309 results about "Environmental sounds" patented technology

The invention relates to the technical field of artificial intelligence, and particularly provides a multi-modal information fusion emotion detection method based on visible light and voiceprint. The method comprises the following steps: respectively acquiring video images and environment sounds of old people in a monitoring environment through a visible light image module and an audio voiceprint acquisition module; a facial expression detection module is used for recognizing a human face in the video image, and a visual anomaly signal is output; recognizing an audio voiceprint signal in the environmental sound according to a voiceprint detection module, and outputting an audio abnormal signal; according to the method, the detection accuracy is effectively improved, the missing report is reduced, the method is suitable for home and old-age care institution environments, and the method is of great significance to guarantee the safety of old people and alleviate serious consequences caused by falling down.

A system and method to generate a video is provided. The method may include generating, based on a user input including a description of a desired video, a structured script including one or more of scene descriptions, dialogue, or explicit shot-level information. The method also includes generating, based on the structured script, a sequence of video frames representing one or more scenes. The method further includes generating, based on the structured script and the sequence of video frames, an audio track including one or more of ambient sounds, sound effects, or music. The generated audio track being temporally synchronized with the sequence of video frames. The method also includes combining the sequence of video frames with the audio track to generate a synchronized video output representing the desired video.

Various implementations include approaches for device control and / or sound source selection in audio devices. In some implementations, an audio device includes: an electro-acoustic transducer for providing an audio output; a set of microphones for detecting ambient sounds; and a processor coupled with the electro-acoustic transducer and the set of microphones, the processor configured to: evaluate microphone signals from the set of microphones to identify classes of sound sources in the ambient sounds; and adjust output of at least one class of the ambient sounds relative to another class of ambient sounds based on a user input.

The invention discloses a sound environment analysis and monitoring method based on artificial intelligence, and belongs to the field of artificial intelligence. Sound feature extraction and parameter analysis; converting sound into text; converting the sound event into a text description form by using a multi-mode big language model with a sound event analysis function and outputting text information; timestamps are added to the output text information, and the text information is classified, sorted, recorded and stored for a user to trace back; determining a key sound event by identifying a dialogue scene; after the key sound event is triggered, the device reminds the user according to a specific form. Any equipment does not need to be implanted, and postoperative risks and maintenance cost do not exist; a user can perceive environment sound and understand dialogue content without listening by himself or herself, and a hearing aid is not needed; sign language actions do not need to be captured through a camera, and the problem of dialect sign language recognition errors does not exist; the user does not need to stare at the character display device in real time during use, and the user is reminded in a specific mode after the key sound event is triggered.

The present disclosure provides for the division of environmental sounds from speech sounds to extract and analyze the behaviors and activities occurring in the environment; thus expanding and improving the functionality of AI assistant devices. These environmental sounds can be securely uploaded to an electronic chart, and may be used to aid in the treatment of existing conditions or the prophylaxis / mitigation of conditions not yet experienced by a patient under observation. Accordingly, the present disclosure provides for improved functionality in assistant devices and devices linked to the AI assistant devices.

The invention discloses an intelligent health monitoring alarm system, and the system comprises an environment behavior monitoring module which is used for collecting environment and behavior data related to daily activities of a user, and the environment and behavior data comprises water data, power data, gas data, image data, environment sound data and refrigerator door state change data; wherein the environment sound data particularly refers to a playing sound source signal which is acquired by an indoor microphone and is generated by a television or audio playing equipment; the data processing center is used for receiving and storing the environment and behavior data; and the user habit learning module is used for establishing and dynamically updating a personalized daily behavior baseline model of the user through a machine learning algorithm based on historical data. According to the invention, through multi-dimensional non-contact monitoring, the influence of contact equipment on the self-respect of the elderly can be avoided, and more comprehensive and intelligent health monitoring alarm of the elderly can be monitored at the same time.

A system and method to generate a video is provided. The method may include generating, based on a user input including a description of a desired video, a structured script including one or more of scene descriptions, dialogue, or explicit shot-level information. The method also includes generating, based on the structured script, a sequence of video frames representing one or more scenes. The method further includes generating, based on the structured script and the sequence of video frames, an audio track including one or more of ambient sounds, sound effects, or music. The generated audio track being temporally synchronized with the sequence of video frames. The method also includes combining the sequence of video frames with the audio track to generate a synchronized video output representing the desired video.

