration emotion features to obtain emotion feature analysis data, and inputting the emotion feature analysis data into a preset emotion recognition large model to generate a mental health state assessment result. According to the invention, accurate data can be obtained.
Owner:MAILEFENG (XIAMEN) E-COMMERCE CO LTD

Digital human voice interaction processing method and device, electronic equipment and medium

The invention provides a digital human voice interaction processing method and device, electronic equipment and a medium, and relates to the technical field of natural language processing, in particular to the technical field of voice recognition, semantic recognition, intelligent agents and generative search. According to the implementation scheme, in response to received first audio data, first voiceprint data of a digital person is obtained, the first audio data indicates a user to initiate a voice interaction request to the digital person, and the first voiceprint data indicates voiceprint data used by the digital person for currently performing voice broadcasting; in response to the received second audio data, first noise reduction processing is carried out on the second audio data based on the first voiceprint data to obtain third audio data, and the time for receiving the second audio data is after the time for receiving the first audio data; and in response to a first instruction which is sent by the user and indicates to interrupt voice interaction and is determined according to the third audio data, generating a stop instruction and sending the stop instruction to the digital person to control the digital person to stop voice broadcasting.
Owner:BEIJING BAIDU NETCOM SCI & TECH CO LTD

Thin loudspeaker of alto cone frame

The utility model discloses a thin loudspeaker of an alto cone frame, which comprises a fixed seat, a connecting block sleeved at the upper end of the fixed seat, a sensing assembly arranged at one side of the outer end of the connecting block, a cone fixedly connected at the upper end of the connecting block, and a plurality of threaded holes arranged at the periphery of the top end of the cone. Wherein the upper end of the sound basin is provided with an elastic ring film, the sound transmission assembly is fixedly installed in the fixed seat and is used for sound transmission, through the synergistic effect of the sound transmission assembly, the sound basin, the elastic ring film and the hemispherical cover body, accurate conversion from an electric signal to a sound wave, the magnetic field effect of the sound transmission assembly and vibration generation are realized, and the sound transmission effect is improved. The sound cone can accurately generate vibration along with the change of an electric signal, and meanwhile, the design of the elastic ring film and the hemispherical cover body further enhances the transmission effect and focusing performance of sound, so that the sound is clearer.
Owner:SHENGZHOU KAIDA ELECTRONICS CO LTD

HiFi sound box with dial display

The invention discloses a HiFi sound box with dial display, relates to the technical field of sound box playing, and provides the following scheme for solving the problem of higher requirements of consumers on tone quality purity, detail expressive force and sound hierarchy in the prior art: the HiFi sound box comprises a shell, and a satellite sound box and a subwoofer are respectively arranged at the lower part in the shell; the satellite sound box is used for outputting sound at medium and high frequency bands, the subwoofer is used for playing a low-frequency part, an electronic tube is arranged at one end of the upper part in the shell, digital power amplification modules are arranged on one side of the electronic tube at intervals, and a dial plate is arranged in each digital power amplification module; according to the invention, the structure is novel, the two satellite sound boxes, the subwoofer and the electronic tube are adopted, and the two satellite sound boxes, the subwoofer and the electronic tube cooperate with each other, so that rich sound effects are brought.
Owner:GUANGZHOU BLUE LIGHT ELECTRONICSTECH CO LTD

Capacitance microphone

ActiveCN224068788UReduce vibration effectsVibration effects are not affected by vibrationElectrostatic transducer microphonesCapacitanceElastic component
The utility model discloses a capacitance microphone, which comprises a mounting seat, a mounting frame is hinged to the top of the mounting seat, a microphone is arranged on the inner side of the mounting frame, a plurality of mounting buckles are arranged on the inner side of the mounting frame, and a plurality of mounting buckles corresponding to the mounting buckles are arranged on the outer side of the microphone. The installation buckle is connected with the installation buckle through an elastic component, the elastic component is an elastic line or an elastic rope, the top of the installation base is hinged to the installation frame through a hinge screw, and the hinge screw is in threaded connection with a manual adjusting screw. The microphone is convenient to mount, when vibration is generated outside, the vibration is transmitted to the elastic component through the mounting seat and the mounting frame, and the vibration is retarded by the elastic component and then transmitted to the microphone due to the elasticity of the elastic component, so that the influence of the external vibration on the microphone is greatly reduced, and the service life of the microphone is prolonged. The microphone is ensured not to influence audio receiving signals due to vibration, and the microphone is ensured to output clear sound.
Owner:ENPING ENSHI PLASTIC TECH CO LTD

