Systems and methods for own voice recognition with adaptations for noise robustness
    1.
    发明授权
    Systems and methods for own voice recognition with adaptations for noise robustness 有权
    用于自身语音识别的系统和方法,适应噪声鲁棒性

    公开(公告)号:US08462969B2

    公开(公告)日:2013-06-11

    申请号:US13089738

    申请日:2011-04-19

    IPC分类号: H04R25/00 G10L17/00 G10L21/02

    摘要: Own voice recognition (OVR) for hearing aids, detects time instances where the person wearing the device is speaking. Classification of the own voice is performed dependent on a fixed or adaptive detection threshold. Automatic tuning in a real-time system depends on general noise statistics in the input signals. The noise is removed from the received signal and is characterized by signal-to-noise ratio and noise color. An optimal detection threshold for own voice recognition is determined based on the noise characteristics. A noise detection model is created by smoothed Voronoi tessellation. Own voice detection is performed by a processor.

    摘要翻译: 自己的语音识别(OVR)用于助听器,可以检测穿戴设备的人在说话的时间。 根据固定或自适应检测阈值执行自身语音的分类。 实时系统中的自动调谐取​​决于输入信号中的一般噪声统计。 噪声从接收信号中去除,其特征在于信噪比和噪声颜色。 基于噪声特性确定自身语音识别的最佳检测阈值。 噪声检测模型通过平滑的Voronoi镶嵌创建。 自己的语音检测由处理器执行。

    SYSTEMS AND METHODS FOR OWN VOICE RECOGNITION WITH ADAPTATIONS FOR NOISE ROBUSTNESS
    2.
    发明申请
    SYSTEMS AND METHODS FOR OWN VOICE RECOGNITION WITH ADAPTATIONS FOR NOISE ROBUSTNESS 有权
    用于噪声语音识别的噪声识别系统和方法

    公开(公告)号:US20110261983A1

    公开(公告)日:2011-10-27

    申请号:US13089738

    申请日:2011-04-19

    IPC分类号: H04R25/00

    摘要: Own voice recognition (OVR) for hearing aids, detects time instances where the person wearing the device is speaking. Classification of the own voice is performed dependent on a fixed or adaptive detection threshold. Automatic tuning in a real-time system depends on general noise statistics in the input signals. The noise is removed from the received signal and is characterized by signal-to-noise ratio and noise color. An optimal detection threshold for own voice recognition is determined based on the noise characteristics. A noise detection model is created by smoothed Voronoi tessellation. Own voice detection is performed by a processor.

    摘要翻译: 自己的语音识别(OVR)用于助听器,可以检测穿戴设备的人在说话的时间。 根据固定或自适应检测阈值执行自身语音的分类。 实时系统中的自动调谐取​​决于输入信号中的一般噪声统计。 噪声从接收信号中去除,其特征在于信噪比和噪声颜色。 基于噪声特性确定自身语音识别的最佳检测阈值。 噪声检测模型通过平滑的Voronoi镶嵌创建。 自己的语音检测由处理器执行。

    Network Element Consolidation for Rapid Discrete Network Simulations
    6.
    发明申请
    Network Element Consolidation for Rapid Discrete Network Simulations 有权
    快速离散网络仿真网络元素整合

    公开(公告)号:US20130060552A1

    公开(公告)日:2013-03-07

    申请号:US13569505

    申请日:2012-08-08

    IPC分类号: G06G7/63

    摘要: Systems and methods are provided for modeling and simulating a communication network operating under at least one communication protocol, which supports a Smart Grid electricity network. Communication performance data of the communication network are generated by a processor based on operating behavior of the Smart Grid with a plurality of assets under a first condition. Devices in the Smart grid are grouped in bins for rapid modeling. One or more different configurations of the communication network are entered into the processor and related performance data is also generated. Network configurations are compared based on the generated performance data which may include end-to-end delay and reception rate. Processor based systems to perform modeling methods are also provided.