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 belongs to the technical field of intelligent breeding, and discloses an animal respiratory tract health detection method and system, and the method comprises the steps: carrying out the noise reduction preprocessing and marking of a sound segment of a target animal, and obtaining a respiratory tract abnormal sound segment and a respiratory tract health sound segment of the target animal; constructing a training set; an audio encoder large model based on a large-scale general audio data set and pre-trained through self-supervised learning is adopted, an output layer of audio classification is added, and an audio classification model used for recognizing the abnormal respiratory tract sound is constructed; when it is detected that the volume root mean square value of the collected continuous environment sound exceeds a preset threshold value, triggering and extracting a sound fragment with the time point as the center, marking the sound fragment as a target sound fragment, and inputting the target sound fragment into the trained audio classification model to obtain a classification result. According to the method, the dependence on the labeled data is remarkably reduced, the recognition accuracy and the model robustness are improved, and intelligent and automatic continuous monitoring and early warning are realized.

The present application provides a collision prompting method, which is suitable for a mobile device. The mobile device comprises an acceleration sensor, a sound sensor and a display screen. First, according to the acceleration data, it is determined whether the mobile device is in a falling state. After confirming that the mobile device is in the falling state, the ambient sound data is collected. Then, according to the acceleration data, it is determined whether the mobile device has a collision. After confirming that the mobile device has a collision, a preset time is calculated, and after the preset time, the collection of the ambient sound data is stopped. Next, according to the acceleration data and the collected ambient sound data, the severity of the collision of the mobile device is determined. Then, according to the severity of the collision, a prompt signal is generated. The present application also provides a collision prompting device.

The application provides a lighting device control circuit, a control method and a lighting device, which are applied to the technical field of intelligent traffic, the circuit is provided with a first light collection device and a sound collection device, light brightness is collected through the first light collection device, and environmental sound is collected through the sound collection device, in the case that the light brightness meets a first preset condition and the environmental sound meets a second preset condition, a second switch is controlled to be closed, so that a driving circuit of the lighting device is powered on and drives a light source in the lighting device to work, through the lighting device control circuit, the environmental light brightness and the environmental sound can be comprehensively considered, compared with the control mode of controlling the lighting device to work according to fixed time in the prior art, the application can more flexibly adapt to environmental changes, realizes the control of the lighting device according to the environmental changes, and further improves the lighting effect.

The system according to the embodiment aims to eliminate inconveniences in daily life caused by hearing impairments or hearing loss. According to an embodiment, the system includes a collection unit, an analysis unit, and a transmission unit. The collection unit collects ambient sound. The analysis unit analyzes the sound collected by the collection unit. The transmission unit transmits the sound analyzed by the analysis unit to the inner ear using bone conduction technology.

The application relates to an environment noise monitoring and event identification method, system and medium of a distributed acoustic sensing system, which comprises the following steps: obtaining real-time environment sound signals f(t) at different distances from the distributed acoustic sensing system; obtaining a frequency domain signal S in the sound signal through Fourier transform; extracting characteristic values corresponding to each event based on the frequency domain signal by adopting a dual-domain adaptive signal peak extraction method based on dynamic morphological coupling; classifying the sound signal characteristics through a convolutional neural network machine learning and determining the corresponding event; and reporting the noise determination result. The application can effectively process diversified noise types and realize real-time monitoring of key infrastructures.

The invention relates to the field of masks, and discloses a mask and a control method thereof, the mask comprises a mask body, a secondary sound source device and a voice signal acquisition part; the mask body comprises a mouth and nose wrapping structure and a mask shell, and the mouth and nose wrapping structure is connected with the mask shell; the voice signal acquisition part comprises a main microphone, and the main microphone is arranged on the inner side of the mouth and nose wrapping structure; the secondary sound source device is arranged on the outer side of the mask shell and works based on a control instruction. According to the mask, user sound or environmental noise is collected through the voice collecting part, the secondary sound source device sends out corresponding sound according to user requirements or conducts phase reversal processing on sound waves, and sound opposite to the user is sent out to achieve sound wave counteracting near the air outlet so as to achieve the purpose of active noise reduction; or scrambling signals such as white noise, environment sound and scene sound are generated, and user voice is hidden to the maximum extent; or the sound of the user is amplified, so that the sound is clearer and more stable.

A hearing protection device to be worn in ear provides communications of ambient sound to an in-ear speaker. Blast noise is detected and measured using either the in-ear speaker as a microphone or using a separate in-ear microphone.

