1004 results about "Bone conduction hearing" patented technology

An acoustic output device is provided. The acoustic output device includes a housing; a bone conduction vibrator configured to generate bone conduction sound waves and transmit the bone conduction sound waves to a cochlea through the housing to produce sound; an air conduction vibrator configured to generate air conduction sound waves, the air conduction sound waves being transmitted to an ear through sound guiding holes in the housing; and a processing module configured to provide the bone conduction vibrator and the air conduction vibrator with a first audio signal and a second audio signal, respectively, the first audio signal and the second audio signal having a frequency division point, the first audio signal and the second audio signal including components with frequencies above and below the frequency division point, respectively. The frequency division point is not less than 600 Hz.

A headphone apparatus and methods of operation for bone conduction headphones with push-to-talk operation is disclosed. The headphone apparatus is capable of wireless communication and can be communicatively coupled to one or more machines. The push-to-talk feature of the headphone apparatus enables transmissions / messages from the headphone apparatus to the one or more communicatively coupled machines. The push-to-talk feature of the headphone apparatus can also enable push-to-talk operation of the one or more communicatively coupled machines. The headphone apparatus is configured to be received by a charging case. The charging case is configured to enable wireless charging and / or wired charging of the headphone. The charging case is configured to be received by a charging cradle.

The invention discloses an intelligent blind guiding glasses system based on a multi-mode large language model. The intelligent blind guiding glasses system comprises an image acquisition module, a voice acquisition module, a large language model module, a bone conduction sound transmission module, a navigation path planning module, a central processor module and a wireless communication module, the image acquisition module is used for acquiring a three-dimensional image of a front scene and providing three-dimensional space information; the voice acquisition module is used for acquiring a voice instruction of a user; the big language model module is used for generating character answers and converting the character answers into voice according to the voice instruction of the user by utilizing a big language model; the bone conduction sound transmission module is used for receiving and playing the voice generated by the large language model module; the navigation path planning module is used for planning a navigation path according to the user position and the destination; the functions of navigation positioning, line guiding, voice prompting and the like are provided for the blind, the glasses are adopted as a carrier, carrying is convenient, voice awakening and other instructions are adopted to replace keys, operation is easy, and practicability is high.

Methods and apparatus are described herein related to improving the sound quality of a bone conduction speaker. The sound quality of the bone conduction speaker is adjusted in the sound generation, sound transferring, and sound receiving of the bone conduction speaker by designing vibration generation manners and vibration transfer structures.

The invention relates to the technical field of earphone noise reduction, and discloses a bone conduction earphone intelligent noise reduction method and system based on multi-mode interactive fusion, and the method comprises the steps: collecting a multi-mode signal when a user uses a bone conduction earphone, carrying out the motion artifact elimination of the multi-mode signal, and obtaining a pure multi-mode signal; identifying a vocal cord vibration fundamental frequency and a formant of the pure multi-mode signal to perform noise fusion characterization processing on the bone conduction earphone to obtain a noise characterization matrix, and identifying a noise type of the bone conduction earphone by using the noise characterization matrix; analyzing a physiological fatigue index of the user, constructing noise reduction parameters of the bone conduction earphone based on the physiological fatigue index and the noise type, and constructing a noise reduction propagation link of the bone conduction earphone; and carrying out anti-howling adaptive filtering on the noise reduction propagation link by using the noise representation matrix to obtain a reverse sound wave, and carrying out noise reduction on the bone conduction earphone to obtain a noise reduction audio. According to the invention, the bone conduction earphone wearing experience of the user can be improved.

The invention discloses a noise reduction method and device, equipment, a storage medium and a program product, and relates to the technical field of audio processing, and the method comprises the steps: collecting a bone conduction signal and at least two paths of environment air conduction signals of an earphone wearer through an earphone, based on the bone conduction signal, performing first noise reduction processing on a target air conduction signal of a target direction determined based on the at least two paths of environment air conduction signals to remove a first air conduction component of a relatively low frequency band of an earphone wearer, and obtaining an initial noise-reduced signal; and performing second noise reduction processing on the initial noise-reduced signal based on the bone conduction signal, the at least two paths of environmental air conduction signals and the phase difference of the at least two paths of environmental air conduction signals, so as to remove a second air conduction signal of a higher frequency band of the earphone wearer, and obtain a target noise-reduced signal. According to the method and the device, the noise generated by the earphone wearer in the audio recorded by the earphone is effectively removed.

