31 results about "Vocal cues" patented technology

The invention provides a system for generating spatially explicit auditory cues for a recipient. It includes a processor to receive real-time location data of multiple physical entities relative to the recipient's spatial position and visual orientation. An audio generation module transforms this data into distinct audio signals using Head-Related Transfer Functions (HRTFs) to simulate perceived direction and distance. The output device, such as a headset or vehicle speakers, presents these audio signals spatially to allow perception of entities' relative locations. The system can adjust volume based on entity distance, integrate Doppler effects to indicate motion, and mute entities outside predefined distance boundaries. It also supports above-ground and ground assets, with altitude information converted to audible cues. The system monitors the recipient's orientation in real-time to adjust the HRTFs accordingly.

A method and a system for generating an explainable prediction of an emotion associated with a vocal sample are disclosed. The method includes receiving, by a processing device, a vector representation (z,) of an initial prediction (y0) of the emotion associated with the vocal sample (x), a counterfactual synthetic vocal sample (xY) associated with the vocal sample (x) and an alternate emotion (y) different from the initial prediction (y0) of the emotion, a vector representation (z,) of an emotion prediction (y0) associated with the counterfactual synthetic vocal sample (xy), vocal cue information (cy, cy) associated with the vocal sample (x) and the counterfactual synthetic vocal sample (xY) and attribution explanation information (iVc7) associated with relative importance of the vocal cue information (cy, cy) in prediction of the emotion. The method also includes determining, using the processing device, numeric cue differences (cyy) between the vocal cue information (cy) associated with the vocal sample (x) and the vocal cue information (cy) associated with the counterfactual synthetic vocal sample (xy), generating, using the processing device, cue difference relations information (r{circumflex over ( )}) based on the attribution explanation information (iv{circumflex over ( )}7), the numeric cue differences (cyy), the vector representation (z,) of the initial prediction (y0) and the vector representation (z,) of the emotion prediction (y0) associated with the counterfactual synthetic vocal sample (xY) using a first neural network (Mr), generating, using the processing device, a final prediction (y) of the emotion based on the numeric cue differences (cyy), the vector representation (z,) of the initial prediction (y0) and the vector representation (z,) of the emotion prediction (y0) associated with the counterfactual synthetic vocal sample (xY) using a second neural network (My), and generating, using the processing device, the explainable prediction of the emotion associated with the vocal sample (x) based on at least the counterfactual synthetic vocal sample (xY), the final prediction (y) of the emotion and the cue difference relations information (r{circumflex over ( )}).

The invention discloses a refrigerator prompt sound self-defining system and method.The refrigerator prompt sound self-defining system comprises an MCU microcontroller unit, an external Flash chip, a power amplifier and a loudspeaker, and a mobile phone APP conducts audio data transmission with the MCU microcontroller unit through a WiFi or Bluetooth module; the MCU microcontroller unit writes audio data into the external Flash chip through an SPI protocol, when the refrigerator needs voice prompt, the MCU microcontroller unit extracts the audio data in the external Flash chip, the audio data are generated into analog audio signals through a DMA controller and a DAC module in the MCU microcontroller unit, and the analog audio signals are sent to the external Flash chip through the MCU microcontroller unit. And the analog audio signal drives the loudspeaker to emit corresponding audio through the power amplifier. According to the method, the user can be allowed to customize sound prompts according to own preferences, using habits or specific requirements, so that the intelligent level, the user interaction experience and the function practicability of the product are improved.

The embodiment of the invention discloses a sound prompting method and device for fatigue of a driver of an environmental sanitation vehicle. A specific embodiment of the method comprises the following steps: acquiring a driver face image sequence and a vehicle control information sequence; performing eye detection on each driver face image in the driver face image sequence to obtain eye detection information; in response to the fact that the eye detection information meets a preset driver fatigue condition, generating a driver fatigue level identifier based on the vehicle control information sequence and the eye detection information; based on the driver fatigue level identifier, generating a corresponding driver fatigue prompt tone, and sending the fatigue prompt tone to an audio device for sound prompt, the driver fatigue prompt tone being a question prompt tone sent to the driver. According to the implementation mode, fatigue sound prompting can be more accurately carried out on the driver, and it is ensured that the sent prompting sound can achieve the sound prompting purpose.