This utility model provides a multi-scene adaptive intelligent light guide LED lamp, relating to the field of intelligent light guide LED lamp technology. It includes a mounting plate with a control mechanism on its outer side. The control mechanism includes two fixed brackets, one side of which is fixedly connected to the other side of the mounting plate. A human body sensor is fixedly connected to the bottom of one bracket, and a sound sensor is fixedly connected to the bottom of the other bracket. This multi-scene adaptive intelligent light guide LED lamp, with its human body sensor and sound sensor, effectively solves the problem of existing light guide LED lamps not being able to adaptively adjust to different scenarios. The human body sensor can detect the approach or departure of a person, and the sound sensor can react to ambient sound. Both sensors transmit the collected information to the controller. When human activity or a sound environment is detected, the controller can intelligently adjust the lamp according to a preset program.

The invention relates to a method (24) for operating a hearing aid (2) in which an input signal (16) is generated by means of a microphone (6) based on ambient sound (7). Based on the input signal (16), an output signal (18) is provided, and an output sound (22) is emitted by means of a receiver (10) based on the output signal (18). The unprocessed ambient sound (22) present in the vicinity of the receiver (10) is determined, and the ratio (36) between the unprocessed ambient sound (22) and the output sound (12) is determined for different frequency bands. The amplitude of the output signal (18) for the frequency band is varied, whereby the ratio (36) lies between an upper limit (38) and a lower limit (40). The invention further relates to a hearing aid (2).

An in-ear hearing protection device is provided. The in-ear hearing protection device includes a microphone (410) configured to receive environmental sound. The in-ear hearing protection device also includes a processor (420) configured to perform an attenuation function on the received environmental sound to provide an attenuated sound. The in-ear hearing protection device also includes a speaker (440) configured to play the attenuated sound. The in-ear hearing protection device also includes a communication module (430) configured to receive second attenuation function details from a second in-ear protection device. The processor is configured to calculate first attenuation function details and compare the first attenuation function details to the second attenuation function details. The attenuation function performed is based on one of the first attenuation function details and the second attenuation function details.

A sound data acquisition unit 110 acquires recording data obtained by recording environmental sound. A sound source separation unit 112 separates the recording data into environmental sound data and sound effect data. A first generation unit 116 generates an environmental sound file including the separated environmental sound data. A second generation unit 118 generates a sound effect file including the separated sound effect data.

The invention provides a noise elimination method and device, an electronic device and a computer medium, the noise elimination method is applied to the noise elimination device, and the method comprises the following steps: acquiring environmental data of a position where the noise elimination device is located, the environment data at least comprises environment sound and a face image of a person at the position within a preset range; performing image analysis on the face image, and detecting whether the person is in a negative emotion or not; if it is detected that the person is in the negative emotion, detecting whether noise appears in the environment sound; if detecting that the noise appears in the environment sound, processing the noise to obtain a noise signal and a noise direction; generating a noise reduction signal with the same amplitude and opposite phase as the noise signal; and playing the noise reduction signal to the noise direction. The noise reduction signal can be played to eliminate noise, and the noise is prevented from affecting life or work of people.

An earpiece, with two ambient sound microphones and an ear canal microphone detects whether the user is speaking and if so then detects an event, saving audio to memory.

The invention relates to the technical field of intelligent sound boxes, and discloses an audio playing control method and system for an intelligent sound box and a storage medium, and the audio playing control method comprises the steps: obtaining environment information and user information; performing environment state recognition based on the environment information; performing emotional state analysis based on the user information; according to the environment state and the emotional state, generating an audio playing control parameter; according to the audio playing control method and device, the audio playing parameters are adaptively adjusted through real-time environment sound analysis, the space sound field control technology is adopted, directional sound release is achieved, smooth transition of the audio parameters is achieved when the environment changes, the user experience is improved, and therefore the problem of environment noise interference is solved.

A hearing instrument includes a housing and at least one electroacoustic input transducer adapted to generate a corresponding electrical input signal from an ambient sound. The housing has a sound entry opening. A sound channel, which guides a sound path from the sound entry opening to the input transducer, is formed inside the housing. A contamination filter, which is transmissive for sound, at least partially covers a first cross section of the sound channel. The sound channel forms a sound chamber between the contamination filter and the sound entry opening, in such a way that the housing partially overlaps the sound chamber in the region of the sound entry opening.