1. The name of this design product: Sports bone conduction headphones (X500). 2. The purpose of this design product: as a headphone audio playback device. 3. The key point of the design of this product lies in its shape. 4. The picture or photo that best illustrates the design points: three-dimensional picture.

The present description relates to an acoustic output device, comprising: a housing; a bone conduction vibrator, which is used for generating bone-conducted sound waves, the bone-conducted sound waves being transmitted to the cochlea by means of the housing to generate sound; an air conduction vibrator, which is used for generating air-conducted sound waves, the air-conducted sound waves being transmitted to the ear of a user by means of sound guide holes in the housing; and a processing circuit, which is configured to provide a first audio signal for the bone conduction vibrator, and provide a second audio signal for the air conduction vibrator, wherein the processing circuit is further configured to adjust a low-frequency component in the first audio signal or adjust a high-frequency component in the second audio signal. The low-frequency component in the first audio signal or the high-frequency component in the second audio signal are adjusted by means of the processing circuit, such that the ratio of bone-conducted components to air-conducted components in the output of the acoustic output device is variable, so as to adjust high and low frequency output effects of the acoustic output device. Thus, the acoustic output device is suitable for different scenarios, thereby enhancing the use experience of the acoustic output device.

The invention discloses a fully-implanted artificial cochlea system and a noise reduction method thereof.The fully-implanted artificial cochlea system comprises an implant and a fully-implanted microphone, the fully-implanted microphone comprises a shell, a PCBA board, a first sound sensor and a bone conduction sensor are arranged in the shell, the first sound sensor is connected with the PCBA board and used for receiving a first external sound signal and transmitting the first external sound signal to the PCBA board, and the bone conduction sensor is connected with the implant. The bone conduction sensor is also connected with the PCBA board and is used for collecting an in-vivo noise signal and transmitting the in-vivo noise signal to the PCBA board; the PCBA board is used for receiving the first external sound signal and the in-vivo noise signal, and at least performing noise reduction on the first external sound signal and then outputting the first external sound signal; the implant or the fully-implanted microphone is connected with a second sound sensor, the second sound sensor is connected with the PCBA, the second sound sensor receives a second external sound signal and transmits the second external sound signal to the PCBA board, and the PCBA board receives the second external sound signal, at least carries out noise reduction on the second external sound signal and then outputs the second external sound signal; according to the system, the wearing comfort of a user is effectively improved, the efficient noise reduction performance is met, and the hearing requirement of a user patient can be met.

The present disclosure is of a bone conduction microphone. The bone conduction microphone comprises of a laminated structure and a base structure. The laminated structure is formed by a vibration unit and an acoustic transducer unit. The base structure is configured to load the laminated structure. At least one side of the laminated structure is physically connected to the base structure. The base structure vibrates based on an external vibration signal, the vibration unit deforms in response to the vibration of the base structure, and the acoustic transducer unit generates an electrical signal based on the deformation of the vibration unit. A resonant frequency of the bone conduction microphone is within a range of 2.5 kHz-4.5 KHz.

The invention discloses a cross-medium wearable audio transmission system and a transmission method thereof, which are suitable for audio communication scenes in an air and water body junction environment such as a natatorium. The system comprises a shore transmitting terminal and an underwater receiving earphone, and adopts a blue-green light wave band as a transmission carrier to realize cross-medium wireless transmission of audio signals. The transmitting terminal comprises an audio preprocessing module, a modulation and driving module and a coarse-fine composite light beam alignment module; the receiving earphone comprises an optical receiving module, a posture sensing and aligning module, a signal processing module and a bone conduction audio output unit. According to the system, through a dynamic attitude compensation and light beam alignment mechanism, the audio transmission rate greater than or equal to 1Mbps in a 10-meter range is realized, the error rate is less than or equal to 1 * 10 <-6 >, and the transmission delay is less than 50ms. The method has the advantages of high communication quality, strong anti-interference capability, good wearable performance and the like, and is suitable for scenes of underwater training, voice guidance, immersive audio playing and the like.

1. The name of this design product: Sports bone conduction headphones (K08). 2. The purpose of this design product: as a headphone audio playback device. 3. The key point of the design of this product lies in its shape. 4. The picture or photo that best illustrates the design points: three-dimensional picture.

1. The name of this design product: Swimming bone conduction earphones (X23). 2. Purpose of this design product: audio playback. 3. The key point of the design of this product lies in its shape. 4. The picture or photo that best illustrates the design points: three-dimensional picture.

