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
    • 11. 发明申请
    • Speech Quality Evaluation System and Storage Medium Readable by Computer Therefor
    • 语音质量评估系统和计算机可读取的存储介质
    • US20110246192A1
    • 2011-10-06
    • US13025970
    • 2011-02-11
    • Takeshi HOMMA
    • Takeshi HOMMA
    • G10L21/02
    • G10L25/69
    • In prediction of a speech quality evaluation score such as a phone speech, even when a background noise exists, a subjective opinion score is predicted with high precision. A speech quality evaluation system that outputs a predicted value of the subjective opinion score for an evaluation speech such as a far-end speech of a phone, includes a speech distortion calculation unit conducts, after calculating frequency characteristics of the evaluation speech, a process of subtracting given frequency characteristics from frequency characteristics of the evaluation speech, and calculates the speech distortion on the basis of the frequency characteristics after the subtracting process has been conducted, and a subjective evaluation prediction unit that calculates the predicted value of the subjective opinion score on the basis of the speech distortion.
    • 在预测诸如电话语音的语音质量评价分数时,即使存在背景噪声,也可以高精度地预测主观意见分数。 输出诸如电话的远端语音等评价语音的主观意见分数的预测值的语音质量评价系统包括语音失真计算单元,在计算了评价语音的频率特性之后,进行以下处理: 根据评估语音的频率特性减去给定的频率特性,并且基于在减法处理之后的频率特性来计算语音失真;以及主观评估预测单元,其计算主观评价预测值 语音失真的基础。
    • 18. 发明申请
    • INFORMATION RETRIEVAL APPARATUS, INFORMATIN RETRIEVAL SYSTEM, AND INFORMATION RETRIEVAL METHOD
    • 信息检索设备,信息检索系统和信息检索方法
    • US20090234847A1
    • 2009-09-17
    • US12368520
    • 2009-02-10
    • Takeshi HOMMAHiroaki KokuboHisashi Takahashi
    • Takeshi HOMMAHiroaki KokuboHisashi Takahashi
    • G06F17/30G10L15/04
    • G01C21/3611
    • Provided is an information retrieval method including: retrieving, by a computer, a name including input characters from a database for storing the name, an attribute word associated with the name, and a degree of relevance between the name and the attribute word; outputting the retrieved name as a candidate name; and extracting an attribute word associated with the candidate name, the extracting including: calculating a degree of independency indicating a degree of difference between the extracted attribute words, a degree of coverage indicating an extent to which the combination of the extracted attribute words covers the candidate names, and a degree of equality of a number of corresponding candidate names for each attribute word; and calculating a score of the combination of the attribute words based on at least one of the independency, the coverage and the equality to output the combinations of the attribute words to an output unit.
    • 提供一种信息检索方法,包括:由计算机检索包括用于存储名称的数据库中的输入字符的名称,与名称相关联的属性字以及名称和属性字之间的相关程度; 将所检索的名称输出为候选名称; 提取与所述候选名称相关联的属性字,所述提取包括:计算指示所提取的属性字之间的差异程度的独立度,所述覆盖程度指示所提取的属性字的组合覆盖所述候选者的程度 名称和每个属性词的相应候选名称的数目相等程度; 以及基于所述独立性,覆盖范围和相等性中的至少一个来计算所述属性词的组合的得分,以将所述属性词的组合输出到输出单元。