The present application belongs to the technical field of vehicle state detection and early warning, in particular to a vehicle state monitoring and early warning method and system, the monitoring and early warning method is: a sensor acquires real-time data, an abnormality detection algorithm is applied, and an abnormal event is marked; according to the abnormal severity and driving scene, the information priority is calculated and distributed to a high priority queue; a multi-modal early warning is generated, high-frequency sound and vibration are used when driving at high speed; sound prompts are extracted, voice waveform data is generated through a voice synthesis module; driver voice input is recognized, intent is analyzed, and abnormal information feedback is provided; according to the scene and abnormal state, the interactive output is optimized, detailed information is displayed when driving at low speed in congestion; the dashboard interface is dynamically adjusted, the key area is enlarged when the abnormality is serious; image and voice data are integrated, multi-modal signals are generated, and after rendering processing, transmission is performed. The present application can timely and accurately transmit vehicle abnormal information to the driver, effectively improving driving safety.

Systems, processes and device configurations are provided for electronic gaming control and performance based sound generation for network games, such as multiplayer or cloud based games. Processes include determining one or more sound cues for a game data stream. By generating and outputting one or more sound cues on the fly, sound feedback may be provided to compliment gameplay and game experience. Sound cues can transform or modify audio elements of games for users and viewers of electronic gaming content. Generating sound cues may include replacing one or more assets of an electronic game, and capturing the user interaction with the modified content. Generating sound cues may include generating one or more sounds for a user, such as crowd cheers or boos, wherein the underlying game code and game content is not modified. Processes and configurations are also provided for determining sound assets of gaming content and tracking user performance.

A virtual world sound-prompting method, apparatus, device, and a storage medium, and belongs to the field of human-computer interaction. The method includes: displaying a visual screen of a first virtual character, the virtual screen displaying compass information comprising an azimuth scale sequence, and an azimuth scale in the azimuth scale sequence indicating a horizontal azimuth that the first virtual character faces in a virtual world. controlling the first virtual character to perform an action in the virtual world, and displaying a first sound indicator based on a first azimuth scale in the azimuth scale sequence based a first sound source located in surroundings of the first virtual character during the action of the first virtual character in the virtual world, the first sound indicator indicating a horizontal azimuth and a vertical azimuth corresponding to the first sound source.

This invention discloses a method, apparatus, device, and computer-readable storage medium for external sound alerts. The method is applied to a vehicle, with at least two microphones installed around the vehicle's exterior and at least two speakers installed inside. The method includes: acquiring ambient sound signals collected by each microphone; extracting a target sound signal from the ambient sound signals and locating the sound source direction of the target sound signal based on the at least two microphones; acquiring playback parameter values ​​for each speaker to simulate the sound source direction; and controlling each speaker to play the target sound signal according to its corresponding playback parameter values. This invention provides an external sound alert solution that, without affecting the vehicle's NVH performance, ensures that the driver can accurately identify external sounds, enabling timely countermeasures and elimination of safety hazards.

The utility model provides an intelligent safety helmet picking and placing rack which comprises a base, the top of the base is fixedly connected with a supporting frame, the inner wall of the supporting frame is fixedly connected with a storage rack, the top of the storage rack is provided with a storage groove, and the inner wall of the storage groove is movably connected with a safety helmet in a clamped mode. The bottom of the supporting frame is fixedly connected with an infrared human body induction module, and one side of the supporting frame is fixedly connected with a voice player. The infrared human body induction module induces passing of a human body, the voice player gives out a warning sound, prompts attention to wearing of the safety helmet, prompts outside personnel how to correctly wear the safety helmet in time and ensures that the personnel safely enter the field, and a second serial number on the taken safety helmet can be registered by scanning a registration two-dimensional code. And the name, the department and the job number of the worker can be taken, so that the safety helmet can be traced more conveniently when being lost.

The embodiment of the invention discloses a sound production device and a control method thereof. The sound production device comprises a main control module, a decoding control module, a sound storage module and a sound production module. Sound information is stored in the sound storage module, and the sound information comprises various kinds of prompt information. And the decoding control module is connected with the sound storage module, the main control module and the sound production module, and is used for determining corresponding prompt information according to the instruction information when receiving the instruction information sent by the main control module, and sending the prompt information to the sound production module, so that the sound production module carries out prompting according to the prompt information. Thus, various prompt messages are stored in the sound storage module at a time, the decoding control module directly calls the corresponding prompt messages in the sound storage module according to the instruction information, different prompt messages do not need to be repeatedly released and read, and therefore the real-time performance of sound prompt is improved.