The invention discloses a hearing aid health analysis method based on a physiological signal monitoring function. The method comprises the following steps: collecting physiological signal data of a user in real time through a multi-mode biosensor array integrated on a hearing aid body; the hearing aid body comprises a digital signal processor and a wireless communication module; the physiological signal data at least comprises a brain wave signal, a skin electric response signal and a temporal artery pulse signal; performing motion artifact elimination processing on the physiological signal data through an adaptive filtering algorithm; performing feature extraction on the preprocessed physiological signal by using an embedded health analysis engine to generate a composite health feature vector containing a sympathetic nerve activity index, cognitive load measurement and a cardiovascular function index; and dynamically generating a health risk assessment report based on an association relationship between the composite health feature vector and a preset hearing scene, the bone conduction vibration unit and the audio synthesis module of the hearing aid body output graded health alarm signals.

Embodiments of this disclosure provide a device operation method and apparatus, and an electronic device. In the device operation method, after obtaining a vibration signal collected by a bone conduction microphone connected to the electronic device, the electronic device extracts a vibration signal feature of the vibration signal, and then compares the extracted vibration signal feature with a control feature stored in the electronic device. When a comparison result is that the extracted vibration signal feature matches the control feature, the electronic device performs an operation corresponding to the control feature. The vibration signal collected by the bone conduction microphone may be a bone conduction audio signal, and the bone conduction audio signal is skin vibration triggered when a nasal cavity and / or a throat of a user who uses the electronic device make / makes a specific sound.

The invention relates to the technical field of emotion monitoring and adjusting, and discloses an emotion monitoring and adjusting system based on real-time dialogue semantic analysis, and the system is characterized in that an information collection module is used for collecting real-time voice information of two dialogue parties; the real-time dialogue semantic analysis module is used for performing semantic analysis on real-time voice information by adopting a MobileViT network, extracting emotional characteristics and dynamically capturing emotional association in a dialogue in combination with a CSN network; the bidirectional emotion regulation module is used for determining the current emotion state of the user based on the output of the real-time dialogue semantic analysis module, mapping the emotion state to a behavior mode, and respectively generating personalized emotion regulation strategies for two dialogue parties by adopting a Bandit algorithm; the hardware and software collaborative interaction module is used for controlling the bone conduction equipment and the LED feedback device according to the emotion regulation strategy generated by the bidirectional emotion regulation module; through cooperative work of software and hardware, real-time monitoring and effective adjustment of emotions of two parties of a dialogue are realized.

The invention provides a recessive gastroesophageal reflux event data analysis system and method based on dynamic changes of abdominal pressure. The system and method are suitable for noninvasive detection of atypical reflux clinically. The system comprises an abdominal pressure dynamic detection unit, a throat vibration detection unit, a multi-mode signal processing module, a reflux event judgment module and a data output module. According to the system, by analyzing time sequence linkage between abdominal pressure mutation and throat vibration, a stomach content countercurrent event is recognized, silent type countercurrent characteristic sound is captured with the assistance of a bone conduction sound wave channel, and multi-path redundancy recognition is achieved. The method is suitable for postoperative patients, children, old people and other people who cannot complain, has the technical advantages of continuous wearing, behavior correlation analysis and clinical verifiability, and significantly improves the recognition rate and diagnosis accuracy of recessive gastroesophageal reflux events.

The invention discloses a radar-vision-I MU fused visual impaired person navigation system, which relates to the technical field of multi-source data processing, and is characterized in that a multi-source data collection module is arranged to collect obstacle distance information, ground feature image data and user motion state data in an environment; a time synchronization module is arranged to carry out space-time alignment on obstacle distance information and ground feature image data to generate multi-modal sensing data, a dynamic map generation module and a fusion model based on a particle filter algorithm are arranged, a dynamic environment map is constructed in combination with motion state data, and the spatial relationship between the current position of a user and surrounding obstacles is output. Setting a trajectory prediction module to perform path planning through a reinforcement learning algorithm to generate a prediction trajectory of user motion, and setting a multi-mode interaction module to output a voice navigation instruction to the visually impaired person through a bone conduction earphone based on the prediction trajectory and a dynamic environment map; the problem of intelligent navigation of a dynamic environment faced by visually impaired people is solved.

