61 results about "Sound localization" patented technology

The described aspects and implementations support sound-based emergency vehicle detection, localization, and tracking for autonomous vehicle and driver-assist systems. The techniques include obtaining, using one or more audio detectors of a vehicle, a sound recording that includes a sound emitted by an emergency vehicle (EV). The techniques further include applying a sound localization (SL) model to the sound recording to obtain a SL output, which includes a first map of possible locations of the EV in a driving environment of the vehicle and can further include a second map of possible velocities of the EV. The techniques further include simulating, using the SL output, trajectories of simulated EV(s) in the driving environment of the vehicle, and causing, responsive to proximity of the simulated trajectories to a driving path of the vehicle, modification of the driving path of the vehicle.

The invention relates to the field of gas leakage identification, and discloses a gas leakage identification method and system based on sound localization, a medium and equipment, and the method comprises the steps: collecting a leakage sound wave signal through a microphone array, and extracting acoustic features in a complex background; simulating a diffusion process of gas in a turbulence environment after gas leakage through an established leakage gas convection-diffusion model, and combining gas concentration distribution in the simulated diffusion process with acoustic characteristics to predict sound source localization at a leakage position; modeling a sound source localization search process as POMDP, and iteratively updating a confidence state of a sound source position through a particle filter; spatial distribution features are extracted from the confidence state through DBSCAN clustering to serve as input of the LSTM-DQN network, spatial and temporal features are fused through the constructed LSTM-DQN network, cross-scene generalization is achieved through transfer learning, and sound source coordinates are dynamically optimized and output through the Q network. According to the invention, the positioning accuracy and real-time performance in a complex environment are improved.

The invention provides an anti-collision driving assistance method based on multi-sensor fusion, electronic equipment and a readable storage medium, and relates to the technical field of automatic driving, and the method comprises the steps: obtaining point cloud data obtained by detecting surrounding obstacles through a laser radar of a current vehicle, and three-dimensional image data obtained by detecting the obstacles through a vehicle-mounted camera, the sound source data is acquired by the microphone array; determining image positioning information of an obstacle based on the three-dimensional image data; determining sound positioning information of the dangerous sound source based on the sound source data; performing data fusion on the point cloud data, the image positioning information and the sound positioning information to obtain environment sensing data of the obstacle; and finally, for any obstacle, according to the environment sensing data of the obstacle and the driving data of the current vehicle, judging whether a collision risk exists between the current vehicle and the obstacle or not. And an anti-collision auxiliary driving strategy is generated when the collision risk exists. According to the method, accurate monitoring of obstacles is realized through multi-sensor fusion, so that the accuracy of an anti-collision driving technology is improved.

A localized sound projection system can coordinate the sounds of speakers to simulate the placement of an auditory cue in a 3D space. The system can include a plurality of speakers configured to output auditory signals and a sound localization controller configured to control the plurality of speakers to coordinate the auditory signals to simulate an origination location of a patient alarm. The sound localization controller can determine adjusted auditory signals and control a plurality of speakers to output the plurality of adjusted auditory signals. A method for dynamically controlling speaker settings in a medical environment can include determining volume settings corresponding to a speaker, monitoring a level of ambient noise corresponding to a room of a patient, controlling the volume settings of the speaker to reduce or increase a sound level output of a speaker. A patient monitoring system can be configured to physically manipulate medical devices in response to audible commands. The system can receive a plurality of vocal commands from a user and can manipulate various settings after confirmation from a user.

The invention provides a fault recognition method based on sound localization and a related device, and by implementing the fault recognition method based on sound localization provided by the embodiment of the invention, an abnormal sound automation system can collect sound signals sent by test equipment in a design or test process, determine fault signals in the sound signals, and send out the fault signals to a test device. And finally, the fault type of the test equipment is determined based on the coordinate information feature information corresponding to the fault signal, so that the fault analysis period and cost of the test equipment can be reduced, and the accuracy of fault type identification can be improved.

