公开(公告)号：US20130262105A1

公开(公告)日：2013-10-03

申请号：US13433186

申请日：2012-03-28

申请人： Jian Luan ,  Linfang Wang ,  Hairong Xia ,  Sheng Zhao ,  Daniela Braga

发明人： Jian Luan ,  Linfang Wang ,  Hairong Xia ,  Sheng Zhao ,  Daniela Braga

IPC分类号： G10L15/26

CPC分类号： G10L15/083 ,  G10L13/08 ,  G10L15/197

摘要： Dynamic features are utilized with CRFs to handle long-distance dependencies of output labels. The dynamic features present a probability distribution involved in explicit distance from/to a special output label that is pre-defined according to each application scenario. Besides the number of units in the segment (from the previous special output label to the current unit), the dynamic features may also include the sum of any basic features of units in the segment. Since the added dynamic features are involved in the distance from the previous specific label, the searching lattice associated with Viterbi searching is expanded to distinguish the nodes with various distances. The dynamic features may be used in a variety of different applications, such as Natural Language Processing, Text-To-Speech and Automatic Speech Recognition. For example, the dynamic features may be used to assist in prosodic break and pause prediction.

摘要翻译： CRF利用动态特征来处理输出标签的长距离依赖关系。 动态特征呈现出根据每个应用场景预定义的特定输出标签的显式距离所涉及的概率分布。 除了段中的单位数（从前一个特殊输出标签到当前单位），动态特征还可以包括段中单位的任何基本特征的总和。 由于添加的动态特征涉及到与先前特定标签的距离，因此扩展了与维特比搜索相关联的搜索点，以区分不同距离的节点。 动态特征可用于各种不同的应用，如自然语言处理，文本到语音和自动语音识别。 例如，动态特征可以用于辅助韵律休息和暂停预测。

公开(公告)号：US09037460B2

公开(公告)日：2015-05-19

申请号：US13433186

申请日：2012-03-28

申请人： Jian Luan ,  Linfang Wang ,  Hairong Xia ,  Sheng Zhao ,  Daniela Braga

发明人： Jian Luan ,  Linfang Wang ,  Hairong Xia ,  Sheng Zhao ,  Daniela Braga

IPC分类号： G10L15/26 ,  G10L15/08 ,  G10L13/08 ,  G10L15/197

CPC分类号： G10L15/083 ,  G10L13/08 ,  G10L15/197

摘要： Dynamic features are utilized with CRFs to handle long-distance dependencies of output labels. The dynamic features present a probability distribution involved in explicit distance from/to a special output label that is pre-defined according to each application scenario. Besides the number of units in the segment (from the previous special output label to the current unit), the dynamic features may also include the sum of any basic features of units in the segment. Since the added dynamic features are involved in the distance from the previous specific label, the searching lattice associated with Viterbi searching is expanded to distinguish the nodes with various distances. The dynamic features may be used in a variety of different applications, such as Natural Language Processing, Text-To-Speech and Automatic Speech Recognition. For example, the dynamic features may be used to assist in prosodic break and pause prediction.

摘要翻译： CRF利用动态特征来处理输出标签的长距离依赖性。 动态特征呈现出根据每个应用场景预定义的特定输出标签的显式距离所涉及的概率分布。 除了段中的单位数（从前一个特殊输出标签到当前单位），动态特征还可以包括段中单位的任何基本特征的总和。 由于添加的动态特征涉及到与先前特定标签的距离，因此扩展了与维特比搜索相关联的搜索点，以区分不同距离的节点。 动态特征可用于各种不同的应用，如自然语言处理，文本到语音和自动语音识别。 例如，动态特征可以用于辅助韵律休息和暂停预测。