会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 6. 发明申请
    • Touch Table Structure
    • 触摸表结构
    • US20120050223A1
    • 2012-03-01
    • US12941032
    • 2010-11-06
    • Xin-Min WUJian-Guo LiWei TangHong ShenQing Guo
    • Xin-Min WUJian-Guo LiWei TangHong ShenQing Guo
    • G06F3/042
    • G06F3/0425G06F1/181
    • A touch table structure is disclosed. The touch table structure includes a touch tabletop; and a table body disposed below the touch tabletop, the table body including a plurality of side plates disposed on a plurality of side surfaces of the table body, and at least one sliding door disposed on at least one side surface of the table body. The touch tabletop can be prevented from dust and water and therefore can be used in restaurants, pubs, etc. The computer disposed in the touch table structure can be taken out or be exposed out by opening the sliding door, such that the users can change the hardware in the computer according to their demand or use the optical disk drive or the connection port in the exposed computer to install application software freely. The computer can be disposed in the receiving space of the touch table structure in one side, and various small items can be disposed in the receiving space of the touch table structure in the other side.
    • 公开了一种触摸台结构。 触摸桌结构包括触摸桌面; 以及设置在所述台面下方的台体,所述台体具有设置在台主体的多个侧面上的多个侧板以及设置在台主体的至少一个侧面上的至少一个滑动门。 触摸台面可防止灰尘和水分,因此可用于餐厅,酒吧等。设置在触摸台结构中的计算机可以通过打开滑动门而被取出或暴露出来,使得用户可以改变 计算机中的硬件根据自己的要求或使用光盘驱动器或连接端口在暴露的计算机中自由安装应用软件。 计算机可以一侧设置在触摸台结构的接收空间中,并且可以在另一侧的触摸台结构的接收空间中设置各种小物品。
    • 7. 发明授权
    • Method and system to scale down a decision tree-based hidden markov model (HMM) for speech recognition
    • 用于缩小基于决策树的隐马尔可夫模型(HMM)用于语音识别的方法和系统
    • US07472064B1
    • 2008-12-30
    • US10019381
    • 2000-09-30
    • Qing GuoYonghong YanBaosheng Yuan
    • Qing GuoYonghong YanBaosheng Yuan
    • G10L15/14
    • G10L15/142G10L15/08G10L2015/085
    • A method and system are provided in which a decision tree-based model (“general model”) is scaled down (“trim-down”) for a given task. The trim-down model can be adapted for the given task using task specific data. The general model can be based on a hidden markov model (HMM). By allowing a decision tree-based acoustic model (“general model”) to be scaled according to the vocabulary of the given task, the general model can be configured dynamically into a trim-down model, which can be used to improve speech recognition performance and reduce system resource utilization. Furthermore, the trim-down model can be adapted/adjusted according to task specific data, e.g., task vocabulary, model size, or other like task specific data.
    • 提供了一种方法和系统,其中对于给定任务,基于决策树的模型(“一般模型”)被缩小(“缩小”)。 可以使用特定于任务的数据来适应给定任务的微调模型。 一般模型可以基于隐马尔可夫模型(HMM)。 通过允许基于决策树的声学模型(“通用模型”)根据给定任务的词汇进行缩放,通用模型可以动态地配置到缩小模型中,该模型可用于改善语音识别性能 并降低系统资源利用率。 此外,缩减模型可以根据任务特定数据(例如,任务词汇,模型大小或其他类似的任务特定数据)进行调整/调整。