According to an embodiment, an electronic device (101) comprises: a communication circuit (190); one or more processors (120) including processing circuitry; and a memory (130) including instructions, wherein the instructions, when executed by the one or more processors individually or collectively, may cause the electronic device to: in a first section, receive a signal of a first channel from a first external electronic device (202) and receive a signal of a second channel from a second external electronic device (204) through the communication circuit; identify that a packet loss has occurred in the first channel; identify whether inter-channel similarity of the first channel and the second channel is greater than a first threshold value on the basis of identifying that the packet loss has occurred in the first channel; and on the basis of identifying that the inter-channel similarity is greater than the first threshold value, restore the signal of the first channel received in the first section by applying sound localization between the first channel and the second channel to the signal of the second channel received in the first section. Other embodiments may be possible.

The invention relates to the technical field of desktop robots, and discloses a wheel type desktop accompanying robot, a control system and a control method of the wheel type desktop accompanying robot. Comprising a robot frame composed of a power supply trunk part, a moving part, limb parts and a head part, a camera module is embedded in the nose protrusion of the head part, a laser radar is installed in the forehead area of the head part, a sound positioning mainboard is installed behind the power supply trunk part, sound collection microphones distributed in an array mode are arranged on the sound positioning mainboard, and the sound collection microphones are connected with the power supply trunk part. The moving part comprises two moving wheels which are distributed triangularly and have collinear axes and a wheat wheel; according to the technical scheme, a multi-mode sensing fusion framework is constructed, visual, auditory and environment sensing data are integrated, real-time interaction and complementary verification are achieved through a communication framework, the problem that single-mode sensing is prone to being interfered by light, noise and shielding is solved, an upper main control board focuses on intelligent algorithm operation and decision logic output, and the real-time interaction and complementary verification are achieved. The lower-layer auxiliary control board is responsible for hardware driving and state feedback, and instruction execution synchronism is improved.

A audio system comprises an analysis unit, configured to receive and analyze a first number of audio signals, an ambient sound unit, configured to determine one or more ambient sounds related to the semantic information of the first number of audio signals obtained by the analysis unit, a sound placement unit, configured to determine a placement of the one or more ambient sounds determined by the ambient sound unit in one or more audio signals of the first number of audio signals, or in one or more processed audio signals of a second number of processed audio signals, and a combiner to combine the one or more ambient sounds with one or more audio signals of the first number of audio signals or with one or more processed audio signals of the second number of processed audio signals, to generate a second number of audio output signals.

The invention relates to the technical field of audio optimization of TWS Bluetooth earphones, in particular to a head posture assisted binaural balance adjustment method, which comprises the following steps: step 1, a head posture assisted TWS Bluetooth earphone calculates relative movement between a left ear and a right ear according to the head posture of a wearer; 2, establishing a binaural balance model considering a head posture factor, analyzing the influence of different head postures on binaural hearing, and quantifying the influence into corresponding hearing features; 3, the head posture auxiliary TWS Bluetooth headset evaluates the current double-ear listening effect, and main ears and auxiliary ears are determined according to the current environment and task requirements; 4, dynamically adjusting the main ear and the auxiliary ear to adapt to the current auditory demand; and 5, performing model verification based on the step 4, and adjusting and optimizing model parameters according to a model verification result, so that the method not only can improve the accuracy of sound positioning, but also can remarkably improve the auditory experience of the user in different environments.

The present application discloses an adaptive sound pickup method and system based on multi-source localization. The method includes: extracting features from the collected multi-source sound generation data to obtain a comprehensive feature vector set; inputting the comprehensive feature vector set into a preset sound source localization model for processing to obtain target sound source features; according to the target sound source features, obtaining the optimal sound pickup device parameters in the current environment through a preset sound pickup strategy prediction model; and setting the adjustable parameters of the sound pickup device according to the optimal sound pickup device parameters to perform sound pickup. The present application accurately locates the target sound source when multiple sound sources are generating sound simultaneously, and sets the relevant parameters of the sound pickup device according to the information of the target sound source, so as to achieve more accurate and rapid sound pickup.

An automatic speaker registration method and system, in which an image is captured by a camera, image data is generated, a face position of a person is identified from the image data, a microphone array is used for sound reception, voice data is generated, a sound source direction is estimated by using a sound localization technique, and then a target speaker is matched according to the face position of the person and the sound source direction. Especially, whether a target speaker is within an effective geometric range is confirmed, so that voice generated by the target speaker in the direction of the target speaker can be recorded, voice enhancement is performed, and speaker characteristics of the target speaker registered in a specific system are formed.

