利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

6 条记录 (耗时 0.034 秒)

    Systems and methods for fast and memory efficient machine translation using statistical integrated phase lattice
    4.
    发明授权
    Systems and methods for fast and memory efficient machine translation using statistical integrated phase lattice 有权
    使用统计综合相位格的快速和高效的机器翻译的系统和方法

    公开(公告)号：US08229731B2

    公开(公告)日：2012-07-24

    申请号：US12824806

    申请日：2010-06-28

    申请人： Stanley Chen ,  Yuging Gao ,  Bowen Zhou

    发明人： Stanley Chen ,  Yuging Gao ,  Bowen Zhou

    IPC分类号： G06F17/28

    CPC分类号： G06F17/2818

    摘要： A phrase-based translation system and method includes a statistically integrated phrase lattice (SIPL) (H) which represents an entire translational model. An input (I) is translated by determining a best path through an entire lattice (S) by performing an efficient composition operation between the input and the SIPL. The efficient composition operation is performed by a multiple level search where each operand in the efficient composition operation represents a different search level.

    摘要翻译： 基于短语的翻译系统和方法包括代表整个翻译模型的统计学上综合的词组（SIPL）（H）。 通过在输入和SIPL之间执行有效的组合操作来确定通过整个网格（S）的最佳路径来转换输入（I）。 通过多级搜索来执行高效合成操作，其中高效合成操作中的每个操作数表示不同的搜索级别。

    SYSTEM AND METHOD FOR APPLYING BRIDGING MODELS FOR ROBUST AND EFFICIENT SPEECH TO SPEECH TRANSLATION
    5.
    发明申请
    SYSTEM AND METHOD FOR APPLYING BRIDGING MODELS FOR ROBUST AND EFFICIENT SPEECH TO SPEECH TRANSLATION 有权
    将语音模型应用于语音翻译的系统与方法

    公开(公告)号：US20090299724A1

    公开(公告)日：2009-12-03

    申请号：US12128199

    申请日：2008-05-28

    申请人： Yonggang Deng ,  Yuging Gao ,  Bing Xiang

    发明人： Yonggang Deng ,  Yuging Gao ,  Bing Xiang

    IPC分类号： G06F17/28

    CPC分类号： G06F17/2809

    摘要： A system and method for speech translation includes a bridge module connected between a first component and a second component. The bridge module includes a transformation model configured to receive an original hypothesis output from a first component. The transformation model has one or more transformation features configured to transform the original hypothesis into a new hypothesis that is more easily translated by the second component.

    摘要翻译： 用于语音翻译的系统和方法包括连接在第一组件和第二组件之间的桥模块。 桥模块包括被配置为从第一组件接收原始假设输出的变换模型。 转换模型具有一个或多个变换特征，其被配置为将原始假设转换为更容易被第二组件翻译的新假设。

    Feature vector-based apparatus and method for robust pattern recognition
    6.
    发明授权
    Feature vector-based apparatus and method for robust pattern recognition 有权
    基于特征向量的鲁棒模式识别装置和方法

    公开(公告)号：US07054810B2

    公开(公告)日：2006-05-30

    申请号：US09968051

    申请日：2001-10-01

    申请人： Yuging Gao ,  Michael A. Picheny ,  Bhuvana Ramabhadran

    发明人： Yuging Gao ,  Michael A. Picheny ,  Bhuvana Ramabhadran

    IPC分类号： G10L15/00

    CPC分类号： G10L15/02

    摘要： N sets of feature vectors are generated from a set of observation vectors which are indicative of a pattern which it is desired to recognize. At least one of the sets of feature vectors is different than at least one other of the sets of feature vectors, and is preselected for purposes of containing at least some complimentary information with regard to the at least one other set of feature vectors. The N sets of feature vectors are combined in a manner to obtain an optimized set of feature vectors which best represents the pattern. The combination is performed via one of a weighted likelihood combination scheme and a rank-based state-selection scheme; preferably, it is done in accordance with an equation set forth herein. In one aspect, a weighted likelihood combination can be employed, while in another aspect, rank-based state selection can be employed. An apparatus suitable for performing the method is described, and implementation in a computer program product is also contemplated. The invention is applicable to any type of pattern recognition problem where robustness is important, such as, for example, recognition of speech, handwriting or optical characters under challenging conditions.

    摘要翻译： 从指示希望识别的图案的一组观察向量生成N组特征向量。 所述特征向量集合中的至少一个不同于所述特征向量集合中的至少另一个，并且为了至少包含关于所述至少一个其他特征向量集合的补充信息的目的而被预先选择。 N组特征向量以一种方式组合以获得最佳表示图案的特征向量的优化集合。 组合通过加权似然组合方案和基于秩的状态选择方案之一执行; 优选地，根据本文所阐述的等式进行。 在一个方面，可以采用加权似然组合，而在另一方面，可以采用基于秩的状态选择。 描述了适用于执行该方法的装置，并且还考虑了计算机程序产品中的实现。 本发明可应用于任何类型的鲁棒性重要的模式识别问题，例如在挑战性条件下的语音识别，手写或光学特征。