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
    • 51. 发明授权
    • Variable speed speech synthesis by interpolation between fast and slow
speech data
    • 通过快速和慢速语音数据之间的插值进行变速语音合成
    • US4817161A
    • 1989-03-28
    • US27711
    • 1987-03-19
    • Hiroshi Kaneko
    • Hiroshi Kaneko
    • G10L21/00G10L13/06G10L13/08G01L1/00
    • G10L13/08
    • The present invention relates to apparatus and method of synthesizing speech for synthesis units which form words. The method comprises the steps of generating, for each of multiple utterances of a given synthesis unit, a series of frames of analysis data, the frames being generated one frame every To period, each frame in each series having a parameter value associated therewith; where one series results in M frames of data, partitioning each other series of frames to provide M time intervals each of which corresponds to one of the frames of said one series; synthesizing speech data for the synthesis unit, the synthesized speech data corresponding to a sequence of time intervals wherein each time interval has an associated parameter value, said synthesizing step including the steps of:(a) representing the synthesized data as a sequence of M time intervals, interpolating each ith time interval (where 1.ltoreq.i.ltoreq.M) for the synthesized data from the respective ith intervals corresponding to the utterance; and(b) interpolating the parameter value at each ith time interval of the synthesized data from the parameter values for the respective ith intervals corresponding to the utterances.
    • 52. 发明授权
    • Character recognition system
    • 字符识别系统
    • US4163214A
    • 1979-07-31
    • US902175
    • 1978-05-02
    • Kazuaki KomoriTakahiko KawataniHiroshi KanekoKenichiro Ishii
    • Kazuaki KomoriTakahiko KawataniHiroshi KanekoKenichiro Ishii
    • G06K9/62G06K9/80G06K9/12
    • G06K9/50G06K9/80G06K2209/01
    • A character in a pattern area is optically scanned and the scanned black and white signal cells of the character are stored in a digital memory. The character in the digital memory is recognized through an initial feature extraction process, unification process, concentration process, and recognition process. In the initial feature extraction process each cell thus scanned is encoded according to the presence of a character line or a black cell in a predetermined direction from each cell. The unification process unifies the code of each cell according to a predetermined algorithm, and the concentration process provides a concentrated code for each cell. The recognition process counts each of the concentrated codes and determines the class to which the character to be recognized belongs when the number of particular concentrated codes reaches a predetermined threshold which is defined for each class. The stepping up in the counting of the concentrated code in the recognition process is performed with some conditions, in which, for instance, only when a predetermined concentrated code appears a predetermined number of times, the particular concentrated code is initiated for counting.
    • 对图案区域中的字符进行光学扫描,将字符的扫描的黑白信号单元存储在数字存储器中。 数字存储器中的字符通过初始特征提取过程,统一处理,浓度处理和识别过程来识别。 在初始特征提取处理中,根据来自每个单元的预定方向的字符行或黑色单元的存在对这样扫描的每个单元进行编码。 统一过程根据预定算法统一每个单元的代码,并且浓度处理为每个单元提供集中代码。 识别处理对每个集中代码进行计数,并且当特定集中代码的数量达到为每个类定义的预定阈值时,确定要识别的字符属于的类。 在识别处理中对集中代码的计数中的增加是用一些条件来执行的,其中例如仅在预定的集中代码出现预定次数时才启动特定的集中代码进行计数。