公开(公告)号：US20170126568A1

公开(公告)日：2017-05-04

申请号：US15227583

申请日：2016-08-03

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Yong Ju LEE ,  Ok Gee MIN

IPC: H04L12/801 ,  H04L12/26 ,  H04L29/08

CPC classification number: H04L47/12 ,  H04L43/0817 ,  H04L43/0882 ,  H04L67/12 ,  H04L67/303

Abstract: Provided is an edge-based load shedding system. The edge-based load shedding system includes an analysis server configured to determine to perform server or edge separation execution, transmit an operational module of an analysis application, issue a request to offload the transmitted operational module, and receive and analyze data obtained through preprocessing and an edge machine configured to receive and offload the operational module from the analysis server, preprocess raw data collected from a sensor by using the offloaded operational module, and transmit the data obtained through the preprocessing to the analysis server.

公开(公告)号：US20160351201A1

公开(公告)日：2016-12-01

申请号：US15230616

申请日：2016-08-08

Applicant: Electronics and Telecommunications Research Institute

Inventor： Yong Ju LEE ,  Tae Jin LEE ,  Kyeong Ok KANG ,  Jin Woong KIM ,  Chie Teuk AHN

IPC: G10L19/16 ,  H04H20/89 ,  H04H20/95 ,  G10L19/008 ,  G10L19/20

CPC classification number: G10L19/167 ,  G10L19/008 ,  G10L19/20 ,  H04H20/89 ,  H04H20/95 ,  H04N21/2335 ,  H04N21/4394 ,  H04N21/8106

Abstract: A broadcast transmitting apparatus and method, and a broadcast playback apparatus and method for providing an object-based audio by encoding and decoding a multichannel audio signal are provided. The broadcast transmitting apparatus may generate audio identification information used to determine whether the multichannel audio signal is an object-based audio signal. When the multichannel audio signal is determined to be the object-based audio signal, based on the audio identification information, the broadcast playback apparatus may control and output the multichannel audio signal for each channel.

Abstract translation: 提供广播发送装置和方法以及通过对多声道音频信号进行编码和解码来提供基于对象的音频的广播回放装置和方法。 广播发送装置可以生成用于确定多声道音频信号是否是基于对象的音频信号的音频识别信息。 当多声道音频信号被确定为基于对象的音频信号时，基于音频识别信息，广播回放设备可以控制和输出每个频道的多声道音频信号。

公开(公告)号：US20160247502A1

公开(公告)日：2016-08-25

申请号：US14817292

申请日：2015-08-04

Applicant: Electronics and Telecommunications Research Institute

Inventor： Tae Jin PARK ,  Yong Ju LEE ,  Seung Kwon BEACK ,  Jong Mo SUNG ,  Tae Jin LEE ,  Jin Soo CHOI

IPC: G10L15/20 ,  G10L15/22 ,  G10L21/0232

CPC classification number: G10L15/20 ,  G10L15/06 ,  G10L15/22 ,  G10L25/03

Abstract: Provided is an audio signal processing apparatus and method that may convert a speech and audio signal to a spectrogram image, calculate a local gradient using a mask matrix from the spectrogram image, divide the local gradient into blocks of a preset size, generate a weighted histogram for each block, generate an audio feature vector by connecting weighted histograms of the blocks, generate a feature set by performing a discrete cosine transform (DCT) on a feature set of the audio feature vector, and generate an optimized feature set by eliminating an unnecessary region from the transformed feature set and reducing a size of the transformed feature set.

Abstract translation: 提供了一种音频信号处理装置和方法，其可以将语音和音频信号转换为频谱图，使用来自频谱图的掩码矩阵计算局部梯度，将局部梯度划分成预设大小的块，生成加权直方图 对于每个块，通过连接块的加权直方图来生成音频特征向量，通过在音频特征向量的特征集上执行离散余弦变换（DCT）生成特征集，并通过消除不必要的 区域，并减小变换后的特征集的大小。