-
公开(公告)号：WO2014183368A1
公开(公告)日：2014-11-20
申请号：PCT/CN2013/084827
申请日：2013-10-08
Inventor： LIU, Qiuge
IPC: H04L29/08
CPC classification number: H04L69/22 , H04L67/1097
Abstract: Systems and methods are provided for voice data processing. For example, a first data packet included in voice data transmitted by a client is received; the first data packet is stored in a storage area; whether to process one or more second data packets stored in the storage area is determined based on at least information associated with a type of the first data packet and a current storage state of the storage area; in response to a determination to process the second data packets, voice resources are applied for; and the second data packets stored in the storage area are processed using the voice resources.
Abstract translation: 为语音数据处理提供了系统和方法。 例如，接收由客户端发送的语音数据中包含的第一数据分组; 第一数据包被存储在存储区域中; 至少基于与第一数据分组的类型相关联的信息和存储区域的当前存储状态来确定是否处理存储在存储区域中的一个或多个第二数据分组; 响应于处理第二数据分组的确定，应用语音资源; 并且使用语音资源来处理存储在存储区域中的第二数据分组。
-
2.发明申请
公开(公告)号：WO2014117584A1
公开(公告)日：2014-08-07
申请号：PCT/CN2013/087998
申请日：2013-11-28
Inventor： LIU, Qiuge
IPC: G10L15/30
Abstract: Systems, methods and/or devices used to enable load balancing in a speech recognition system are provided. The method includes, at a speech access server: (1) initializing the speech access server, (2) receiving a speech request from a terminal, (3) determining, in accordance with a predefined load balancing algorithm, a first speech recognition server to process the speech request, (4) determining whether the first speech recognition server is available for processing, (5) if the first speech recognition server is available, forwarding the speech request to the first speech recognition server for processing, and (6) if the first speech recognition server is not available: (a) determining whether other speech recognition servers are available for processing, and (b) if a second speech recognition server is available, forwarding the speech request to the second speech recognition server for processing.
Abstract translation: 提供了用于在语音识别系统中实现负载平衡的系统，方法和/或设备。 该方法在语音接入服务器中包括：（1）初始化语音接入服务器，（2）从终端接收语音请求，（3）根据预定义的负载均衡算法，确定第一语音识别服务器 处理语音请求，（4）确定第一语音识别服务器是否可用于处理，（5）如果第一语音识别服务器可用，则将语音请求转发到第一语音识别服务器进行处理，以及（6）如果 第一语音识别服务器不可用：（a）确定其他语音识别服务器是否可用于处理，以及（b）如果第二语音识别服务器可用，则将语音请求转发到第二语音识别服务器进行处理。
-
3.发明申请
公开(公告)号：WO2014117553A1
公开(公告)日：2014-08-07
申请号：PCT/CN2013/086618
申请日：2013-11-06
Inventor： LIU, Haibo , WANG, Eryu , ZHANG, Xiang , LU, Li , YUE, Shuai , LIU, Qiuge , CHEN, Bo , LIU, Jian , LI, Lu
CPC classification number: G10L15/04 , G10L15/1815
Abstract: A method of processing information content based on a language model is performed at a computer. The method includes the following steps: identifying a plurality of expressions in the information content that is queued to be processed; dividing the plurality of expressions into a plurality of characteristic units according to semantic features and predetermined characteristics associated with each of the plurality of characteristic units, each characteristic unit including a subset of the plurality of expressions and the predetermined characteristics at least including a respective integer number of expressions that are included in the characteristic unit; extracting, from the language model, a plurality of probabilities for a plurality of punctuation marks associated with each of the plurality of characteristic units; and in accordance with the extracted probabilities, associating a respective punctuation mark with each of the plurality of characteristic units included in the information content.
Abstract translation: 在计算机上执行基于语言模型处理信息内容的方法。 该方法包括以下步骤：识别排队等待处理的信息内容中的多个表达; 根据与多个特征单元中的每一个相关联的语义特征和预定特征将多个表达式划分为多个特征单元，每个特征单元包括多个表达式的子集和预定特征，至少包括相应的整数 包含在特征单元中的表达式; 从所述语言模型中提取与所述多个特征单元中的每一个相关联的多个标点符号的多个概率; 并且根据所提取的概率，将相应的标点符号与包括在信息内容中的多个特征单元中的每一个相关联。
-
-
Search Results
3
records
(took 0.01 seconds)