The utility model relates to the technical field of direction guiding, and discloses a direction guiding device which comprises a road surface, blind road bricks are laid on the road surface, an installation box is fixedly installed on the road surface, a cover plate is installed on the installation box in a clamped mode, an indication assembly is arranged on the installation box, and the indication assembly comprises an installation frame. According to the direction guiding device, in order to enable the device to meet the direction guiding requirements of different crowds, the indicating assembly is arranged, after the assembly is matched with a worker to step on a small disc for a long time to enable a large disc to descend to trigger a button, a motor can drive the large disc to slowly rotate to adjust the indicating direction, and a sound prompt can be given out during rotation; the display in the arrow groove on the large disc can display direction information and provide visual guidance for normal people; meanwhile, the triggered sound box can give out sound indication to provide auditory guidance for the blind, and the direction guidance requirements of different crowds are met.

The application discloses a vibration prompt method and related equipment, and belongs to the technical field of terminals. The method comprises the following steps: in response to receiving a notification message, in the case that a sound prompt mode is a vibration mode, according to a current vibration type, a target vibration audio file corresponding to the vibration type is acquired, the target vibration audio file is determined based on a motor vibration waveform corresponding to the vibration type, a preset sampling rate and a target resonance frequency of a motor of the electronic equipment; the motor is controlled to vibrate, and the target vibration audio file is synchronously played. The application triggers the motor vibration and synchronously plays the acquired vibration audio file, so that the vibration effect is enhanced.

The utility model discloses a shaving pressure sound feedback assembly and a shaver. The shaving pressure sound feedback assembly comprises a shaver head; the trigger switch is used for outputting a trigger signal when it is determined that the shaver head abuts against the skin of the user during use; the control panel is used for acquiring a load current of a motor linked with the shaver head based on the trigger signal and outputting output information containing the load current; and the sound output unit is used for providing the output information of the load current determined by the control panel for the user, and the sound output unit has output information of a plurality of different volumes, frequencies or voices. The pressure value is fed back in a sound prompt mode, so that a user can conveniently obtain whether the current shaving pressure is under the condition of proper shaving pressure or not from different sound prompts when no observation condition is provided, and the shaving effect is better.

Embodiments disclosing an audio processing system for isolating and extracting a varying number of sound sources from an audio mixture are provided. The audio processing system includes a prompt input interface configured to produce a set of input digital encodings representing input sound prompts of at least some of the sound sources forming the audio mixture in a space of the features of the audio mixture. The set of input digital encodings includes a set of target digital encodings representing target sound prompts for extracting target sound sources from the audio mixture. An information exchanger neural network is trained to modify each of the set of target digital encodings and the features of the audio mixture. An extraction neural network is trained to extract a varying number of the target sound sources by processing the modified target digital encodings and the modified features of the audio mixture.

The present disclosure relates to a hearing aid hearing test and calibration system. An exemplary system includes: a hearing aid that amplifies sound and further plays the amplified sound; and a computing device that communicates with the hearing aid, and performs a fitting process responsive to a user's activation. The fitting process includes: setting a test frequency and a test amplitude; causing the hearing aid to play a sound at the test frequency and the test amplitude; prompting the user to respond as to whether the user is able to hear; and upon a positive or negative response from the user, causing the hearing aid to change the amplitude to calibrate.

Systems, computer program products, and methods are described herein for detecting artificial intelligence (AI) masking using persistent response testing. The present invention is configured to identify a vocal request; generate a primary prompt associated with the vocal request; receive, based on the primary prompt, a primary vocal cue data; determine at least one primary vocal characteristic based the primary vocal cue data; generate at least one secondary prompt associated with the vocal request for at least one second period; receive, based on the at least one secondary prompt, at least one secondary vocal cue data; determine at least one secondary vocal characteristic based on the one secondary vocal cue data; compare the at least one primary vocal characteristic to the at least one secondary vocal characteristic; and determine, based on the comparison, whether the vocal request is based on artificial intelligence (AI).

