10 results about "Bone conduction" patented technology

The disclosure provides an earphone comprising: a housing assembly, a bone-conduction speaker, and an air-conduction speaker, the housing assembly including a first housing, a second housing, and a third housing, wherein the second housing is engaged with the first housing, the second housing and the first housing cooperate with each other to form a first accommodation cavity, the third housing is engaged with the first housing and the second housing, respectively, the third housing and the first housing cooperate with each other to form a second accommodation cavity; an air-conduction speaker disposed within the first accommodation cavity; and a bone-conduction speaker disposed within the second accommodation cavity, wherein the third housing is provided to contact a user's face in a wearing state, and an engagement seam between the third housing and the second housing does not contact the user's face.

Provided are a speaker assembly and an earphone. The speaker assembly includes a housing assembly, a bone-conduction speaker, and an air-conduction speaker. The housing assembly is provided with a first accommodating cavity, a second accommodating cavity, and a communication hole connecting the first accommodating cavity and the second accommodating cavity. The bone-conduction speaker is disposed in the first accommodating cavity and blocks the communication hole to isolate the first accommodating cavity from the second accommodating cavity. The air-conduction speaker is disposed in the second accommodating cavity. The present disclosure can simply and effectively enlarge a volume of an acoustic cavity formed in an internal space of the speaker assembly, thereby improving the sound quality effect of the speaker assembly.

The application discloses a multi-target optimization AI traffic signal control method and system, and relates to the field of intelligent traffic systems.The method comprises the following steps: establishing a traffic signal control model, wherein the model comprises multiple optimization targets, and each optimization target is configured with an initial weight; setting a bone conduction sensor network in a traffic signal control area to obtain real-time motion information of blind users; detecting whether there is a visually impaired person; if there is a visually impaired person, adjusting the initial weight of each optimization target to obtain a dynamically adjusted weight; running the traffic signal control model according to the dynamically adjusted weight to generate a traffic signal control instruction; and controlling the display state of a traffic signal lamp according to the traffic signal control instruction, and simultaneously starting a variable sound and light guiding system to guide the visually impaired person to pass through an intersection.The application solves the technical problem that the existing multi-target optimization AI traffic signal control cannot meet the travel demand of visually impaired persons, and achieves the technical effect of meeting the travel demand of visually impaired persons.

The application discloses a quality inspection task scheduling method, relates to the technical field of bone conduction quality inspection, and aims to solve the problem that the existing scheduling algorithm is insufficient. The method comprises the following steps: S1, initializing model training parameters, wherein the model is a reinforcement learning model; S2, constructing a scheduling state feature; S3, outputting a corresponding action according to a current scheduling state, and decoding the scheduling state to obtain a sample and equipment corresponding to the action; S4, calculating a reward value and updating the training parameters; S5, judging whether a scheduling task is completed: when the scheduling task is completed and a training step number is reached, the training is ended, otherwise, returning to step S2; when the scheduling task is not completed, entering a next scheduling state and returning to step S2. The application further discloses a quality inspection task scheduling electronic device and a computer storage medium. The application is modeled based on reinforcement learning, and a good scheduling model is obtained.

The present disclosure relates to a vibration transmission plate, a loudspeaker assembly, and a bone-conduction earphone. The vibration transmission plate includes an inner ring body, an outer ring body, a first connecting rod, and a second connecting rod. The inner ring body includes a first inner ring edge including two first straight line segments and two first curved segments. The outer ring body includes a first outer ring edge including two second straight line segments and two second curved segments. The first connecting rod includes a first inner connecting portion, a first outer connecting portion, and a straight extending portion located within a straight gap. The second connecting rod includes a second inner connecting portion, a second outer connecting portion, and a curved extending portion located within a curved gap.

The invention relates to a bone-conduction hearing implant (100) comprising a subcutaneous implantable module (110) comprising a permanent magnet (111), a first near-field electromagnetic induction antenna (112), and a first transducer (113). In one particular embodiment, the module has a magnetized one-piece body. The permanent magnet (111) and the first transducer (113) define, respectively, a first surface SDC1 of contact and a second surface SDC2 of contact with the temporal bone OT. The module is positioned in a subperiosteal space ESP, the natural tension of the periosteum maintaining the elements without invasive anchoring. The implant interacts with a sound processor (200) and a microphone, both of which are configurable externally or internally. There are two modes of operation: internal transduction via the first transducer (113) using bone-conduction ultrasound technology and SDC2, and external transduction via the permanent magnet (111) and SDC1. A detection system (114) monitors the first transducer and ensures automatic switching. This non-invasive approach provides a scalable solution for different types of hearing loss.

A method includes receiving, as input to an initial block of a stack of self-attention blocks of a speech enhancement model, an input concatenating short-time Fourier transform (STFT) coefficients for a single channel noisy input signal and upscaled STFT coefficients of a bone conducted signal (BCS) recorded by an accelerometer. The method includes generating, using a final block of the stack of self-attention blocks, an un-masked output based on the input concatenating STFT coefficients for the single channel noisy input signal. The method includes generating, using a masking layer, a masked single channel noisy input signal based on the un-masked output. The method includes generating, using an inverse STFT layer, enhanced input speech features corresponding to a target utterance based on the STFT coefficients for the single channel noisy input signal and the masked single channel noisy input signal.

The invention discloses a vehicle-mounted multi-screen independent audio system and method based on a directional sound field and multi-mode conduction, and relates to the technical field of new energy automobile intelligent cabins. In-vehicle audio source signals and corresponding position labels are acquired through a signal acquisition module; the intelligent sensing module obtains information about whether the seat is a passenger or not and the type of the passenger; the audio distribution controller module processes the information according to a preset rule and generates an output instruction; the multimode audio output module receives an output instruction and activates a corresponding output module, and the output module comprises a loudspeaker module, a bone conduction module and a tactile feedback module; and when the output instruction meets the deaf person activation mode, the tactile feedback module is automatically activated. According to the invention, the entertainment requirements of passengers are met, the audios do not interfere with each other, the media content perception requirements of deaf passengers are met, and the riding experience of the passengers is integrally improved.

The present disclosure provides an acoustic output apparatus. The acoustic output apparatus may include a bone-conduction acoustic assembly, an air-conduction acoustic assembly, and a housing. The bone-conduction acoustic assembly may be configured to generate bone-conduction sound waves. The air-conduction acoustic assembly may be configured to generate air-conduction sound waves. The housing may include an accommodating chamber configured to accommodate the bone-conduction acoustic assembly and the air-conduction acoustic assembly. At least a portion of the housing may be in contact with a user's skin to transmit the bone-conduction sound waves under an action of the bone-conduction acoustic assembly. The air-conduction sound waves may be generated based on vibrations of at least one of the housing or the bone-conduction acoustic assembly when the bone-conduction sound waves are generated.

Provided are a bone-conduction speaker and an earphone. The bone-conduction speaker includes a cylindrical housing, a driving assembly, and two sealing plates. The cylindrical housing is enclosed an accommodating space. The driving assembly is disposed within the accommodating space and connected with the cylindrical housing. The sealing plates are respectively disposed at two ends of the cylindrical housing and block the accommodating space. In this way, the present disclosure is configured to limit the driving assembly in the bone-conduction speaker, improve the sound quality of the bone-conduction speaker, and increase the service life of the bone-conduction speaker.