专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US09837102B2 User environment aware acoustic noise reduction 有权
公开(公告)号：US09837102B2
公开(公告)日：2017-12-05
申请号：US14321813
申请日：2014-07-02
申请人： Syavosh Zad Issa , Youhong Lu , Rod G. Fleck , Hundraj S. Gopal
发明人： Syavosh Zad Issa , Youhong Lu , Rod G. Fleck , Hundraj S. Gopal
IPC分类号： G06F17/20 , G06F17/28 , G10L21/00 , G10L15/26 , G10L25/84 , H03G3/32 , G10L21/02 , G10L21/0216 , G10L25/51
CPC分类号： G10L25/84 , G10L21/02 , G10L21/0216 , G10L25/24 , G10L25/51 , H03G3/32
摘要： Examples of the disclosure describe user environment aware single channel acoustic noise reduction. A noisy signal received by a computing device is transformed and feature vectors of the received noisy signal are determined. The computing device accesses classification data corresponding to a plurality of user environments. The classification data for each user environment has associated therewith a noise model. A comparison is performed between the determined feature vectors and the accessed classification data to identify a current user environment. A noise level, a speech level, and a speech presence probability from the transformed noisy signal are estimated and the noise signal is reduced based on the estimates. The resulting signal is outputted as an enhanced signal with a reduced or eliminated noise signal.

2. 发明申请

US20160005422A1 USER ENVIRONMENT AWARE ACOUSTIC NOISE REDUCTION 有权
标题翻译：用户环境意识减少声音噪声
公开(公告)号：US20160005422A1
公开(公告)日：2016-01-07
申请号：US14321813
申请日：2014-07-02
申请人： Syavosh Zad Issa , Youhong Lu , Rod G. Fleck , Hundraj S. Gopal
发明人： Syavosh Zad Issa , Youhong Lu , Rod G. Fleck , Hundraj S. Gopal
IPC分类号： G10L25/84
CPC分类号： G10L25/84 , G10L21/02 , G10L21/0216 , G10L25/24 , G10L25/51 , H03G3/32
摘要： Examples of the disclosure describe user environment aware single channel acoustic noise reduction. A noisy signal received by a computing device is transformed and feature vectors of the received noisy signal are determined. The computing device accesses classification data corresponding to a plurality of user environments. The classification data for each user environment has associated therewith a noise model. A comparison is performed between the determined feature vectors and the accessed classification data to identify a current user environment. A noise level, a speech level, and a speech presence probability from the transformed noisy signal are estimated and the noise signal is reduced based on the estimates. The resulting signal is outputted as an enhanced signal with a reduced or eliminated noise signal.
摘要翻译：本公开的示例描述用户环境感知单声道噪声降低。由计算装置接收到的噪声信号被变换，并且确定接收到的噪声信号的特征向量。计算设备访问对应于多个用户环境的分类数据。每个用户环境的分类数据与噪声模型相关联。在所确定的特征向量和所访问的分类数据之间进行比较以识别当前用户环境。估计来自变换噪声信号的噪声电平，语音电平和语音存在概率，并且基于估计减小噪声信号。所得到的信号作为具有减少或消除的噪声信号的增强信号被输出。

3. 发明授权

US08184537B1 Method and apparatus for quantifying, predicting and monitoring the conversational quality 失效
标题翻译：量化，预测和监测会话质量的方法和装置
公开(公告)号：US08184537B1
公开(公告)日：2012-05-22
申请号：US11700698
申请日：2007-01-30
申请人： Hundraj S. Gopal , Mohammad Reza Zad-Issa , Keith T. Chu
发明人： Hundraj S. Gopal , Mohammad Reza Zad-Issa , Keith T. Chu
IPC分类号： H04L12/26 , H04L12/66
CPC分类号： H04M7/1205 , H04L43/0864 , H04L65/80 , H04M3/2236
摘要： There is provided a method of quantifying a voice quality in a telecommunication system including a first gateway in communication with a second gateway over a packet network. The method comprises deriving speech parameters from a first speech signal of a first talker received by the first gateway over a first communication line and a second speech signal of a second talker received by the first gateway from the second gateway over the packet network, determining a conversational impairment index using the speech parameters, deriving technology parameters based on voice technology and components in the telecommunication system, determining a technology impairment index using the technology parameters, and mapping the conversational impairment index and the technology impairment index into a conversational quality index to quantify the voice quality in the telecommunication system.
摘要翻译：提供了一种在电信系统中量化语音质量的方法，包括通过分组网络与第二网关通信的第一网关。该方法包括从第一通信网络通过第一通信线路接收的第一通话者的第一语音信号和由第一网关从第二网关通过分组网络接收的第二讲话者的第二语音信号，从分组网络导出语音参数，使用语音参数的对话性损伤指标，基于电话系统中的语音技术和组件的技术参数的导出，使用技术参数确定技术损害指数，并将会话性损耗指数和技术损害指数映射到对话质量指标中以量化电信系统中的语音质量。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式