The utility model discloses a sound production unit and a head-mounted sound production device, the sound production unit comprises a housing assembly, and a bone conduction sound production device and an air conduction sound production device which are arranged in the housing assembly, the housing assembly comprises a contact surface which is used for contacting with human skin and a sound outlet hole through which sound of the air conduction sound production device is sent out; the sounding unit is provided with a middle surface perpendicular to the width direction of the sounding unit, and the gravity center of the bone conduction sounding device and the gravity center of the air conduction sounding device are located on the two sides of the middle surface respectively; the distance D16 between the gravity center of the bone conduction sound production device and the middle surface is smaller than the distance D17 between the gravity center of the air conduction sound production device and the middle surface, so that the vibration sense generated when the bone conduction sound production device works is closer to the middle area of the surface cover, and the use comfort is better.

The invention provides a bone conduction speech enhancement method based on a double-flow self-attention fusion network. The bone conduction speech enhancement method comprises the following steps: acquiring and preprocessing a bone conduction speech signal to be processed; a double-flow self-attention fusion network is constructed, the double-flow self-attention fusion network comprises a double-flow encoder, a cross-modal feature fusion module, a multi-scale decoder and a waveform reconstruction module which are connected in sequence, the double-flow self-attention fusion network is trained, a trained model is obtained, and the performance of the model under different conditions is evaluated. According to the method, a double-flow structure is used for processing time domain information and frequency domain information respectively, a self-attention mechanism is introduced, so that the model can capture a long-distance dependency relationship in each mode, and the feature quality is improved. According to the invention, the time-frequency information can be better integrated through the cross-modal feature fusion module. According to the invention, the multi-scale loss function supervises the output of different levels of the decoder, so that the network can learn effective spectrogram representation at different resolutions, and a finer spectrum structure can be recovered.

The invention relates to a speech recognition method for a tactical AR helmet, and the method comprises the steps: collecting a first audio signal through a near-field pickup disposed near the mouth and nose of a wearer, and collecting a second audio signal through an environment pickup disposed at the outer side of the helmet or away from the mouth and nose; synchronously acquiring a third signal sounding with the wearer, wherein the third signal is at least one of helmet inner side contact type micro vibration, bone conduction vibration pickup or helmet inner sound pressure change; calculating a near-field difference indicator based on the first audio signal and the second audio signal, the near-field difference indicator comprising at least one of an energy difference or an energy ratio; determining sound production starting and ending moments from the first audio signal and the third signal, and calculating a time sequence synchronization index; and when the near-field difference index satisfies a preset near-field condition and the time sequence synchronization index satisfies a preset synchronization condition, determining that the voice is sent by the helmet wearer and a corresponding voice segment is output for subsequent identification, otherwise, shielding the voice segment.

Provided in the present disclosure are an integrated bone conduction sound generating device and method. The device includes a controller, a sound generating structure and a functional structure, and the three components are integrated together. The functional structure can touch the oral cavity and / or the teeth of the human body, and after the controller drives the sound generating structure to generate a vibration signal, the functional structure can transmit the vibration signal to the auditory system of the human body through the oral cavity and / or the teeth of the human body.

1. The name of this design product: Swimming bone conduction earphones (X7 MAX). 2. Purpose of this design product: audio playback. 3. The key point of the design of this product lies in its shape. 4. The picture or photo that best illustrates the design points: three-dimensional picture.

The invention discloses a bone conduction sleep pillow based on audio vibration analysis, which comprises a sleep pillow body, an integrally formed pillow back is arranged in the middle of the rear side of the sleep pillow body, and bone conduction loudspeakers are arranged on both sides of the top of the sleep pillow body; electromagnetic linear vibration assemblies are arranged at the tops of the sleep pillow body and the pillow back, and driving signals of the electromagnetic linear vibration assemblies directly come from audio low-frequency electric signals; the integrated processor comprises a Bluetooth audio processing system and has the functions of real-time frequency division and vibration signal extraction; and the power supply system provides electric energy for the sleep pillow. The two bone conduction loudspeakers are symmetrically distributed about the central axis of the sleep pillow body. By means of the processor, low-frequency components (20-150 Hz) in music signals are directly analyzed to drive the vibrator, vibration and music rhythm synchronization is achieved, and by means of the bone conduction loudspeaker, composite biomechanical stimulation is formed by a bone conduction sound field (50-4000 Hz) and low-frequency vibration.

The present disclosure relates to a hearing apparatus comprising: a bone conduction sensor configured to convert bone vibrations of voice sound information into a bone conduction signal; a signal processing unit configured to implement a synthetic speech generation process, the synthetic speech generation process implementing a speech model; wherein the synthetic speech generation process receives the bone conduction signal as a control input and outputs a synthetic speech signal.

