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

US08473295B2 Redictation of misrecognized words using a list of alternatives 有权
标题翻译：使用备选方案列表来消除误识别的单词
公开(公告)号：US08473295B2
公开(公告)日：2013-06-25
申请号：US11255329
申请日：2005-10-21
申请人： David Mowatt , Robert E. Dewar , Robert L. Chambers , Felix Gerard Torquil Ifor Andrew , Oliver Scholz
发明人： David Mowatt , Robert E. Dewar , Robert L. Chambers , Felix Gerard Torquil Ifor Andrew , Oliver Scholz
IPC分类号： G10L15/04 , G10L15/02
CPC分类号： G10L15/22
摘要： Upon selection of a displayed word, a list of alternatives for the selected word is displayed. Each alternative in the list has an associated symbol. A speech signal is then decoded to identify a list of possible words and the list of possible words is displayed with each possible word having an associated symbol.
摘要翻译：在选择所显示的单词时，显示所选择的单词的替换列表。列表中的每个替代项都有一个关联的符号。然后解码语音信号以识别可能的词的列表，并且显示可能的词的列表，其中每个可能的单词具有相关联的符号。

2. 发明授权

US07742923B2 Graphic user interface schemes for supporting speech recognition input systems 有权
标题翻译：用于支持语音识别输入系统的图形用户界面方案
公开(公告)号：US07742923B2
公开(公告)日：2010-06-22
申请号：US10950020
申请日：2004-09-24
申请人： Ryan Terry Bickel , Oscar E. Murillo , David Mowatt , Robert L. Chambers , Oliver Scholz
发明人： Ryan Terry Bickel , Oscar E. Murillo , David Mowatt , Robert L. Chambers , Oliver Scholz
IPC分类号： G10L21/00
CPC分类号： G06F3/0481
摘要： A numbering scheme is disclosed for implementation in the context of an application display. A user is able to select an item on the display by speaking a number corresponding to a desired control item. In some cases, the screen can include so many numbers that the user loses context and is unable to identify which number they want to select. For this reason, in one embodiment, a temporal switching mechanism is implemented wherein periodic switches (e.g., second-long intervals) occur between showing numbered items and showing a non-numbered screen. In one embodiment, an optional secondary confirmation step is implemented wherein the user sees only the item they just selected and has the chance to (a) learn the programmatic name of the item they selected and/or (b) either confirm and proceed with their selection, or cancel. In one embodiment, the optional secondary confirmation step is omitted if the user speaks a number followed by a predetermined command word.
摘要翻译：公开了用于在应用程序显示的上下文中实现的编号方案。用户能够通过说出与期望的控制项目对应的号码来选择显示器上的项目。在某些情况下，屏幕可以包含如此多的数字，用户丢失上下文，并且无法识别他们想要选择的号码。为此，在一个实施例中，实现了时间切换机制，其中在显示编号的项目之间出现周期性的开关（例如，第二长的间隔），并显示非编号的屏幕。在一个实施例中，实现可选的辅助确认步骤，其中用户仅看到他们刚刚选择的项目，并且有机会（a）学习他们选择的项目的编程名称和/或（b）确认并继续进行他们的选择或取消。在一个实施例中，如果用户说出一个后面是预定命令字的号码，则省略可选的辅助确认步骤。

3. 发明授权

US07643999B2 Microphone feedback and control 有权
标题翻译：麦克风反馈和控制
公开(公告)号：US07643999B2
公开(公告)日：2010-01-05
申请号：US10996770
申请日：2004-11-24
申请人： Robert L. Chambers , Oliver Scholz , Oscar E. Murillo , David Mowatt
发明人： Robert L. Chambers , Oliver Scholz , Oscar E. Murillo , David Mowatt
IPC分类号： G10L21/06
CPC分类号： G10L15/22 , G06F3/0481
摘要： A system and method for positioning a software User Interface (UI) window on a display screen is provided, wherein the method includes displaying the software UI window on the display screen and identifying at least one suitable location on the display screen responsive to an active target window area of a target application UI window. The method further includes determining whether the software UI window is disposed at the at least one suitable location on the display screen and if the software UI window is disposed in a location other than the at least one suitable location on the display screen, positioning the software UI window at the at least one suitable location on the display screen.
摘要翻译：提供了一种用于在显示屏幕上定位软件用户界面（UI）窗口的系统和方法，其中所述方法包括在显示屏幕上显示软件UI窗口，并且响应于活动目标来识别显示屏幕上的至少一个合适位置目标应用程序UI窗口的窗口区域。该方法还包括确定软件UI窗口是否被布置在显示屏幕上的至少一个适当位置，并且如果软件UI窗口被布置在除了显示屏幕上的至少一个适当位置之外的位置，则定位该软件 UI窗口在显示屏幕上的至少一个合适的位置。

