Method for entering text
    51.
    发明授权
    Method for entering text 失效
    输入文字的方法

    公开(公告)号:US07363224B2

    公开(公告)日:2008-04-22

    申请号:US10748404

    申请日:2003-12-30

    IPC分类号: G10L15/04

    摘要: In a method of entering text into a device a first character input is provided that is indicative of a first character of a text entry. Next, a vocalization of the text entry is captured. A probable word candidate is then identified for a first word of the vocalization based upon the first character input and an analysis of the vocalization. Finally, the probable word candidate is displayed for a user.

    摘要翻译: 在将文本输入到设备中的方法中,提供指示文本输入的第一个字符的第一个字符输入。 接下来,捕获文本条目的发声。 然后基于第一个字符输入和发声分析,识别发音的第一个单词的可能的词候选。 最后,为用户显示可能的候选词。

    Delegated presence for unified messaging/unified communication
    52.
    发明申请
    Delegated presence for unified messaging/unified communication 有权
    代理存在统一消息/统一通信

    公开(公告)号:US20060245434A1

    公开(公告)日:2006-11-02

    申请号:US11119346

    申请日:2005-04-29

    IPC分类号: H04L12/56

    摘要: The present invention relates to methods and systems for handling interactions between a user and a computer. In particular, the present invention relates to methods and systems for handling communication messages from different types of communication interfaces.

    摘要翻译: 本发明涉及用于处理用户和计算机之间的交互的方法和系统。 特别地,本发明涉及用于处理来自不同类型的通信接口的通信消息的方法和系统。

    Speech recognition method and apparatus utilizing multi-unit models
    55.
    发明授权
    Speech recognition method and apparatus utilizing multi-unit models 有权
    使用多单元模型的语音识别方法和装置

    公开(公告)号:US06629073B1

    公开(公告)日:2003-09-30

    申请号:US09559505

    申请日:2000-04-27

    IPC分类号: G01L1506

    摘要: A speech recognition method and system utilize an acoustic model that is capable of providing probabilities for both a large acoustic unit and an acoustic sub-unit. Each of these probabilities describes the likelihood of a set of feature vectors from a series of feature vectors representing a speech signal. The large acoustic unit is formed from a plurality of acoustic sub-units. At least one sub-unit probability and at least on large unit probability from the acoustic model are used by a decoder to generate a score for a sequence of hypothesized words. When combined, the acoustic sub-units associated with all of the sub-unit probabilities used to determine the score span fewer than all of the feature vectors in the series of feature vectors. An overlapping decoding technique is also provided.

    摘要翻译: 语音识别方法和系统利用能够为大声学单元和声学子单元提供概率的声学模型。 这些概率中的每一个描述了来自表示语音信号的一系列特征向量的一组特征向量的可能性。 大型声学单元由多个声学子单元形成。 解码器使用来自声学模型的至少一个子单元概率和至少基于大的单位概率来为假设词的序列生成分数。 当组合时,与用于确定分数的所有子单元概率相关联的声学子单元小于该系列特征向量中的所有特征向量。 还提供了重叠的解码技术。

    Identifying query formulation suggestions for low-match queries
    56.
    发明授权
    Identifying query formulation suggestions for low-match queries 有权
    识别低匹配查询的查询制定建议

    公开(公告)号:US08965872B2

    公开(公告)日:2015-02-24

    申请号:US13172561

    申请日:2011-06-29

    IPC分类号: G06F7/00 G06F17/00 G06F17/30

    摘要: Systems, methods and computer-storage media are provided for identifying low-match search queries and determining comparable item matches to suggest to the user in response to a low-match query. “Low-match queries” are queries for which an insufficient number of exact item matches are available. In embodiments, exact and/or comparable item matches may be determined via semantic analysis. Also provided are systems, methods and computer-storage media for informing the user, by way of a presented indicator, or the like, that a presented item was selected for presentation based upon a similarity metric rather than being determined an exact match for the input query.

