Sz Dji Technology Co., Ltd.

Ubtech Robotics Corp Ltd

Jiebin Xie

Wei Ren

Guyue Zhou

Youjun Xiong

Yang Liu

Xiaoping Hong

Huai Huang

Dongyan Huang

Ruotong Wang

Zhichao Tang

Zhipeng Zhan

Weisi Ma

Cong Zhao

Bo Zang

Xian Li

Litian Zhang

Wan Ding

Zhiyuan Zhao

Shuhan Zhang

Bai Li

The present disclosure discloses a voice conversion method. The method includes: obtaining a to-be-converted voice, and extracting acoustic features of the to-be-converted voice; obtaining a source vector corresponding to the to-be-converted voice from a source vector pool, and selecting a target vector corresponding to the target voice from the target vector pool; obtaining acoustic features of the target voice output by the voice conversion model by using the acoustic features of the to-be-converted voice, the source vector corresponding to the to-be-converted voice, and the target vector corresponding to the target voice as an input of the voice conversion model; and obtaining the target voice by converting the acoustic features of the target voice using a vocoder. In addition, a voice conversion apparatus and a storage medium are also provided.

Method and apparatus for voice conversion and storage medium

A method of controlling a mobile platform includes measuring a distance between the mobile platform and an object when the mobile platform is located at each of a plurality of positions to obtain a plurality of measured distances each being obtained at one of the plurality of positions. Location information of the plurality of positions of the mobile platform is obtained by an inertial measurement unit (IMU) on the mobile platform. The at least two distance sensors being configured to capture data from different directions. The method further includes determining a position of the object based on the plurality of measured distances and the location information and controlling the mobile platform to avoid the object based on the results of the determined position of the object.

System and method for mobile platform operation

The present disclosure provides a streaming voice conversion method as well as an apparatus and a computer readable storage medium using the same. The method includes: obtaining to-be-converted voice data; partitioning the to-be-converted voice data in an order of data obtaining time as a plurality of to-be-converted partition voices, where the to-be-converted partition voice data carries a partition mark; performing a voice conversion on each of the to-be-converted partition voices to obtain a converted partition voice, where the converted partition voice carries a partition mark; performing a partition restoration on each of the converted partition voices to obtain a restored partition voice, where the restored partition voice carries a partition mark; and outputting each of the restored partition voices according to the partition mark carried by the restored partition voice. In this manner, the response time is shortened, and the conversion speed is improved.

Streaming voice conversion method and apparatus and computer readable storage medium using the same

A sensor system includes an optical aperture, a light source configured to generate a light pulse along a first optical path, a reflective surface configured to reflect the light pulse from the first optical path to a second optical path for passing through the optical aperture, a beam steering device positioned in the optical aperture and configured to steer the light pulse along different directions to one or more objects in an angle of view of the sensor system, a detector configured to receive a reflected light pulse and convert the reflected light pulse into an electrical signal, the reflected light pulse being reflected back from the one or more objects and passed through the beam steer device, and a spatial filtering device positioned between the beam steering device and the detector to block undesirable light in both the light pulse and the reflected light pulse.

LIDAR sensor system with small form factor

The present disclosure discloses a voice conversion training method. The method includes: forming a first training data set including a plurality of training voice data groups; selecting two of the training voice data groups from the first training data set to input into a voice conversion neural network for training; forming a second training data set including the first training data set and a first source speaker voice data group; inputting one of the training voice data groups selected from the first training data set and the first source speaker voice data group into the network for training; forming the third training data set including the second source speaker voice data group and the personalized voice data group that are parallel corpus with respect to each other; and inputting the second source speaker voice data group and the personalized voice data group into the network for training.

Voice conversion training method and server and computer readable storage medium

A detection apparatus includes an emission component, a receiver, and a controller electrically connected with the emission component and the receiver. The emission component includes an emitter configured to emit a signal, a reflector disposed in proximity to the emitter and configured to reflect the signal emitted by the emitter, and a driver connected to the reflector. The controller is configured to control the driver to drive the reflector to rotate.