4. 发明授权

US07680514B2 Wireless speech recognition 有权
标题翻译：无线语音识别
公开(公告)号：US07680514B2
公开(公告)日：2010-03-16
申请号：US11378550
申请日：2006-03-17
申请人： Daniel B. Cook , David Mowatt , Oliver Scholz , Oscar E. Murillo , Robert L. Chambers , Ryan T. Bickel
发明人： Daniel B. Cook , David Mowatt , Oliver Scholz , Oscar E. Murillo , Robert L. Chambers , Ryan T. Bickel
IPC分类号： H04B1/38
CPC分类号： G10L15/28 , H04M1/6066 , H04M2250/74
摘要： A portable wireless-enabled system includes an input transducer (for example, a microphone), an output transducer (for example, a speaker) and a wireless transceiver system. Also included, is a memory having a programmable user speech profile. A processor system controls operation of the input transducer, the output transducer, the wireless transceiver system and the memory.
摘要翻译：便携式无线系统包括输入换能器（例如，麦克风），输出换能器（例如扬声器）和无线收发器系统。还包括，是具有可编程用户语音简档的存储器。处理器系统控制输入传感器，输出变换器，无线收发器系统和存储器的操作。

5. 发明申请

US20090234647A1 Speech Recognition Disambiguation on Mobile Devices 有权
标题翻译：移动设备语音识别消歧
公开(公告)号：US20090234647A1
公开(公告)日：2009-09-17
申请号：US12049243
申请日：2008-03-14
申请人： Oliver Scholz , Robert L. Chambers , Julian James Odell
发明人： Oliver Scholz , Robert L. Chambers , Julian James Odell
IPC分类号： G10L15/26
CPC分类号： G10L15/30
摘要： A method, program storage device and mobile device provide speech disambiguation. Audio for speech recognition processing is transmitted by the mobile device. Results representing alternates identified to match the transmitted audio are received. The alternates are displayed in a disambiguation dialog screen for making corrections to the alternates. Corrections are made to the alternates using the disambiguation dialog screen until a correct result is displayed. The correct result is selected. Content associated with the selected correct result is received in parallel with the receiving of the results representing alternates identified to match the transmitted audio.
摘要翻译：一种方法，程序存储设备和移动设备提供语音消歧。用于语音识别处理的音频由移动设备发送。接收到表示与发送音频相匹配的候补的结果。替代物显示在消歧对话屏幕中，用于对替代物进行更正。使用消歧对话框屏幕对替代品进行更正，直到显示正确的结果。选择正确的结果。与所选择的正确结果相关联的内容与接收到表示被识别为匹配所发送的音频的替代的结果并行地接收。

6. 发明授权

US08725492B2 Recognizing multiple semantic items from single utterance 有权
标题翻译：从单一语音识别多个语义项
公开(公告)号：US08725492B2
公开(公告)日：2014-05-13
申请号：US12042460
申请日：2008-03-05
申请人： Julian J Odell , Robert L. Chambers , Oliver Scholz
发明人： Julian J Odell , Robert L. Chambers , Oliver Scholz
IPC分类号： G06F17/28
CPC分类号： G10L15/1815
摘要： Semantically distinct items are extracted from a single utterance by repeatedly recognizing the same utterance using constraints provided by semantic items already recognized. User feedback for selection or correction of partially recognized utterance may be used in a hierarchical, multi-modal, or single step manner. An accuracy of recognition is preserved while the less structured and more natural single utterance recognition form is allowed to be used.
摘要翻译：通过使用已经识别的语义项提供的约束重复地识别相同的话语，从单个话语中提取语义上不同的项目。用于部分识别的话语的选择或校正的用户反馈可以以分层，多模式或单步的方式使用。识别的准确性得到保留，而较少结构化和更自然的单个话语识别形式被允许使用。