    摘要翻译: 系统,方法和计算机存储介质被提供用于识别低匹配搜索查询并且确定可响应于低匹配查询的用户建议的可比较项目匹配。 “低匹配查询”是对可用的确切项目匹配数量不足的查询。 在实施例中,可以通过语义分析来确定精确和/或可比较的项目匹配。 还提供了系统,方法和计算机存储介质,用于通过所呈现的指示符等向用户通知基于相似性度量而选择呈现的呈现项目,而不是确定输入的精确匹配 查询。

    User authentication by combining speaker verification and reverse turing test
    58.
    发明授权
    User authentication by combining speaker verification and reverse turing test 有权
    通过组合说话人验证和反向图测试进行用户认证

    公开(公告)号:US08457974B2

    公开(公告)日:2013-06-04

    申请号:US13558431

    申请日:2012-07-26

    申请人: Kuansan Wang

    发明人: Kuansan Wang

    CPC分类号: G06F21/31 G06F21/32 G10L17/22

    摘要: Methods and system for authenticating a user are disclosed. The present invention includes accessing a collection of personal information related to the user. The present invention also includes performing an authentication operation that is based on the collection of personal information. The authentication operation incorporates at least one dynamic component and prompts the user to give an audible utterance. The audible utterance is compared to a stored voiceprint.

    摘要翻译: 公开了用于认证用户的方法和系统。 本发明包括访问与用户相关的个人信息的集合。 本发明还包括执行基于收集个人信息的认证操作。 认证操作包含至少一个动态组件,并提示用户给出可听见的发音。 将可听话语与存储的声纹进行比较。

    Routing a VoIP call with contextual information
    59.
    发明授权
    Routing a VoIP call with contextual information 有权
    使用上下文信息路由VoIP通话

    公开(公告)号:US08451829B2

    公开(公告)日:2013-05-28

    申请号:US13284572

    申请日:2011-10-28

    IPC分类号: H04L12/66

    摘要: A method and system for routing a call connection signal and corresponding contextual information to an appropriate destination is provided. A call center and at least one user may exchange signals, and/or contextual information during a call set-up phase. Relevant contextual information and other detailed information may be identified and collected from their corresponding sources. Based on the relevant contextual information and other detailed information, one or more appropriate routed destinations may be determined. In addition, contextual information may be tailored for each of the determined routed destinations. The call connection signal and the tailored contextual information are routed to each routed destination. In this manner, necessary contextual information may be readily available for the routed destination at the time of the call connection and thus the routed destination can provide a faster service.

    摘要翻译: 提供了一种用于将呼叫连接信号和对应的上下文信息路由到适当的目的地的方法和系统。 呼叫中心和至少一个用户可以在呼叫建立阶段期间交换信号和/或上下文信息。 相关的上下文信息和其他详细信息可以从其相应的来源被识别和收集。 基于相关的上下文信息和其他详细信息,可以确定一个或多个适当的路由目的地。 此外,可以为每个确定的路由目的地量身定制上下文信息。 呼叫连接信号和定制的上下文信息被路由到每个路由的目的地。 以这种方式,在呼叫连接时,必要的上下文信息可以容易地用于路由目的地,并且因此路由目的地可以提供更快的服务。

    USER AUTHENTICATION BY COMBINING SPEAKER VERIFICATION AND REVERSE TURING TEST
    60.
    发明申请
    USER AUTHENTICATION BY COMBINING SPEAKER VERIFICATION AND REVERSE TURING TEST 有权
    用户通过组合声音验证和反向测试进行认证

    公开(公告)号:US20120296651A1

    公开(公告)日:2012-11-22

    申请号:US13558431

    申请日:2012-07-26

    申请人: Kuansan Wang

    发明人: Kuansan Wang

    IPC分类号: G10L15/00

    CPC分类号: G06F21/31 G06F21/32 G10L17/22

    摘要: Methods and system for authenticating a user are disclosed. The present invention includes accessing a collection of personal information related to the user. The present invention also includes performing an authentication operation that is based on the collection of personal information. The authentication operation incorporates at least one dynamic component and prompts the user to give an audible utterance. The audible utterance is compared to a stored voiceprint.

    摘要翻译: 公开了用于认证用户的方法和系统。 本发明包括访问与用户相关的个人信息的集合。 本发明还包括执行基于收集个人信息的认证操作。 认证操作包含至少一个动态组件,并提示用户给出可听见的发音。 将可听话语与存储的声纹进行比较。