Detection apparatus, detection system, detection method, and movable device

Example embodiments include a motion mechanism that can be coupled between the main body of an unmanned movable object and the optoelectronic scanning module. The motion mechanism can include, e.g., a spinning device and a tilting device. The spinning device can be operable to rotate the scanning module relative to the main body about a spin axis. The tilting device can be operable, e.g., in response to a tilt angle input, to rotate the scanning module about an additional axis that is transverse to the spin axis. Further example embodiments include an orientation sensor installed on the main body of the unmanned movable object. Some embodiments also provide a controller that is configured to receive an orientation signal from the orientation sensor and, based at least in part on the orientation signal, determine a tilt value for the tilt angle input for the tilting device in the motion mechanism.

Laser radar scanning and positioning mechanisms for UAVs and other objects, and associated systems and methods

An apparatus includes a light source configured to emit light, a beam shaper configured to project the light to substantially surround the apparatus in a plane and onto an object in the plane, and a receiver configured to project the light reflected from the object in the plane to an image sensor. A distortion parameter of the receiver in conjunction with a difference between the emitted light and the reflected light detected at the image sensor is indicative of at least one of a direction or a distance of the apparatus relative to the object.

Circular light source for obstacle detection

A method of controlling a mobile platform includes measuring a distance between the mobile platform and an object at each of a plurality of positions of the mobile platform, and determining a position of the object based on results of measuring the distance.

A system for detecting objects using ultrasonic waves and methods for making and using the same are provided. The object detection system uniquely encodes each of a plurality of ultrasonic waves and transmit each of the uniquely-encoded ultrasonic waves in a respective direction. The object detection system then receives any of the emitted uniquely-encoded ultrasonic waves that are reflected from an object. By decoding the reflected ultrasonic waves, the object detection system distinguishes among the uniquely-encoded ultrasonic waves and detect the existence and location of the object.

System and method for detecting an object

A sensor system can comprise a light source generating a light pulse that is collimated, and a plurality of optical elements. Each of the plurality of optical elements is configured to rotate independently about an axis that is substantially common, and the plurality of optical elements operate to collectively direct the light pulse to one or more objects in an angle of view of the sensor system. Furthermore, the sensor system can comprise a detector configured to receive, via the plurality of optical elements, at least a portion of photon energy of the light pulse that is reflected back from the one or more objects in the angle of view of the sensor system, and convert the received photon energy into at least one electrical signal.

A system for determining a signal source position and velocity, and methods for manufacturing and using same are provided. An exemplary method includes determining a signal source position and velocity by performing a direction analysis on a plurality of audio signals and performing an intensity analysis on the audio signals. Another exemplary method includes determining that a signal source is on a collision course with a moving platform and providing an instruction for altering the course of the moving platform to avoid a collision with the signal source. An exemplary system includes an acoustic sensing system, having a primary microphone array, a secondary microphone, and a processing device for determining a signal source position and velocity by performing a direction analysis on a plurality of audio signals and performing an intensity analysis on the audio signals.

System and method for detecting aerial vehicle position and velocity via sound

A system for using ultrasound to detect distance on mobile platform and methods for making and using same. The system includes an ultrasound transceiver that can transmit and/or receive ultrasound waves and determine distance from an object of interest using a time-of-flight of the ultrasound wave. The system is adapted to reduce noise by using a dynamic model of the mobile platform to set constraints on the possible location of a received ultrasound echo. A linear, constant-speed dynamic model can be used to set constraints. The system can further reduce noise by packetizing a received ultrasound waveform and filtering out noise according to height and width of the packets. The system likewise can remove dead zones in the ultrasound transceiver by subtracting an aftershock waveform from the received waveform. The systems and methods are suitable for ultrasound distance detection on any type of mobile platform, including unmanned aerial vehicles.

System and method for ultrasound distance detection

Lidar sensor system with small form factor

RGB-D imaging system having an ultrasonic array fin generating images that include depth data, and methods fin manufacturing and using same. The RGB-D imaging system includes an ultrasonic sensor array positioned on a housing that includes an ultrasonic emitter and a plurality of ultrasonic sensors. The RGB-D imaging system also includes an RGB camera assembly positioned on the housing in a parallel plane with, and operably connected to, the ultrasonic sensor. The RGB-D imaging system thereby provides/enables improved imaging in a wide variety of lighting conditions compared to conventional systems.

Growing community of inventors

Shenzhen, China

Jiebin Xie