A medical device configured to provide a real-time audio feedback for use during administration of an emergency medical treatment of a patient by medical personnel is disclosed. The medical device may comprise a memory, and a processor coupled to the memory. The processor may be configured to perform operations. The operations may include analyzing measurement data collected from the patient. The operations may also include associating a particular audio font based on a characteristic of the measurement data. The operations may further include identifying, based on the characteristic of the measurement data, one or more clinically meaningful thresholds in the measurement data. The operations may also include generating an audible change in the particular audio font to reflect whether a particular characteristic of the measurement data has crossed a clinically meaningful threshold of the one or more clinically-meaningful thresholds.

The utility model relates to the technical field of metal detection, and discloses an underground metal detector, which comprises a handheld part and a detection disc, the handheld part and the detection disc are connected together by arranging a rod body, the bottom of the handheld part is connected with a loudspeaking assembly, the loudspeaking assembly comprises an outer shell, a circuit board is arranged in the outer shell, and the circuit board is connected with the handheld part. A controller and an audio output module are arranged on the circuit board, the controller is connected with the detection disc, and the audio output module is connected with the controller; the side wall of the outer shell is also provided with a loudspeaker; the loudspeaker is connected with the audio output module; according to the utility model, the loudspeaking assembly is arranged at the bottom of the hand-held part and is close to a user, so that the user can still hear related sound prompts even in a noisy environment, the phenomenon of missing detection is difficult to occur in detection work, and compared with the prior art, the utility model has the advantages of wide application place and stable detection capability.

The invention discloses an information prompting method and device, electronic equipment and a computer readable storage medium. According to the embodiment of the invention, a game picture corresponding to a controlled game role is displayed on a graphical user interface, and the game picture comprises at least part of a virtual scene; acquiring position information of a sound source in the virtual scene, wherein the sound source is a target game role in the virtual scene; on the basis of the position information, sound prompt information of the target game role is displayed, the sound prompt information is used for indicating the position of the target game role and role evaluation information, the time spent by a player for deciding actions of the player can be shortened, and the player experience is improved.

To provide a method and a system for enhancing speech in echo environment.SOLUTION: A method includes: a step for receiving or generating a sound sample 202 indicating a sound signal which an array 201 of a microphone receives during a prescribed time period; a step 203 for frequency-converting a sound sample for providing a sample whose frequency is converted; a step 204 for clustering the sample whose frequency is converted to a speaker based on a spatial cue related to the received sound signal and an acoustic cue related to the speaker for providing a speaker-related cluster; a step 205 for determining a relative transfer function for each speaker for providing a speaker-related relative transfer function; a step 206 for applying multiple input multiple output MIMO beam formation operation to the speaker-related relative transfer function for providing a beam-formed signal; and a step 207 for inverse-frequency-converting the beam-formed signal for providing a voice signal.SELECTED DRAWING: Figure 2

This utility model provides a controllable quantity ointment container that is not easily contaminated, relating to the field of container technology. It includes an upper cap, an inner cap, a bottle body, a piston, a screw, a screw sleeve, and a bottom cap. In this design, a well-sealed receiving cavity is formed between the bottle body, the inner cap, and the piston, preventing contamination of the ointment contents within the cavity. During use, the ointment is squeezed through an elongated hole onto the outer top surface of the inner cap, allowing the user to directly use the squeezed ointment without contacting the ointment in the receiving cavity, thus reducing the probability of contamination. During use, the bottom cap and the screw sleeve rotate relative to each other. When the positioning rib moves from one positioning notch to another, a tactile and auditory feedback is generated, indicating to the user that a measured amount has been reached. This allows for precise control of the amount of ointment used, providing users with convenience and comfort.

The invention relates to the technical field of auxiliary training devices, and discloses an auxiliary training device for music rhythm training, the auxiliary training device comprises a fixed mounting pad, the top of the fixed mounting pad is fixedly provided with a guide rail, the outer side of the guide rail is slidably connected with a metal sliding sleeve, and one side of the fixed mounting pad is fixedly provided with a protective shell; the device is provided with the rhythm flapping mechanism, the device attracts visual focuses through color changes and movement tracks while auditory stimulation is carried out, the exercise concentration duration of a user can be prolonged, part of visual learners replace traditional sound prompts through a light guiding module connected with the shell through light, and therefore the training effect is improved. Auxiliary training for music rhythm training is facilitated; the device is provided with a fine adjustment mechanism, the position of the mounting block is driven to be finely adjusted by impacting the connecting block, normal triggering and use of the impacting sounding block and the lamplight connecting shell are ensured, and normal proceeding of auxiliary training for music rhythm training can be ensured.

