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. 发明申请

US20100246837A1 Systems and Methods for Tuning Automatic Speech Recognition Systems 审中-公开
标题翻译：自动语音识别系统调优系统与方法
公开(公告)号：US20100246837A1
公开(公告)日：2010-09-30
申请号：US12748608
申请日：2010-03-29
申请人： Lee S. Krause , Bonny Banerjee , Mark Skowronski , Rahul Shrivastav , Alice E. Holmes
发明人： Lee S. Krause , Bonny Banerjee , Mark Skowronski , Rahul Shrivastav , Alice E. Holmes
IPC分类号： H04R29/00
CPC分类号： G10L15/00 , A61N1/36038 , G10L13/00 , G10L15/063 , G10L15/07 , G10L2015/0631 , G10L2015/0638 , H04R25/30 , H04R25/505 , H04R2225/43 , H04R2225/67
摘要： A tuning system for tuning a speech recognition system includes a transmitter for sending a user response to a speech recognition system. The user response is based at least in part on a test stimulus that may be generated by the control system. A receiver receives a recognized response from the speech recognition system; this recognized response is based at least in part on the associated user response. An adjustment module adjusts at least one parameter of the speech recognition system based at least in part on at least one of the test stimulus, the associated user response, and the recognized response.
摘要翻译：用于调谐语音识别系统的调谐系统包括用于向语音识别系统发送用户响应的发射机。用户响应至少部分地基于可由控制系统产生的测试刺激。接收器从语音识别系统接收识别的响应; 该认可的响应至少部分地基于相关联的用户响应。调整模块至少部分地基于测试刺激，相关联的用户响应和所识别的响应中的至少一个来调整语音识别系统的至少一个参数。

2. 发明授权

US07206416B2 Speech-based optimization of digital hearing devices 有权
标题翻译：基于语音的数字听力设备优化
公开(公告)号：US07206416B2
公开(公告)日：2007-04-17
申请号：US10872313
申请日：2004-06-18
申请人： Lee S. Krause , Rahul Shrivastav , Alice E. Holmes , Purvis Bedenbaugh
发明人： Lee S. Krause , Rahul Shrivastav , Alice E. Holmes , Purvis Bedenbaugh
IPC分类号： H04R29/00 , A61B5/00
CPC分类号： G10L25/00 , H04R25/505 , H04R25/70
摘要： A method of tuning a digital hearing device can include playing portions of test audio, wherein each portion of test audio represents one or more distinctive features of speech. The method also can include receiving user responses to played portions of test audio heard through the digital hearing device and comparing the user responses with the portions of test audio. An operational parameter of the digital hearing device can be adjusted according to the comparing step, wherein the operational parameter is associated with one or more of the distinctive features of speech.
摘要翻译：调整数字听力设备的方法可以包括播放测试音频的部分，其中测试音频的每个部分表示语音的一个或多个独特特征。该方法还可以包括接收用户对通过数字听觉设备听到的测试音频播放部分的响应，并将用户响应与测试音频的部分进行比较。可以根据比较步骤来调整数字听力装置的操作参数，其中操作参数与语音的一个或多个特征相关联。

3. 发明申请

US20160239763A1 Motif recognition 审中-公开
标题翻译：主题识别
公开(公告)号：US20160239763A1
公开(公告)日：2016-08-18
申请号：US15137973
申请日：2016-04-25
申请人： Lee S. Krause , Craig T. Hagan , Bruce R. McQueary , James B. Schneider
发明人： Lee S. Krause , Craig T. Hagan , Bruce R. McQueary , James B. Schneider
IPC分类号： G06N99/00 , G06F17/30
CPC分类号： G06N99/005 , G06F17/30153 , G06F17/3053 , G06F17/3064 , G06F17/30648 , G06F17/30867
摘要： Methods and systems for motif recognition in graph sets. Distribution scores comparing the canonical representations of a compressed graph in the set of graphs versus the canonical representations of a compressed graph in a reference graph are used to determine the significance of the compressed graph.
摘要翻译：图集中图案识别的方法和系统。使用比较图中的压缩图的规范表示与参考图中的压缩图的规范表示的分布分数来确定压缩图的重要性。

