Harman International Industries, Inc.

Harman International (china) Holdings Co., Ltd.

Other

Guoxia Zhang

Qingshan Zhang

Zeng Yang

Jianjun Ma

Xiangru Bi

Zhilei Liu

Min Xu

Liangfu Chen

Youye Xie

Aspects disclosed herein generally relate to a method and a system for improving voice separation by eliminating overlaps or overlapping points. The time-frequency points from the two recorded mixtures are separated by using a Degenerate unmixing estimation technique (DUET) algorithm. The method or system further eliminates the overlapping time-frequency points which belongs to neither of the original resources of sounds.

Method and system to improve voice separation by eliminating overlap

An object tracking method and an object tracking system are provided. The method includes: obtaining a first relative position vector from a first node to a second node at a first time point; obtaining a first position data of the first node and a second position data of the second node at a second time point; identifying a position variation vector from the first node to the second node based on the first position data of the first node and the second position data of the second node; and identifying a second relative position vector from the first node to the second node at the second time point based on the first relative position vector and the position variation vector. The method improves the tracking accuracy.

Object tracking method and system

Aspects disclosed herein generally related to a method and system for efficient blind source separation using a topological approach. The method and system comprise locating and separating the audio streams by constructing and simplifying contour tree in a built time-frequency smooth weighted histogram in the subsystems included. Thus, in one example, the audio streams can be separated and reproduced in a faster, more reliability, higher quality and more robust way.

Efficient blind source separation using topological approach

An in-vehicle computing system and method that extracts driving intention data, driving capability data, and a driving mode data from one or more vehicle systems including an autonomous driving system. Autonomous driving information is derived from the extracted data. A message frame is created to include the autonomous driving information and sent to a V2X system.

V2X communication system with autonomous driving information

The present disclosure provides method and system for voice separation based on DUET algorithm, and the method comprises receiving signals from microphones; performing a Fourier transform on the received signals; calculating a relative attenuation parameter and a relative delay parameter for each data point; selecting a clustering range for the relative delay parameters based on a distance between the microphones and a sampling frequency of the microphones, clustering the data points within the clustering range for the relative delay parameters into subsets, and performing an inverse Fourier transform on each subsets. According to the present disclosure, it is possible to provide an efficient and intelligent solution to deploy DUET on the software and/or hardware.

Method and system for voice separation based on degenerate unmixing estimation technique

A method and a system for speech enhancement including a time synchronization unit configured to synchronize microphone signals sent from at least two microphones; a source separation unit configured to separate the synchronized microphone signals and output a separated speech signal, which corresponds to a speech source; and a noise reduction unit including a feature extraction unit configured to extract a speech feature of the separated speech signal and a neural network configured to receive the speech feature and output a clean speech feature.

Method and system for speech enhancement

Methods and devices for conducting, based on a clock difference, a synchronization process on voice information collected by a plurality of voice collection devices. Then, after the synchronization process is performed on the voice information collected by the plurality of voice collection devices, conducting a voice separation and recognition process on voice information that was collected by the plurality of voice collection devices and synchronized based on the clock difference among the plurality of voice collection devices.

Pre-voice separation/recognition synchronization of time-based voice collections based on device clockcycle differentials

A device for virtualizing a driving environment surrounding a first node, which includes: a data acquisition device, configured to acquire position data of the first node, position data and sensing data of at least one second node, where the at least one second node and the first node are in a first communication network; and a scene construction device, configured to construct a scene virtualizing the driving environment surrounding the first node based on the position data of the fist node and the at least one second node, and on the sensing data of the at least one second node. Accordingly, by utilizing position data and sensor data of a node, a scene for virtualizing a driving environment can be constructed in real time for a driver, which improves driving safety.

Device and method for virtualizing driving environment, and vehicle

A vehicle identification method and system are provided. The method includes: identifying a first vehicle to be a second vehicle based on a first group of data and a second group of data, the first group of data representing information of the first vehicle obtained through at least one sensor, and the second group of data representing information received from the second vehicle through an inter-vehicle communication network. By the method, an identity of the first vehicle in the inter-vehicle communication network can be known, the first group of data may be used to check the accuracy of the second group of data, and the second vehicle may be still tracked even if it is out of sight of the at least one sensor.

Vehicle identification method and system

A method for communicating messages in a channel of a wireless communication network is provided. In the channel, successive cycles, each of which including a predetermined number of successive time slots, are defined. The method may include: a first node obtaining a first list of its neighboring nodes before a first qtime slot; broadcasting a first message in the first qtime slot; receiving acknowledge information from other nodes within the network for one cycle after the first qtime slot; obtaining a second list of its neighboring nodes after the first qtime slot; and determining whether qtime slots are proper for communicating messages by the first node by checking whether all nodes on both the first and the second lists have received the first message based on the received acknowledge information, each piece of which indicates whether a corresponding node has received the first message.

Time slot selection in wireless communication

A method for extracting a message from a received signal frame is provided. The method includes: receiving a signal frame having N parts which are modulated with different power levels, where N is an integer equal to or greater than 2; demodulating and decoding the received signal frame to obtain N bit sequences which correspond to the N parts respectively; and forming a message based on the N bit sequences and a partition scheme according to which the message is partitioned into N message parts corresponding to the N bit sequences respectively.

Communication method and system

Method and system for soft decision decoding are provided. A soft decision decoding method implemented by a receiver in a communication network may include: receiving a signal frame carrying a message through a communication network; obtaining data structure of the message; obtaining at least one bit of the message based on the data structure and known information; and decoding the received signal frame based on the at least one bit using soft decision decoding to obtain a decoding result. Decoding efficiency and accuracy may be improved.

Soft decision decoding method and system thereof

One embodiment of the present disclosure sets forth a technique for enabling vehicular communication. The technique includes broadcasting, from a first communication device of a first vehicle and in a dedicated vehicular communication channel, a service advertisement message indicating that a service is available and can be provided through a temporary communication channel which is determined to be available. The technique further includes receiving from a second communication device of a second vehicle a request for the service in the dedicated vehicular communication channel. The technique further includes transmitting, in response to the request, content of the service in the temporary communication channel to the second communication device.

Vehicular communication method and system

A method and a system for communicating a high priority message in a vehicular ad hoc network is provided. In the communication channel, time slots are defined, and N successive time slots constitute one cycle, where m th time slot of each cycle is reserved for transmitting a pre-emption message. The method may include: selecting a sub-frame, transmitted in a first q th time slot, having a priority lower than that of the high priority message; transmitting in a first m th time slot after the first q th time slot a pre-emption message indicating that a second q th time slot, which is after the first m th time slot, will be occupied to transmit the high priority message; and transmitting in the second q th time slot the high priority message. By using the method and system, messages with higher priority can be transmitted timely even under very congested conditions.

Growing community of inventors

Shanghai, China

Guoxia Zhang