The invention discloses an active and passive combined type low-frequency enhanced bone conduction vibrator which comprises a shell and a passive elastic piece, the passive elastic piece is embedded in a groove hole formed in the shell, and the bottom of the passive elastic piece is fixedly connected with a passive magnet; when an audio signal passes through the voice coil, current is generated, the active elastic piece is driven to vibrate, the passive magnet and the active elastic piece resonate, the passive vibration system is of a passive structure and is not affected by power, and the resonant frequency Fo of the vibration system can be designed to be lower than that of a main vibration system, so that the low-frequency enhancement effect is achieved, and the HIFI-level mega bass effect is generated; the music experience of consumers is improved; through the active-passive dual-vibration system, the problem of balance of mega bass, power and low, medium and high frequencies of music is effectively solved, the active vibration system outputs medium-high frequency vibration signals, the passive system mainly outputs low-frequency vibration signals, output of broadband bone conduction audio signals is achieved, and the overall tone quality effect is improved.

1. Name of the product in this design: Bone conduction hearing aid. 2. Purpose of this design: To improve the user's hearing ability. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: 3D view 1.

The invention relates to the technical field of speech recognition and synthesis, and discloses a multi-mode speech conversion method and system based on user behaviors, and the method comprises the steps: carrying out the vibration separation of a bone conduction signal, obtaining a separation vibration signal, mapping the face muscle micro-current into a muscle deformation gradient, and analyzing the intention intensity of a user through implicit behavior data; mapping the muscle deformation gradient into a voice fundamental frequency of the user, linearly converting the separation vibration signal into a voice formant of the user, and performing noise injection on a non-voice active section based on intention intensity to obtain noise injection voice; constructing user behavior voice corresponding to the voice fundamental frequency, the voice formant and the noise injection voice through an orthogonal projection layer in a preset orthogonal regularization vocoder; and synthesizing the speech feature vector and the user behavior speech into bone conduction propagation speech through a bone conduction synthesis layer in an orthogonal regularization vocoder. According to the invention, the accuracy of the multi-mode voice conversion technology can be improved.

The invention discloses an intelligent exoskeleton bone auxiliary conduction hearing aid system capable of being remotely controlled and having an electroencephalogram control function, and relates to the technical field of intelligent rehabilitation robots and hearing aid devices. The wearable mechanical part comprises a flexible actuator, an elastic fabric base material, an inertial measurement unit IMU, a plantar pressure sensor array, a surface myoelectricity EMG sensor and an electroencephalogram EEG sensor. And the information processing communication part comprises a central controller, a bone conduction hearing aid module, a multi-mode sensor, an embedded SoC, a DSP / AI accelerator, a 4G / 5G / Wi-Fi module and a power management unit. The flexible exoskeleton walking aid system and the bone conduction hearing aid module are integrated, the electroencephalogram EEG sensor is additionally arranged to achieve the electroencephalogram control function, and cooperation of the three functions of movement assistance, auditory perception and neural intention recognition is achieved. A user can directly control the exoskeleton action mode through electroencephalogram signals, meanwhile, intelligent assistance of lower limb joints is obtained in the walking process, and environment sounds and voice prompts are clearly received in a bone conduction mode. According to the system, the perception ability, the control flexibility and the social participation degree of old people or rehabilitation patients who are inconvenient to move and accompanied with hearing impairment in a complex environment are remarkably improved, and more natural and convenient man-machine interaction experience is provided for users.

The invention relates to the technical field of audio signal processing, and discloses a microphone far-field pickup amplitude dynamic range control method, and the method comprises the steps: processing synchronous bone conduction and air conduction signals; respectively extracting feature vectors representing near-field interference and far-field human voice from the bone conduction signal and the air conduction signal; inputting the feature vector into an artificial intelligence decision engine, and carrying out collaborative analysis to generate a gain strategy considering interference suppression and human voice maintenance; and the gain of the air conduction signal is adjusted according to the strategy. The system comprises a signal preprocessing module, a first feature extraction module, a second feature extraction module, an artificial intelligence decision engine and a gain adjustment and reconstruction module. Unambiguous observation is carried out on near-field interference by using the bone conduction signal, the gain control problem when far-field weak human voice and near-field strong interference coexist is solved, and the pickup quality can be ensured while signal clipping can be effectively prevented.