4. 发明授权

US09372929B2 Methods and systems for node and link identification 有权
标题翻译：节点和链路识别的方法和系统
公开(公告)号：US09372929B2
公开(公告)日：2016-06-21
申请号：US14221251
申请日：2014-03-20
申请人： Lee S. Krause , James B. Schneider , Bruce R. McQueary , Craig T. Hagan , Sean K. Thornton , Peter M. LaMonica , Craig S. Anken , Carlos Guestrin
发明人： Lee S. Krause , James B. Schneider , Bruce R. McQueary , Craig T. Hagan , Sean K. Thornton , Peter M. LaMonica , Craig S. Anken , Carlos Guestrin
IPC分类号： G06F17/00 , G06F17/30
CPC分类号： G06N99/005 , G06F17/30153 , G06F17/3053 , G06F17/3064 , G06F17/30648 , G06F17/30867
摘要： Methods and systems for node and link detection in social network analysis. Interactive noise reduction allows reduction of the data set under analysis to enable substantially real time detection of links and nodes.
摘要翻译：社会网络分析中节点和链路检测的方法和系统。交互式降噪允许减少分析中的数据集，以实现链路和节点的基本实时检测。

5. 发明授权

US09020621B1 Network based media enhancement function based on an identifier 有权
标题翻译：基于网络的媒体增强功能，基于标识符
公开(公告)号：US09020621B1
公开(公告)日：2015-04-28
申请号：US12948515
申请日：2010-11-17
申请人： James Proctor , Mark Skowronski , James R. Bress , Lee S. Krause , George Shenoda
发明人： James Proctor , Mark Skowronski , James R. Bress , Lee S. Krause , George Shenoda
IPC分类号： G06F17/00 , H04R5/04 , H04R25/00
CPC分类号： H04R5/04 , H04R3/00 , H04R25/75 , H04R27/00 , H04R2227/003 , H04R2227/009
摘要： A network based processing element for processing audio information improves the understanding of speech or music for intended listeners based on an identifier. The processing involves performing a media enhancement function, where a parameter affecting the utilization or performance aspects of the media enhancement function are dependent upon the identifier. A “media enhancement server” (MES) is included, whereby the audio of a telephone call, video call, multimedia program or other stream to be heard by a specific listener is processed using a personalized audio enhancement parameter to enhance the audio signal such that the listener will enjoy a benefit, such as better comprehension of the information, reduced listening effort, and more listening comfort during the call. The personalized parameters are stored and retrieved based upon the identifier, and used within the MES. The audio portion of the call or stream could be speech, music, or a combination.
摘要翻译：用于处理音频信息的基于网络的处理元件基于标识符改善对于预期听众的语音或音乐的理解。该处理涉及执行媒体增强功能，其中影响媒体增强功能的利用或性能方面的参数取决于标识符。包括“媒体增强服务器”（MES），由此使用个性化音频增强参数来处理要由特定收听者听到的电话呼叫，视频呼叫，多媒体节目或其他流的音频，以增强音频信号，使得听众将享受到更好的理解信息，减少听力，以及更多的聆听舒适性。基于标识符存储和检索个性化参数，并在MES中使用。呼叫或流的音频部分可以是语音，音乐或组合。

6. 发明授权

US10115061B2 Motif recognition 有权
公开(公告)号：US10115061B2
公开(公告)日：2018-10-30
申请号：US15137973
申请日：2016-04-25
申请人： Lee S. Krause , Craig T. Hagan , Bruce R. McQueary , James B. Schneider
发明人： Lee S. Krause , Craig T. Hagan , Bruce R. McQueary , James B. Schneider
IPC分类号： G06F17/00 , G06N99/00 , G06F17/30
摘要： Methods and systems for motif recognition in graph sets. Distribution scores comparing the canonical representations of a compressed graph in the set of graphs versus the canonical representations of a compressed graph in a reference graph are used to determine the significance of the compressed graph.