A children's piano

A children's piano comprises a piano frame, one side of the piano frame is provided with piano keys, and the other side is provided with a sound cavity; the piano keys extend to the inner side of the sound cavity after passing through a partition; in the sound cavity, a sound-generating device for generating sound by striking the piano keys is provided on the upper side of the piano keys, and a sound cavity cover is detachably fixed on the top of the sound-generating device; the sound-generating device comprises a group of sound tubes, and the sound tubes are fixedly mounted on a sound tube bracket through gaskets; the sound tubes comprise a plurality of metal hollow tubes arranged in sequence, and the plurality of metal hollow tubes are arranged in a structure according to musical temperament with different lengths; the gasket is provided with slots corresponding to the metal hollow tubes, and the plurality of metal hollow tubes are installed and fixed in the plurality of slots at intervals; a piano key mounting seat is installed between the piano keys and the bottom plate of the piano frame, and soft pads for eliminating noise are provided on the piano key mounting seat, the bottom surface of the partition and the bottom plate of the piano frame at the parts that contact the piano keys when they move.
Owner:ROYALSOUND MUSIC INSTR MFR CO LTD

Lightweight ear mold, ear mold assembly and hearing aid

The utility model discloses a lightweight ear mold, an ear mold assembly and a hearing aid, the lightweight ear mold comprises an ear mold body, the interior of the ear mold body is hollowed to form an installation cavity with an opening at the installation rear end, and the front end of the ear mold body is provided with a through sound guide hole; the mounting cylinder is fixed in the mounting cavity and arranged corresponding to the sound guide hole, the mounting cylinder is used for clamping a receiver, and the front end of the receiver penetrates through the sound guide hole and is flush with the outer surface of the ear mold body; and the pull rope assembly is arranged in the mounting cavity and close to the tail end of the ear mold body, and the pull rope assembly is used for taking out the ear mold from the human ear under the action of external tension. Due to the fact that the interior of the ear mold body is hollowed out, compared with a solid structure, materials are greatly reduced, and the mass of the ear mold is greatly reduced while the material cost is saved; the telephone receiver is directly clamped and fixed by arranging the mounting cylinder, so that the telephone receiver can be conveniently pulled out during maintenance, and the maintenance efficiency and convenience are improved.
Owner:BOYIN HEARING EQUIP (SUZHOU) CO LTD

A back-input microphone with double pads

The embodiment of the present invention discloses a back-input sound microphone with double pads, comprising a circuit substrate, a packaging shell buckled on the circuit substrate, a microphone assembly installed on the top of the circuit substrate, a first pin, a second pin and a third pin arranged on the circuit substrate, and the bottom surface of the circuit substrate is provided with: an acoustic through hole; at least one inner pad arranged on the bottom surface of the circuit substrate and connected to the first pin; at least one outer pad arranged around the outer side of the inner pad and connected to the first pin; a plurality of auxiliary pads, at least one rectangular pad connected to the second pin, and at least one rectangular pad connected to the third pin. The present invention adopts a method of outer pads surrounding inner pads, thereby increasing the connection area of ​​the pads and avoiding the problem of insufficient airtightness of a single pad. The double pads connect electrical components, thereby improving the airtightness of the microphone pads, so that the background sound microphone has no sound loss and the microphone sound is louder and clearer.
Owner:ZILLTEK TECH SHANGHAI +1