To support sound-based emergency vehicle detection, localization, and tracking for an autonomous vehicle and a driver-assist system.SOLUTION: Techniques of the present invention include obtaining, using one or more audio detectors of a vehicle, a sound recording that includes a sound emitted by an emergency vehicle (EV). The techniques further include applying a sound localization (SL) model to the sound recording to obtain an SL output, which includes a first map of possible locations of the EV in a driving environment of the vehicle and can further include a second map of possible velocities of the EV. The techniques further include simulating, using the SL output, trajectories of simulated EV(s) in the driving environment of the vehicle, and causing, responsive to proximity of the simulated trajectories to a driving path of the vehicle, modification of the driving path of the vehicle.SELECTED DRAWING: Figure 4

A conference speech presentation system, a sound localization method and apparatus, a conference system and a pickup device. The method includes the following steps: collecting (S101) a multi-channel voice signal through a directional microphone array; determining (S103) a steering vector including phase information and amplitude information according to array shape information and microphone pointing direction information; determining (S105) sound direction information according to the steering vector and the voice signal. By adopting this processing mode, both the phase information and the amplitude information are considered when determining the steering vector, which can effectively improve the accuracy of sound localization.

A vehicle system uses OEM sensors and OEM speakers to spatially convey, inside the cabin, the location and distance of real-world entities relative to a driver. A processor determines a directional bearing and, when available, a distance from proximity sensors, integrated cameras, or a directional microphone. An audio generation module produces a warning that is routed only to the speakers on the side that corresponds with the bearing, with audio gain set as a function of distance so closer entities sound louder. For emergency vehicles, the system synthesizes a siren or isolates and re-broadcasts the original siren, then plays the siren only through the speakers that correspond with the detected bearing. An interior microphone gates synthesis when the original siren is already audible. The approach enables drivers to localize pedestrians and other hazards by sound.

The present disclosure discloses a sound transducer including a substrate; a back plate mounted on the substrate; a back plate electrode mounted on a side of back plate facing the substrate, including a plurality of first electrode plates arranged at intervals; a diaphragm electrode opposite to the back plate along a first direction, including: a plurality of second electrode plates arranged at intervals; and a center pillar arranged between the back plate and the diaphragm electrode, extending along the first direction; the plurality of first electrode plates surrounds the center pillar; the plurality of second electrode plates surrounds the center pillar; each second electrode plate is flexibly connected to the center pillar. The sound transducer in the present disclosure has sound localization function.

An audio system and method of using the audio system to augment spatial audio rendition is described. The audio system can include a device to receive user inputs designating positions on an augmented reality view of a listening environment. Sound source icons can be presented in the augmented reality view at the designated positions. The sound source icons can visually represent sound sources at locations in the listening environment that correspond to, but are different than, the positions. One or more processors of the audio system can apply head-related transfer functions, which correspond to the locations in the listening environment, to audio input signals to generate binaural audio signals. The audio system can include a headset that uses the binaural audio signals to render spatialized audio localizing sounds to the locations in the listening environment. Other aspects are also described and claimed.

The application provides a sound image matching method and a system thereof. The method comprises: collecting participant audio of each seat by each microphone; setting the number of routers of each row according to the number of microphones of each row, the number of interfaces of each router is not less than the number of collection areas, and different interfaces of each router are connected to the microphones of different collection areas in the row where the router is located to route the participant audio collected by the microphones of different collection areas to an audio processor; selecting at least one collection area with participant audio output as a sound area according to a preset rule; processing all participant audio in each sound area by the audio processor to make each sound area correspond to one piece of processed audio, and obtaining multiple pieces of audio; and sending the multiple pieces of video and the multiple pieces of audio to a remote end. The application effectively realizes accurate matching of sound and image and provides an immersive audio and video experience for users.