7. 发明授权

US09553984B2 Systems and methods for remotely tuning hearing devices 有权
标题翻译：用于远程调谐听力设备的系统和方法
公开(公告)号：US09553984B2
公开(公告)日：2017-01-24
申请号：US12748819
申请日：2010-03-29
申请人： Lee S. Krause , Rahul Shrivastav , Bonny Banerjee , Alice E. Holmes
发明人： Lee S. Krause , Rahul Shrivastav , Bonny Banerjee , Alice E. Holmes
IPC分类号： H04R29/00 , H04M3/42 , A61N1/08 , A61N1/36 , A61N1/372 , H04M3/26 , G10L25/69 , G10L21/06 , H04M1/247 , H04M1/60 , H04M1/725 , H04M3/493 , H04M7/00 , H04R25/00
CPC分类号： H04M3/42391 , A61N1/08 , A61N1/36036 , A61N1/37264 , G10L25/69 , G10L2021/065 , H04M1/2474 , H04M1/6016 , H04M1/72591 , H04M3/26 , H04M3/493 , H04M7/006 , H04M2201/39 , H04M2207/18 , H04R25/505 , H04R25/70 , H04R2225/55 , H04R2225/67 , H04R2499/11
摘要： A method of tuning a hearing device includes sending a test signal to a model of a hearing device that may be remote from the actual hearing device being tuned. The test signal is encoded by the model and sent to the hearing device being tuned. The user of that hearing device sends a response signal based at least in part on the encoded test signal. This response is received and compared to the original test signal. Thereafter, an operational parameter is sent to the hearing device based on the comparison.
摘要翻译：调谐听力设备的方法包括将测试信号发送到可能远离被调谐的实际听力设备的听力设备的模型。测试信号由模型编码并发送到被调谐的听力设备。该听力设备的用户至少部分地基于编码的测试信号发送响应信号。接收该响应并将其与原始测试信号进行比较。此后，基于比较将操作参数发送到听力设备。

8. 发明申请

US20100232613A1 Systems and Methods for Remotely Tuning Hearing Devices 有权
标题翻译：用于远程调谐听力装置的系统和方法
公开(公告)号：US20100232613A1
公开(公告)日：2010-09-16
申请号：US12748819
申请日：2010-03-29
申请人： Lee S. Krause , Rahul Shrivastav , Bonny Banerjee , Alice E. Holmes
发明人： Lee S. Krause , Rahul Shrivastav , Bonny Banerjee , Alice E. Holmes
IPC分类号： H04R29/00
CPC分类号： H04M3/42391 , A61N1/08 , A61N1/36036 , A61N1/37264 , G10L25/69 , G10L2021/065 , H04M1/2474 , H04M1/6016 , H04M1/72591 , H04M3/26 , H04M3/493 , H04M7/006 , H04M2201/39 , H04M2207/18 , H04R25/505 , H04R25/70 , H04R2225/55 , H04R2225/67 , H04R2499/11
摘要： A method of tuning a hearing device includes sending a test signal to a model of a hearing device that may be remote from the actual hearing device being tuned. The test signal is encoded by the model and sent to the hearing device being tuned. The user of that hearing device sends a response signal based at least in part on the encoded test signal. This response is received and compared to the original test signal. Thereafter, an operational parameter is sent to the hearing device based on the comparison.
摘要翻译：调谐听力设备的方法包括将测试信号发送到可能远离被调谐的实际听力设备的听力设备的模型。测试信号由模型编码并发送到被调谐的听力设备。该听力设备的用户至少部分地基于编码的测试信号发送响应信号。接收该响应并将其与原始测试信号进行比较。此后，基于比较将操作参数发送到听力设备。

9. 发明申请

US20070286350A1 SPEECH-BASED OPTIMIZATION OF DIGITAL HEARING DEVICES 审中-公开
标题翻译：基于语音的数字听觉设备优化
公开(公告)号：US20070286350A1
公开(公告)日：2007-12-13
申请号：US11421889
申请日：2006-06-02
申请人： Lee S. Krause , Rahul Shrivastav , Alice E. Holmes , Purvis Bedenbaugh
发明人： Lee S. Krause , Rahul Shrivastav , Alice E. Holmes , Purvis Bedenbaugh
IPC分类号： H04M1/24 , H04M3/22 , H04M3/08
CPC分类号： H04M3/42391 , H04M1/2474 , H04M1/6016 , H04M3/26 , H04M3/493
摘要： A method of tuning a digital hearing device, such as a cellular phone, a mobile phone for communicating via a wireless ad hoc network, and a Voice-over-Internet-Protocol (VoIP) phone, can include playing portions of test audio, wherein each portion of test audio represents one or more distinctive features of speech. The method also can include receiving user responses to played portions of test audio heard through the digital hearing device and comparing the user responses with the portions of test audio. An operational parameter of the digital hearing device can be adjusted based on one or more of the distinctive features of speech that is associated with the operational parameter.
摘要翻译：调谐诸如蜂窝电话的数字听力设备，用于经由无线自组织网络进行通信的移动电话和互联网电话协议（VoIP）电话）的方法可以包括播放测试音频的部分，其中测试音频的每个部分表示语音的一个或多个独特特征。该方法还可以包括接收用户对通过数字听觉设备听到的测试音频播放部分的响应，并将用户响应与测试音频的部分进行比较。可以基于与操作参数相关联的语音的一个或多个独特特征来调整数字听力设备的操作参数。

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