Sound control method and device

The embodiment of the present invention provides a sound control method and device, which transmits corresponding audio signals to multiple sets of windings of a motor respectively, and the audio signals are used to control the windings to emit sounds corresponding to the audio signals; and the multiple sets of windings are controlled to emit sounds so that the synthetic torque formed by the torque for sound generation corresponding to each set of windings is within a target synthetic torque range. In the embodiment of the present invention, the motor of the vehicle has multiple sets of windings, and the multiple sets of windings are independently controlled. Corresponding audio signals for controlling the windings to emit sounds corresponding to the audio signals are transmitted to the multiple sets of windings of the motor respectively. When the multiple sets of windings of the motor are controlled to emit sounds, since the synthetic torque formed by the torque for sound generation corresponding to each set of windings is within the target synthetic torque range, that is, the torque of the motor is controlled within a relatively small range or even cancels each other out, thereby reducing the impact of the torque on the vibration of the motor, and thus reducing the noise when the motor emits sounds.
Owner:BYD CO LTD

A scarf for detecting carotid pulse

ActiveCN224806518UAdjust tightnessclear voice
The utility model provides a kind of scarf of detecting carotid artery pulsation, belong to intelligent wearing technical field.The technical problem of scarf in prior art cannot analyze pulse frequency, and the technical problem that detection equipment is inconvenient to disassemble simultaneously does not have early warning mechanism is solved.Its technical scheme is: a kind of scarf of detecting carotid artery pulsation, including scarf body, fixing device and pulse detection device, fixing device is set on scarf body, and pulse detection device is detachably set on fixing device;Fixing device is provided with outside groove, middle protrusion and inside groove, and the material of fixing device adopts the silica gel material of rich elasticity.The beneficial effects of the utility model are: the utility model takes convenience and comprehensiveness as core, sensor, microprocessor, loudspeaker are simultaneously designed on detachable scarf, integration degree, i.e.the number of devices per unit area, compared with traditional design has reduced, and it is convenient to wear.
Owner:SUZHOU UNIV

High-pitch loudspeaker capable of eliminating resonance

The invention discloses a high pitch loudspeaker capable of eliminating resonance, and belongs to the technical field of loudspeakers. In order to solve the problem that the sound quality of the loudspeaker is damaged due to resonance transmission of the high-pitch loudspeaker, the bottom of a connecting block is in sliding contact with the top face of a vibration reduction ring, the top of the connecting block is arranged on a guide column in a sliding mode through a sliding piece, and when the loudspeaker vibrates, a vibration reduction spring can be compressed and stretched, absorb vibration energy and reduce vibration transmitted to a mounting panel; the spring sleeved outside the spring column forms a suspension system, elastic support can be provided when the high pitch loudspeaker body vibrates, the spring can absorb and isolate vibration and reduce vibration transmission, one end of the spring column is movably connected with the inner wall of the vibration reduction ring through the pin shaft, and the movable connection allows the vibration reduction ring to move freely when the loudspeaker vibrates. The vibration reduction gasket reduces echo and resonance, so that sound emitted by the loudspeaker is clearer and more natural, and the tone quality is remarkably improved.
Owner:ANHUI JINGLI ELECTRONICS CO LTD

Control method based on voice recognition

The invention discloses a control method based on voice recognition, and belongs to the technical field of voice recognition, and the method comprises the following steps: S1, collecting the control voice of a user, and carrying out the framing processing of the control voice; s2, generating a global audio matrix, a first combination matrix and a second combination matrix according to a plurality of frames of control voice segments obtained through framing processing, and constructing a control voice objective function according to the global audio matrix, the first combination matrix and the second combination matrix; s3, processing the control voice by using the control voice target function to obtain an optimal control voice; and S4, generating a control password according to the optimal control voice. The control voice objective function is generated, quality processing of the control voice is completed, the accuracy of converting the control voice into the control password is improved, home control is more visual and easy to use, and popularization of smart home is facilitated.
Owner:四川易景智能终端有限公司