The utility model discloses a kind of elevator unbalance load detection and its voice rectification device, belong to elevator unbalance load detection technical field.This kind of elevator unbalance load detection and its voice rectification device include car and bottom plate, bottom plate is installed in car bottom, detection mechanism is installed in car inner chamber, detection mechanism includes bearing plate, weight sensor and loudspeaker, bearing plate is installed in car inner chamber, weight sensor is installed between bottom plate and bearing plate.The utility model is detected by setting detection mechanism, and the bearing plate is zoned by digital identification, and the weight distribution on the surface of bearing plate can be detected by four weight sensors, and weight data is transmitted to controller, controller analyzes data, and sets weight error, when the difference between each weight sensor is greater than weight error, it shows that there is unbalance load condition, sound is emitted by loudspeaker, personnel is prompted to move to the area where the weight sensor of small weight value is located, so as to realize the adjustment of unbalance load.

The invention provides an information display method and device in a game and electronic equipment, if the distance between a controlled virtual object and a target sound source in a game scene meets a preset condition, azimuth information and attribute information of the target sound source are determined, and the attribute information comprises at least one of the following information: a game event type corresponding to the sound source, and a game event type corresponding to the target sound source. The distance between the target sound source and the controlled virtual object is determined; determining a target orientation of the target sound source relative to the controlled virtual object based on the orientation information, and displaying a sound prompt identifier of the target sound source on the target orientation of the controlled virtual object based on the attribute information; and in response to the change of the position of the target sound source, updating the display mode of the sound prompt identifier of the target sound source. According to the method, the orientation information and the attribute information of the target sound source in the game scene are indicated through the sound prompt identifier, so that a player can accurately position the orientation and the attribute of the target sound source, the player can be helped to better acquire the sound information in the game, and the game experience of the player is improved.

Systems, processes and device configurations are provided for electronic gaming control and performance based sound generation for network games, such as multiplayer or cloud based games. Processed include determining one or more sound cues for a game data stream. By generating and outputting one or more sound cues on the fly, sound feedback may be provided to compliment gameplay and a game experience. Sound cues can transform or modify audio elements of games for users and viewers of electronic gaming content. Generating sound cues may include replacing one or more assets of an electronic game, and capturing the user interaction with the modified content. Generating sound cues may include generating one or more sounds for a user, such as crowd cheers or boos, wherein the underlying game code and game content is not modified. Processes and configurations are also provided for determining sound assets of gaming content and tracking user performance.

The present application discloses a method, device, equipment and storage medium for sound prompts in a virtual world, belonging to the field of human-computer interaction. The method includes: displaying a perspective screen of a first virtual character, on which compass information is displayed, and the compass information includes at least one azimuth scale; controlling the first virtual character to move in the virtual world; in the presence of a first sound source in the surrounding environment of the first virtual character, displaying a first sound indicator based on the first azimuth scale in the compass information, the first sound indicator being used to indicate the horizontal and vertical directions corresponding to the first sound source. The present application can use only the first sound indicator below at least one azimuth scale in the compass information to prompt sound, and can superimpose different visual expressions on the same sound indicator to indicate multiple sound information at the same time.

Embodiments disclosing an audio processing system for isolating and extracting a varying number of sound sources from an audio mixture are provided. The audio processing system includes a prompt input interface configured to produce a set of input digital encodings representing input sound prompts of at least some of the sound sources forming the audio mixture in a space of the features of the audio mixture. The set of input digital encodings includes a set of target digital encodings representing target sound prompts for extracting target sound sources from the audio mixture. An information exchanger neural network is trained to modify each of the set of target digital encodings and the features of the audio mixture. An extraction neural network is trained to extract a varying number of the target sound sources by processing the modified target digital encodings and the modified features of the audio mixture.

An oral care device and a control method thereof are provided. The oral care device includes a motor. The control method includes steps of obtaining target oral care information and determining a target driving signal based on the current oral care information, and controlling a motor of the oral care device to vibrate based on the target driving signal, so that the motor drives a care component of the oral care device to vibrate to generate sound prompting information. The target oral care information includes current oral care information of the oral care device. The sound prompting information is matched with the current oral care information. When a current oral care position or an attribute of the current oral care position changes, a loudness / volume of sound prompting vibrations generated by the motor driving the care component changes.