    摘要翻译: 提供了系统和方法,用于建模和模拟在支持智能电网电力网络的至少一个通信协议下运行的通信网络。 通信网络的通信性能数据由处理器基于在第一条件下具有多个资产的智能电网的操作行为来生成。 智能电网中的设备分组在箱中进行快速建模。 通信网络的一个或多个不同配置被输入到处理器中,并且还产生相关的性能数据。 基于生成的可能包括端到端延迟和接收速率的性能数据来比较网络配置。 还提供了基于处理器的系统来执行建模方法。

    System and method for distributed cross-leyer congestion control for real-time video over wireless LAN
    7.
    发明授权
    System and method for distributed cross-leyer congestion control for real-time video over wireless LAN 失效
    用于通过无线局域网实时视频分布式跨线程拥塞控制的系统和方法

    公开(公告)号:US07916659B2

    公开(公告)日:2011-03-29

    申请号:US12252580

    申请日:2008-10-16

    IPC分类号: H04L12/26

    摘要: A method for controlling congestion for real-time video transmission in a wireless network includes receiving a packet loss rate of a video camera in a wireless network, receiving an estimated maximum throughput of the video camera from the camera to a server, decrementing a bit transmission rate when the packet loss rate is greater than a first predetermined threshold, incrementing the bit transmission rate when the packet loss rate is less than a second predetermined threshold for a predetermined time period, and transmitting the bit transmission rate to a video encoder that is part of an application layer of a network communication protocol for the wireless network.

    摘要翻译: 一种用于控制无线网络中的实时视频传输的拥塞的方法包括:在无线网络中接收视频摄像机的分组丢失率,从摄像机接收估计的摄像机的最大吞吐量到服务器,减少位传输 当分组丢失率大于第一预定阈值时,在分组丢失率小于第二预定阈值预定时间段时增加比特传输速率,并将比特传输速率传输到作为部分的视频编码器 用于无线网络的网络通信协议的应用层。

    Network element consolidation for rapid discrete network simulations
    9.
    发明授权
    Network element consolidation for rapid discrete network simulations 有权
    用于快速离散网络模拟的网络元素整合

    公开(公告)号:US09158870B2

    公开(公告)日:2015-10-13

    申请号:US13569505

    申请日:2012-08-08

    IPC分类号: G06F17/50 G01R21/00 G01R21/06

    摘要: Systems and methods are provided for modeling and simulating a communication network operating under at least one communication protocol, which supports a Smart Grid electricity network. Communication performance data of the communication network are generated by a processor based on operating behavior of the Smart Grid with a plurality of assets under a first condition. Devices in the Smart grid are grouped in bins for rapid modeling. One or more different configurations of the communication network are entered into the processor and related performance data is also generated. Network configurations are compared based on the generated performance data which may include end-to-end delay and reception rate. Processor based systems to perform modeling methods are also provided.

    摘要翻译: 提供了系统和方法,用于建模和模拟在支持智能电网电力网络的至少一个通信协议下运行的通信网络。 通信网络的通信性能数据由处理器基于在第一条件下具有多个资产的智能电网的操作行为来生成。 智能电网中的设备分组在箱中进行快速建模。 通信网络的一个或多个不同配置被输入到处理器中,并且还产生相关的性能数据。 基于生成的可能包括端到端延迟和接收速率的性能数据来比较网络配置。 还提供了基于处理器的系统来执行建模方法。

    Network Traffic Profile Aggregation for Efficient Discrete Event Smart Grid Network Simulations
    10.
    发明申请
    Network Traffic Profile Aggregation for Efficient Discrete Event Smart Grid Network Simulations 有权
    高效离散事件智能电网网络模拟的网络流量简档聚合

    公开(公告)号:US20130060554A1

    公开(公告)日:2013-03-07

    申请号:US13590463

    申请日:2012-08-21

    IPC分类号: G06G7/63

    摘要: Systems and methods are provided for modeling and simulating a communication network operating under at least one communication protocol, which supports a Smart Grid electricity network. Communication performance data of the communication network are generated by a processor based on operating behavior of the Smart Grid with a plurality of assets under a first condition. Devices in the Smart grid are grouped in bins for rapid modeling. One or more different configurations of the communication network are entered into the processor and related performance data is also generated. Network configurations are compared based on the generated performance data which may include end-to-end delay and reception rate. Processor based systems to perform modeling methods are also provided.

    摘要翻译: 提供了系统和方法,用于建模和模拟在支持智能电网电力网络的至少一个通信协议下运行的通信网络。 通信网络的通信性能数据由处理器基于在第一条件下具有多个资产的智能电网的操作行为来生成。 智能电网中的设备分组在箱中进行快速建模。 通信网络的一个或多个不同配置被输入到处理器中,并且还产生相关的性能数据。 基于生成的可能包括端到端延迟和接收速率的性能数据来比较网络配置。 还提供了基于处理器的系统来执行建模方法。