Systems and methods for providing improved localization of recorded and played back sound are provided by improved microphone arrays for recording sound and by improved systems for playback of sound. Microphone arrays include four microphones with sound transducers located and aimed to mimic capture of sound by human ears. Sound captured by two side-viewing microphones is attenuated, at the time of sound capture and / or recording, at a later processing stage, or at the time of sound playback, by low-pass filtering. The recording maintains four separate channels of sound. Playback occurs through four speakers arranged to reproduce sound in the way human ears hear sound, with appropriate attenuation for side speakers. Playback can also occur through four-channel headphones. Improved playback of two-channel stereo sound can also occur through low-pass filtering of each track and playing the filtered sound through side / rear speakers on the opposite sides.

A sound image localization processing method includes inputting a sound source signal of a same sound source and localization information of the sound source to a first signal processing unit and a second signal processing unit; generating the first sound signal by subjecting the sound source signal to first localization processing based on the localization information and position information of the first speaker group to localize a sound of the sound source at a position indicated by the localization information; and generating the second signal by subjecting the sound source signal to second localization processing based on the localization information and position information of the second speaker group to localize the sound of the sound source at the position indicated by the localization information.

The invention provides a multichannel noise simulation system based on XAudio 2, and the system comprises an XAudio 2 engine initialization module which is used for initializing a COM assembly and creating an XAudio 2 engine instance; the main audio frequency sound mixer creating module is used for calling a CreateMasteringVoice method to create a main audio frequency sound mixer; the audio data loading module is used for reading an audio stream from an audio file and filling the audio stream into the XAUDIO2BUFFER structure; the source voice creating and playing module is used for calling a CreateSourceVoice method to create source voice, submitting the source voice to XAUDIO2BUFFER and starting playing; and the volume control module is used for independently adjusting the volume of each sound channel through a SetChannelVolumes function and muting other sound channels when the target sound channel is played. According to the invention, the accuracy of sound positioning and the user experience can be improved, and the system cost is reduced.

A sound image localization processing method includes inputting a sound source signal of a same sound source and localization information of the sound source to a first signal processing unit and a second signal processing unit; generating the first sound signal by subjecting the sound source signal to first localization processing based on the localization information and position information of the first speaker group to localize a sound of the sound source at a position indicated by the localization information; and generating the second signal by subjecting the sound source signal to second localization processing based on the localization information and position information of the second speaker group to localize the sound of the sound source at the position indicated by the localization information.

A method or apparatus switches between binaural sound and stereo sound in response to head movements of a listener. An electronic device provides the listener with binaural sound at a sound localization point (SLP) in a field-of-view of the listener. Binaural sound at the SLP switches to one of mono or stereo sound when head movements of the listener cause the SLP to move outside the field-of-view.

The invention discloses a three-dimensional sound event positioning and detection method based on audio guidance visual attention, and belongs to the field of audio-visual fusion positioning detection, and the method comprises the steps: extracting audio features of audio data through an audio encoder, and outputting the audio features to an audio guidance visual attention module; extracting visual features of the video data through a visual encoder and outputting the visual features to an audio-guided visual attention module; an audio-guided visual attention module guides visual features through audio features to obtain attention visual features, and an output branch serves as a visual sound positioning result to be output; the audio features and the attention visual features are fused through the fusion module, and the obtained multi-modal features are input into the context network to obtain a sound event detection result and a sound source coordinate estimation result which are output through the two output branches. The method effectively improves the positioning and detection performance of sound events in a three-dimensional space through an audio-guided visual attention mechanism and audio-visual fusion in combination with a sound source coordinate estimation branch.

A method and a system for automated speaker enrollment are provided. In the method, a camera is used to capture image data so that a facial position of a person can be recognized, a microphone array is used to generate speech data, and a sound localization technology is used to estimate a sound source direction. A target speaker can be determined by matching the facial position and the direction toward the sound source, and more particularly whether the target speaker is within a valid geometric range. After that, the speech produced by the target speaker along a target speaker direction is recorded, and the speech can be enhanced for generating speaker features with respect to the target speaker for enrolling to a specific system.

The present invention provides a sound positioning control method for a stereo headset, a stereo headset, and related equipment. The stereo headset includes a left-ear headset having a left-ear vibration motor and a right-ear headset having a right-ear vibration motor. The method includes: monitoring changes in a left-ear audio signal of the left-ear headset and a right-ear audio signal of the right-ear headset in real time; when the left-ear audio signal and / or the right-ear audio signal change, controlling the left-ear vibration motor of the left-ear headset and / or the right-ear vibration motor of the right-ear headset whose audio signal has changed to vibrate. In this way, the sound spatial positioning effect can be enhanced through the combination of hearing and touch, providing the user with a more immersive experience.

