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

US06673424B1 Devices based on molecular electronics 失效
标题翻译：基于分子电子学的器件
公开(公告)号：US06673424B1
公开(公告)日：2004-01-06
申请号：US10173939
申请日：2002-06-18
申请人： Stuart Lindsay , John Devens Gust , Xiaodong Cui
发明人： Stuart Lindsay , John Devens Gust , Xiaodong Cui
IPC分类号： B32B700
CPC分类号： H01L51/0595 , B82Y10/00 , H01L51/0075 , Y10S428/91 , Y10T428/12014 , Y10T428/24917 , Y10T428/31678
摘要： Molecular electronic devices and method of making molecular electronic devices having a self-assembled ordered insulating molecular electronic film having insulating molecules attached at one end to a first electrode, and conducting device molecules inserted into the insulating molecular electronic film such that the device molecules are attached at the bottom end to a first electrode and the top end to a second electrode are provided.
摘要翻译：分子电子器件和制造分子电子器件的方法，其具有在一端连接到第一电极的绝缘分子的自组装有序绝缘分子电子膜，以及插入绝缘分子电子膜中的器件分子，使得器件分子附着在第一电极的底端和第二电极的顶端。

2. 发明申请

US20100169090A1 WEIGHTED SEQUENTIAL VARIANCE ADAPTATION WITH PRIOR KNOWLEDGE FOR NOISE ROBUST SPEECH RECOGNITION 有权
标题翻译：用于噪声强调语音识别的先验知识的加权顺序变化适应
公开(公告)号：US20100169090A1
公开(公告)日：2010-07-01
申请号：US12347504
申请日：2008-12-31
申请人： Xiaodong Cui , Kaisheng Yao
发明人： Xiaodong Cui , Kaisheng Yao
IPC分类号： G10L15/20
CPC分类号： G10L15/20
摘要： A method for adapting acoustic models used for automatic speech recognition is provided. The method includes estimating noise in a portion of a speech signal, determining a first estimated variance scaling vector using an estimated 2-order polynomial and the noise estimation, wherein the estimated 2-order polynomial represents a priori knowledge of a dependency of a variance scaling vector on noise, determining a second estimated variance scaling vector using statistics from prior portions of the speech signal, determining a variance scaling factor using the first estimated variance scaling vector and the second estimated variance scaling vector, and using the variance scaling factor to adapt an acoustic model.
摘要翻译：提供了一种用于适应用于自动语音识别的声学模型的方法。该方法包括估计语音信号的一部分中的噪声，使用估计的2阶多项式和噪声估计来确定第一估计方差缩放矢量，其中估计的2阶多项式表示方差缩放的依赖性的先验知识使用来自语音信号的先前部分的统计确定第二估计方差缩放向量，使用第一估计方差缩放向量和第二估计方差缩放矢量确定方差缩放因子，并使用方差缩放因子来适应声学模型。

3. 发明授权

US08180635B2 Weighted sequential variance adaptation with prior knowledge for noise robust speech recognition 有权
标题翻译：加权顺序方差适应与噪声鲁棒语音识别的先验知识
公开(公告)号：US08180635B2
公开(公告)日：2012-05-15
申请号：US12347504
申请日：2008-12-31
申请人： Xiaodong Cui , Kaisheng Yao
发明人： Xiaodong Cui , Kaisheng Yao
IPC分类号： G10L15/20
CPC分类号： G10L15/20
摘要： A method for adapting acoustic models used for automatic speech recognition is provided. The method includes estimating noise in a portion of a speech signal, determining a first estimated variance scaling vector using an estimated 2-order polynomial and the noise estimation. The estimated 2-order polynomial represents a prior knowledge of a dependency of a variance scaling vector on noise, determining a second estimated variance scaling vector using statistics from prior portions of the speech signal, determining a variance scaling factor using the first estimated variance scaling vector and the second estimated variance scaling vector, and using the variance scaling factor to adapt an acoustic model.
摘要翻译：提供了一种用于适应用于自动语音识别的声学模型的方法。该方法包括估计语音信号的一部分中的噪声，使用估计的2阶多项式和噪声估计来确定第一估计方差缩放向量。估计的2阶多项式表示方差缩放矢量对噪声的依赖性的先验知识，使用来自语音信号的先前部分的统计确定第二估计方差缩放矢量，使用第一估计方差缩放矢量确定方差缩放因子和第二估计方差缩放向量，并使用方差缩放因子来适应声学模型。

4. 发明申请

US20050256714A1 Sequential variance adaptation for reducing signal mismatching 审中-公开
标题翻译：用于减少信号不匹配的顺序方差适应
公开(公告)号：US20050256714A1
公开(公告)日：2005-11-17
申请号：US10811596
申请日：2004-03-29
申请人： Xiaodong Cui , Yifan Gong
发明人： Xiaodong Cui , Yifan Gong
IPC分类号： G10L15/00 , G10L15/20
CPC分类号： G10L15/20
摘要： The mismatch between the distributions of acoustic models and features in speech recognition may cause performance degradation. A sequential variance adaptation (SVA) adapts the covariances dynamically based on a sequential EM algorithm. The original covariances in acoustic models are adjusted by scaling factors which are sequentially updated once new collection data is available.
摘要翻译：语音识别中声学模型和特征的分布之间的不匹配可能会导致性能下降。顺序方差适应（SVA）基于顺序EM算法动态地协调协方差。声学模型中的原始协方差通过缩放因子进行调整，一旦新的收集数据可用，则依次更新。

5. 发明申请

US20050216266A1 Incremental adjustment of state-dependent bias parameters for adaptive speech recognition 审中-公开
标题翻译：用于自适应语音识别的状态相关偏差参数的增量调整
公开(公告)号：US20050216266A1
公开(公告)日：2005-09-29
申请号：US10811705
申请日：2004-03-29
申请人： Yifan Gong , Xiaodong Cui
发明人： Yifan Gong , Xiaodong Cui
IPC分类号： G10L15/00 , G10L15/06 , G10L15/14
CPC分类号： G10L15/144 , G10L15/065
摘要： The mismatch between the distributions of acoustic models and features in speech recognition may cause performance degradation. A sequential bias adaptation (SBA) applies state or class dependent biases to the original mean vectors in acoustic models to take into account the mismatch between features and the acoustic models.
摘要翻译：语音识别中声学模型和特征的分布之间的不匹配可能会导致性能下降。顺序偏置适应（SBA）将声学模型中的状态或类依赖偏移应用于原始平均矢量，以考虑特征与声学模型之间的不匹配。

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