Building interphone with constant temperature structure

The utility model relates to the technical field of communication equipment, in particular to a building interphone with a constant-temperature structure, which comprises a mounting bottom plate, a protective frame body is fixedly mounted on the front surface of the mounting bottom plate, a constant-temperature assembly is arranged in the protective frame body, a heat dissipation assembly is arranged in the protective frame body, and the constant-temperature assembly and the heat dissipation assembly are fixedly mounted on the mounting bottom plate. An operation assembly is arranged on the front face of the protection frame body. According to the building interphone with the constant-temperature structure, by installing the constant-temperature assembly, through cooperation of a constant-temperature bin, a clamping rod and other components, the heating plate can be installed in the constant-temperature bin through the clamping rod, then a heating coil can heat the interior of the interphone, and the situation that the interphone cannot be used due to the too low temperature is prevented; and then the temperature detection module monitors the temperature in the interphone in real time, the temperature control module stops the work of the heating coil when the temperature reaches a proper temperature, and meanwhile, the heat preservation layer is matched for heat preservation, so that the interior of the interphone can be kept at a constant temperature, and meanwhile, the electric power can be saved.
Owner:NANCHANG FUTAIBUILDING INTERCOMEQUIPMENT CO LTD

Anti-explosion sound-light alarm system for bank security and protection

The utility model discloses an explosion-proof acousto-optic alarm system for bank security, which comprises a left explosion-proof acousto-optic alarm and a right explosion-proof acousto-optic alarm, a connecting seat is connected between the left explosion-proof acousto-optic alarm and the right explosion-proof acousto-optic alarm to form a shape like a Chinese character'ao ', and a detection light curtain is mounted on the surface of the connecting seat. The detection light curtain is of a detachable structure, an alarm bell is installed on the surface of the detection light curtain, a notch is formed in the bottom of the detection light curtain, and at least one photoelectric sensor is arranged in the detection light curtain. The two groups of explosion-proof audible and visual alarms and the detection light curtain are arranged, when a light path of a light source of a photoelectric sensor in the detection light curtain is blocked by an object, a signal is output to enable the two groups of explosion-proof audible and visual alarms to give an alarm and flicker, the two groups of explosion-proof audible and visual alarms are matched with the sound of an alarm bell, and the three have different tones and sound in turn from high to low, so that the sound is clear and powerful; the warning device can attract attention of people, the warning effect is better, and meanwhile, a signal can be sent into a control room to remind and warn security.
Owner:FUJIAN FUGUANG TIANWEI ELECTRONIC TECH CO LTD

A pet activity monitoring collar with removable batteries

ActiveCN224267806Uplay clearlyAccurate playbackOther apparatusComputer hardwareElectrical battery
This utility model relates to the field of pet equipment technology, specifically to a pet activity monitoring collar with a removable battery. Under normal circumstances, when the accelerometer detects that the collar is stationary and has been placed there for 10 minutes, the accelerometer will promptly transmit this detected state signal to the main control MCU. Upon receiving the signal, the main control MCU will immediately enter sleep mode, thereby reducing energy consumption and achieving energy saving. However, once the accelerometer senses that the collar has moved, it will immediately receive this dynamic change signal and quickly transmit the signal to the main control MCU, thereby controlling the main control MCU to start from sleep mode. After the main control MCU is awakened, it will activate the audio IC through its control function. When the audio IC is activated, it will output an analog signal to the speaker device, ultimately enabling the stored voice commands to be played clearly and accurately for further operation or command transmission.
Owner:CHANGSHA LIUBA PET CO LTD

Hearing aid system and method capable of automatically adjusting volume according to environment