The system according to the embodiment aims to ensure the safety of a user by analyzing surrounding sounds to detect danger and providing route guidance to a destination. [Solution] A system according to an embodiment includes a collection unit, an analysis unit, a warning unit, a reception unit, a calculation unit, and a guidance unit. The collection unit collects ambient sounds. The analysis unit analyzes the sounds collected by the collection unit. The warning unit detects danger and issues a warning based on the results of the analysis by the analysis unit. The reception unit accepts input of a destination. The calculation unit calculates the most suitable route based on the information accepted by the reception unit. The guidance unit provides route guidance based on the route calculated by the calculation unit.

The application discloses a method and device for unmanned aerial vehicle noise suppression and environmental noise identification based on double-task cooperative learning, relates to the technical field of environmental noise identification, solves the problems of serious environmental sound spectrum masking leading to low recognition rate under strong noise interference of an unmanned aerial vehicle, and cooperative failure caused by feature loss and gradient conflict between tasks in a traditional noise reduction-identification serial architecture, and the method comprises the following steps: constructing and training a double-task cooperative learning network, combining phased gradient isolation and task-aware gradient routing through a frequency domain unwinding network TaylorSENet based on Taylor series inspiration, a Doppler time-varying mask compensation mechanism and a branch convolution residual network BCResNet, so as to realize noise reduction and environmental noise identification of audio, suppress the unmanned aerial vehicle noise in the input audio, and at the same time, retain the time-frequency structure information of the environmental noise to the maximum extent, thereby greatly improving the overall classification accuracy.

The invention discloses a smart home control system based on Internet of Things, which belongs to the field of home control systems and comprises an Internet of Things sensor module, an edge computing gateway, a cloud analysis platform and an execution control module. The Internet of Things sensor module is deployed in a home environment, and comprises a plurality of high-definition cameras used for collecting pet dynamic video streams in real time; the microphone array is used for collecting environment sound signals; the millimeter wave radar sensor is used for detecting micro-motion characteristics of the life body; the infrared thermal imaging sensor is used for positioning the position of a living body; the environment sensor group comprises a temperature and humidity detection sensor, a door and window state detection sensor and a current detection sensor; and the edge computing gateway is connected with the Internet of Things sensor module and is used for preprocessing the video stream and the sound signal. According to the invention, life experience of pets at home can be effectively improved, and abnormity of the pets can be found in time and remedied.

In one possible example aspect, the present disclosure provides a context-aware noise compensation system for a wearable device playing back media content to a user in a noisy environment, wherein the system is configured to: obtain a sound signal from the noisy environment; determine context information associated with the sound signal, wherein the context information comprises at least one of: vocal sound detection information indicative of presence of one or more vocal sounds of the user in the sound signal, or sound event detection information indicative of presence of one or more environmental sound events in the sound signal; and optimize, based on the context information, the media content for playback by the wearable device.

The utility model provides a sound acquisition device and AR glasses. The sound acquisition device comprises at least one microphone; the at least one loudspeaker comprises a vibrating diaphragm, a coil and a magnetic piece; when the coil is electrified, the coil moves relative to the magnetic piece to enable the vibrating diaphragm to vibrate, and when the vibrating diaphragm vibrates, the coil moves relative to the magnetic piece to enable the coil to generate an induction electric signal; the control module is connected with the microphone and the loudspeaker, and the control module is used for obtaining a signal output by the microphone, obtaining an induction electric signal generated by the loudspeaker when the sound intensity of the sound intensity signal collected by the microphone corresponding to the environment sound is greater than or equal to a preset sound intensity threshold value, and sending the induction electric signal to the microphone; and converting the induction electric signal generated by the loudspeaker into the first sound data so as to improve the sound data acquisition effect of the sound acquisition device when the sound intensity of the environment sound is too high.

This application discloses an audio circuit and electronic device, relating to the field of electronic technology. The audio circuit includes a processor, a power amplifier, and a sound-emitting device. The processor's first communication terminal is connected to the power amplifier's communication terminal. The power amplifier's output terminal is connected to the sound-emitting device. The power amplifier's detection terminal is connected to the sound-emitting device. The sound-emitting device can be used to emit sound or to sense external ambient sounds. This audio circuit can utilize the sound-emitting device to sense external ambient sounds and obtain the ambient sound intensity, thus enabling applications in various scenarios to achieve functions such as noise detection, traffic accident detection, pedestrian fall detection, shaking detection, sound source localization, and fluctuating magnetic field detection.