-
公开(公告)号：US08229729B2
公开(公告)日：2012-07-24
申请号：US12054636
申请日：2008-03-25
CPC分类号： G06F17/2818
摘要： A system and method for training a statistical machine translation model and decoding or translating using the same is disclosed. A source word versus target word co-occurrence matrix is created to define word pairs. Dimensionality of the matrix may be reduced. Word pairs are mapped as vectors into continuous space where the word pairs are vectors of continuous real numbers and not discrete entities in the continuous space. A machine translation parametric model is trained using an acoustic model training method based on word pair vectors in the continuous space.
摘要翻译： 公开了一种用于训练统计机器翻译模型和使用其的解码或翻译的系统和方法。 创建源词与目标词同现矩阵以定义单词对。 可以减小矩阵的尺寸。 字对被映射为连续空间中的向量，其中单词对是连续实数的向量，而不是连续空间中的离散实体。 使用基于连续空间中的字对矢量的声学模型训练方法训练机器翻译参数模型。
-
公开(公告)号：US20090248394A1
公开(公告)日：2009-10-01
申请号：US12054636
申请日：2008-03-25
IPC分类号： G06F17/28
CPC分类号： G06F17/2818
摘要： A system and method for training a statistical machine translation model and decoding or translating using the same is disclosed. A source word versus target word co-occurrence matrix is created to define word pairs. Dimensionality of the matrix may be reduced. Word pairs are mapped as vectors into continuous space where the word pairs are vectors of continuous real numbers and not discrete entities in the continuous space. A machine translation parametric model is trained using an acoustic model training method based on word pair vectors in the continuous space.
摘要翻译： 公开了一种用于训练统计机器翻译模型和使用其的解码或翻译的系统和方法。 创建源词与目标词同现矩阵以定义单词对。 可以减小矩阵的尺寸。 字对被映射为连续空间中的向量，其中单词对是连续实数的向量，而不是连续空间中的离散实体。 使用基于连续空间中的字对矢量的声学模型训练方法训练机器翻译参数模型。
-
3.发明授权System and method for applying bridging models for robust and efficient speech to speech translation 有权用于将强大而有效的语音桥接模型应用于语音翻译的系统和方法公开(公告)号：US08566076B2
公开(公告)日：2013-10-22
申请号：US12128199
申请日：2008-05-28
申请人： Yonggang Deng , Yuqing Gao , Bing Xiang
发明人： Yonggang Deng , Yuqing 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。
-
公开(公告)号：US07117153B2
公开(公告)日：2006-10-03
申请号：US10365850
申请日：2003-02-13
CPC分类号： G10L15/197 , G10L15/183
摘要： A method of modeling a speech recognition system includes decoding a speech signal produced from a training text to produce a sequence of predicted speech units. The training text comprises a sequence of actual speech units that is used with the sequence of predicted speech units to form a confusion model. In further embodiments, the confusion model is used to decode a text to identify an error rate that would be expected if the speech recognition system decoded speech based on the text.
摘要翻译： 对语音识别系统进行建模的方法包括对从训练文本产生的语音信号进行解码以产生预测语音单元的序列。 训练文本包括与预测语音单元的序列一起使用以形成混淆模型的实际语音单元的序列。 在另外的实施例中，混淆模型用于对文本进行解码以识别如果语音识别系统基于文本解码的语音将会预期的错误率。
-
公开(公告)号：US07103544B2
公开(公告)日：2006-09-05
申请号：US11146324
申请日：2005-06-06
CPC分类号： G10L15/197 , G10L15/183
摘要： A method of modeling a speech recognition system includes decoding a speech signal produced from a training text to produce a sequence of predicted speech units. The training text comprises a sequence of actual speech units that is used with the sequence of predicted speech units to form a confusion model. In further embodiments, the confusion model is used to decode a text to identify an error rate that would be expected if the speech recognition system decoded speech based on the text.
-
6.发明申请公开(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。
-
公开(公告)号：US20050228670A1
公开(公告)日：2005-10-13
申请号：US11146324
申请日：2005-06-06
CPC分类号： G10L15/197 , G10L15/183
摘要： A method of modeling a speech recognition system includes decoding a speech signal produced from a training text to produce a sequence of predicted speech units. The training text comprises a sequence of actual speech units that is used with the sequence of predicted speech units to form a confusion model. In further embodiments, the confusion model is used to decode a text to identify an error rate that would be expected if the speech recognition system decoded speech based on the text.
摘要翻译： 对语音识别系统进行建模的方法包括对从训练文本产生的语音信号进行解码以产生预测语音单元的序列。 训练文本包括与预测语音单元的序列一起使用以形成混淆模型的实际语音单元的序列。 在另外的实施例中，混淆模型用于对文本进行解码以识别如果语音识别系统基于文本解码的语音将会预期的错误率。
-
-
-
-
-
-
搜索结果
7 条记录 (耗时 0.031 秒)