The invention discloses a hearing aid system and method capable of automatically adjusting volume according to environment. The method comprises the following steps: collecting environment noise data through at least one microphone of a hearing aid; performing fast Fourier transform (FFT) on the sound feature vector V to calculate a frequency feature F = {f1, f2,..., fm}, and extracting a frequency component and an energy spectrum E = F2 thereof; calculating the total sound pressure level SPL of the environmental noise according to the frequency domain feature F and the energy spectrum E; adaptive compensation is carried out according to the total sound pressure level SPL and a hearing curve C = {c1, c2,..., ck} of a user, and a needed gain G is calculated; and based on the gain G, adjusting the output volume of the hearing aid through a digital signal processor. The method has the following advantages that real-time adaptability is achieved, the comfort level of the user can be improved, the voice recognition capacity is enhanced, and the method adapts to diversified use scenes.
Owner:深圳市婕妤达电子有限公司

A mental health monitoring system based on large model

The present invention provides a mental health monitoring system based on a large model, and relates to the technical field of data processing. The method includes: collecting multimodal data of a user, and preprocessing the data to obtain voice data, video data and text data; processing the voice data to obtain short-term high-frequency noise data, processing the video data to obtain image fuzzy data, and obtaining voice emotion features and behavior emotion features according to the frequency domain voice data and video data; processing the short-term high-frequency noise data to obtain voice repair emotion features, and repairing the image fuzzy data to obtain behavior repair emotion features; fusing the voice emotion features, behavior emotion features, voice repair emotion features and behavior repair emotion features to obtain emotion feature analysis data, and inputting the data into a preset emotion recognition large model to generate a mental health status assessment result. The present invention can obtain accurate data.
Owner:MAILEFENG (XIAMEN) E-COMMERCE CO LTD

Key device of membrane keyboard

A key device of a membrane keyboard comprises a lower cover, a supporting plate, an elastic piece, a membrane circuit piece, an elastic body, an upper cover and a key cap. The lower cover comprises a lower substrate and a lower convex cover. And the supporting plate and the lower convex cover jointly define a sound effect enhancing space. And the elastic sheet is located in the sound effect enhancing space. The key cap abuts against the elastic body and comprises a cap cover, a plunger connected with the cap cover and two supporting feet extending downwards from the plunger. The supporting legs extend into the sound effect enhancing space, and one of the supporting legs abuts against the elastic sheet. When the key cap is pressed, one of the supporting feet abuts against the elastic piece to enable the elastic piece to deform and accumulate elastic force, and when the key cap is loosened, the elastic piece pushes the key cap to move upwards, and the elastic piece releases the elastic force and impacts one of the supporting feet to make a sound.
Owner:JINGYUAN COMPUTER JIANGSU CO LTD

Steam quality alarm mechanism and coating machine

The utility model relates to the technical field of medicine production, and discloses a steam quality alarm mechanism and a coating machine, which comprise an electro connecting pressure gauge, a relay, a power supply module and an alarm device, the electric contact pressure gauge is arranged on the steam pipeline and is used for detecting the pressure in the pipeline; the relay comprises a coil and a normally open contact, and the coil is electrically connected with the electric contact pressure gauge; one end of the power supply module is electrically connected with one end of a normally open contact of the relay; one end of the alarm device is electrically connected with the other end of the normally open contact of the relay, and the other end of the alarm device is electrically connected with the other end of the power supply module. According to the utility model, an operator can respond according to an alarm, deal with abnormities in time and control risks in time, so that the coating quality of a solid preparation is improved.
Owner:YABAO PHARMA GRP CO LTD

Bone conduction anti-noise listening and speaking earphone

The utility model discloses a bone conduction anti-noise listening and speaking earphone, which comprises a head beam main body and two sets of sound transmission components which are symmetrically arranged left and right, each sound transmission component comprises an ear-crossing support piece, a bone conduction microphone and a bone conduction loudspeaker, the bone conduction microphone is inserted into a rear ring piece of the ear-crossing support piece and is attached to a temporal bone behind an ear, and the bone conduction loudspeaker is connected with the bone conduction microphone. The bone conduction loudspeakers are inserted into the front ring pieces of the ear-crossing supporting pieces and attached to temporal bones in front of ears, and the head beam body is connected between the two ear-crossing supporting pieces.
Owner:BEIJING WANGE DIGITAL COMM TECH CO LTD