The present application relates to the technical field of LED display. Provided is a passive 3D LED display module with a sound-transmitting effect, comprising a support structure, an area matrix driving board, a mask layer, a polarizing layer and sound-transmitting channels, wherein the area matrix driving board is fixed to the support structure, and light-emitting diodes arranged in an array are provided on the side of the area matrix driving board away from the support structure; the mask layer is fixed on the side of the area matrix driving board away from the support structure; the polarizing layer is attached to the side of the mask layer away from the area matrix driving board; and the sound-transmitting channels sequentially pass through the support structure, the area matrix driving board, the mask layer and the polarizing layer. According to the technical solution provided in the embodiments of the present application, by means of the provision of the sound-transmitting channels that pass through the support structure, the area matrix driving board, the mask layer and the polarizing layer, a sound source perceived by a viewer comes from a display image. In this way, from the audiovisual perspective of the viewer, image and sound are in the same position, that is, the integration of image and sound positioning is achieved by means of the sound-transmitting channels, thereby improving the synchronization between sound and image, and thus improving the audiovisual effect of a playback device.

The utility model relates to the technical field of sound positioning, and discloses a sound positioning device based on a microphone array, which comprises a fixed shell, a power supply interface is fixedly arranged on the front side surface of the fixed shell, the power supply interface is electrically connected with a signal processing device, and the signal processing device is fixedly arranged on the inner surface of the fixed shell. And an array microphone is mounted at the upper end of the signal processing device. According to the sound positioning device based on the microphone array, the position of the adjusting plate is adjusted, so that the sound positioning device can be clamped and fixed on robots with different sizes without being fixed by screws, and the situation that the sound positioning device cannot be mounted and fixed due to the position deviation of holes formed in different robots can be effectively avoided; the sound positioning device is simple in structure and convenient to use, rapid and lossless disassembly and assembly can be achieved in a clamping and fixing mode, more convenience and rapidness are achieved, the sound positioning device can be clamped on robots with different shapes through rotation of the rotating plate, and the use range of the sound positioning device is widened.

The invention discloses a method and device for determining an unsteady state detection boundary of high-altitude unmanned detection equipment, and relates to the technical field of unmanned detection, and the method comprises the steps: obtaining a detection index of the detection equipment; the detection equipment comprises an overall deformation optical detection module, an abnormal heating and sound positioning module, a non-contact stress detection module and a paint layer surface crack detection module. A detection index is a performance limit which can be reached by detection equipment according to a 100% success rate under a static condition, namely, steady-state detection; the detection indexes comprise detection spacing, deformation detection resolution, minimum sound intensity, minimum heat source resolution, positioning precision, minimum stress resolution, paint layer thickness, minimum crack depth and minimum crack width; and determining an unsteady state detection boundary of the detection equipment based on the detection index of the detection equipment and the corresponding target detection accuracy. According to the invention, the motion index that the unmanned aerial vehicle should have when the specific detection equipment can reach a relatively high accuracy rate can be given.

The described aspects and implementations support sound-based emergency vehicle detection, localization, and tracking for autonomous vehicle and driver-assist systems. The techniques include obtaining, using one or more audio detectors of a vehicle, a sound recording that includes a sound emitted by an emergency vehicle (EV). The techniques further include applying a sound localization (SL) model to the sound recording to obtain a SL output, which includes a first map of possible locations of the EV in a driving environment of the vehicle and can further include a second map of possible velocities of the EV. The techniques further include simulating, using the SL output, trajectories of simulated EV(s) in the driving environment of the vehicle, and causing, responsive to proximity of the simulated trajectories to a driving path of the vehicle, modification of the driving path of the vehicle.

A method provides binaural sound to a listener while the listener watches a movie so sounds from the movie localize to a location of a character in the movie. Sound is convolved with head related transfer functions (HRTFs) of the listener, and the convolved sound is provided to the listener who wears a wearable electronic device.