7. 发明授权

US08224656B2 Speech recognition disambiguation on mobile devices 有权
标题翻译：移动设备上的语音识别消歧
公开(公告)号：US08224656B2
公开(公告)日：2012-07-17
申请号：US12049243
申请日：2008-03-14
申请人： Oliver Scholz , Robert L. Chambers , Julian James Odell
发明人： Oliver Scholz , Robert L. Chambers , Julian James Odell
IPC分类号： G10L21/06
CPC分类号： G10L15/30
摘要： A method, program storage device and mobile device provide speech disambiguation. Audio for speech recognition processing is transmitted by the mobile device. Results representing alternates identified to match the transmitted audio are received. The alternates are displayed in a disambiguation dialog screen for making corrections to the alternates. Corrections are made to the alternates using the disambiguation dialog screen until a correct result is displayed. The correct result is selected. Content associated with the selected correct result is received in parallel with the receiving of the results representing alternates identified to match the transmitted audio.
摘要翻译：一种方法，程序存储设备和移动设备提供语音消歧。用于语音识别处理的音频由移动设备发送。接收到表示与发送音频相匹配的候补的结果。替代物显示在消歧对话屏幕中，用于对替代物进行更正。使用消歧对话框屏幕对替代品进行更正，直到显示正确的结果。选择正确的结果。与所选择的正确结果相关联的内容与接收到表示被识别为匹配所发送的音频的替代的结果并行地接收。

8. 发明授权

US08942985B2 Centralized method and system for clarifying voice commands 有权
标题翻译：用于澄清语音命令的集中方法和系统
公开(公告)号：US08942985B2
公开(公告)日：2015-01-27
申请号：US10990345
申请日：2004-11-16
申请人： David Mowatt , Robert L. Chambers , Felix G. T. I. Andrew
发明人： David Mowatt , Robert L. Chambers , Felix G. T. I. Andrew
IPC分类号： G10L21/00 , G10L25/00 , G06F3/16
CPC分类号： G10L15/22 , G06F3/167 , G10L15/18 , G10L2015/223 , G10L2015/228
摘要： A method and system for facilitating centralized interaction with a user includes providing a recognized voice command to a plurality of application modules. A plurality of interpretations of the voice command are generated by at least one of the plurality of application modules. A centralized interface module visually renders the plurality of interpretations of the voice command on a centralized display. An indication of selection of an interpretation is received from the user.
摘要翻译：用于促进与用户的集中交互的方法和系统包括向多个应用模块提供识别的语音命令。语音命令的多个解释由多个应用模块中的至少一个生成。集中式界面模块在视觉上呈现了集中显示上的语音命令的多种解释。从用户接收到对解释的选择的指示。

9. 发明申请

US20090228270A1 Recognizing multiple semantic items from single utterance 有权
标题翻译：从单一语音识别多个语义项
公开(公告)号：US20090228270A1
公开(公告)日：2009-09-10
申请号：US12042460
申请日：2008-03-05
申请人： Julian J. Odell , Robert L. Chambers , Oliver Scholz
发明人： Julian J. Odell , Robert L. Chambers , Oliver Scholz
IPC分类号： G10L15/00
CPC分类号： G10L15/1815
摘要： Semantically distinct items are extracted from a single utterance by repeatedly recognizing the same utterance using constraints provided by semantic items already recognized. User feedback for selection or correction of partially recognized utterance may be used in a hierarchical, multi-modal, or single step manner. An accuracy of recognition is preserved while the less structured and more natural single utterance recognition form is allowed to be used.
摘要翻译：通过使用已经识别的语义项提供的约束重复地识别相同的话语，从单个话语中提取语义上不同的项目。用于部分识别的话语的选择或校正的用户反馈可以以分层，多模式或单步的方式使用。识别的准确性得到保留，而较少结构化和更自然的单个话语识别形式被允许使用。

10. 发明授权

US08725505B2 Verb error recovery in speech recognition 有权
标题翻译：语音识别中的动词错误恢复
公开(公告)号：US08725505B2
公开(公告)日：2014-05-13
申请号：US10971817
申请日：2004-10-22
申请人： David Mowatt , Robert L. Chambers
发明人： David Mowatt , Robert L. Chambers
IPC分类号： G10L15/22 , G10L15/18
CPC分类号： G10L15/22
摘要： A computer implemented method and system for speech recognition are provided. The method and system generally maintain a set of verbs for speech recognition commands. Upon recognizing utterance of a verb of the set in combination with an invalid object or objects for the verb, the method and system generate an indication relative to the verb and invalid object. The indication can include informing the user that the system is unsure how to execute the command associated with the verb with the invalid object. The method and system can then receive a user input to specify how the verb and invalid object should be treated.
摘要翻译：提供了一种用于语音识别的计算机实现方法和系统。该方法和系统通常保留一组用于语音识别命令的动词。在识别出动词与动词无效对象或动词对象的动词的发音时，该方法和系统生成关于动词和无效对象的指示。指示可以包括通知用户系统不确定如何用无效对象执行与动词相关联的命令。然后，方法和系统可以接收用户输入，以指定如何处理动词和无效对象。

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