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
    • 8. 发明申请
    • FREQUENCY CONVERSION CIRCUIT, FREQUENCY CONVERSION METHOD, AND ELECTRONIC APPARATUS
    • 频率转换电路,频率转换方法和电子设备
    • US20110292290A1
    • 2011-12-01
    • US13115038
    • 2011-05-24
    • Tadashi Aizawa
    • Tadashi Aizawa
    • H04N5/21
    • H03D7/165
    • A frequency conversion circuit includes: a phase shifter that generates a first signal and a second signal having a phase difference of 90 degrees from the first signal; a first mixer that multiplies the first signal by a local oscillation signal; a second mixer that multiplies the second signal by the local oscillation signal; a first filter that extracts a signal component of an intermediate frequency from the output signal of the first mixer; a second filter that extracts a signal component of the intermediate frequency from the output signal of the second mixer; an image signal remover that removes an image signal from the output signals of the first and second filters; and a phase shift quantity adjuster that adjusts a phase shift quantity of the signal in the phase shifter based on the output signal of the image signal remover at a predetermined time.
    • 频率转换电路包括:移相器,其产生与第一信号相差90度的第一信号和第二信号; 第一混频器,将第一信号乘以本地振荡信号; 第二混频器,将第二信号乘以本地振荡信号; 第一滤波器,从第一混频器的输出信号中提取中频信号分量; 第二滤波器,从第二混频器的输出信号中提取中频信号分量; 图像信号去除器,其从第一和第二滤波器的输出信号中去除图像信号; 以及相移量调整器,其基于在预定时间的图像信号去除器的输出信号来调整移相器中的信号的相移量。
    • 10. 发明授权
    • Similar word discrimination method and its apparatus
    • 类似词辨识方法及其装置
    • US6038531A
    • 2000-03-14
    • US10621
    • 1998-01-22
    • Yasunaga MiyazawaHiroshi HasegawaMitsuhiro InazumiTadashi Aizawa
    • Yasunaga MiyazawaHiroshi HasegawaMitsuhiro InazumiTadashi Aizawa
    • G10L15/16G10L9/06
    • G10L15/16
    • A method is provided which performs word recognition using the dynamic recurrent neural networks (DRNN) model and which is able to discriminate, with high precision, similar words for which misrecognition often occurs. When the vocal sounds of some words are input, the DRNN output corresponding to the input word vocal data is generated by the word detection signal output component using the DRNN word model and encoded into coded data by using a code book. When the DRNN output from the word detection signal output component has a correctness of a predetermined or greater level, a processor establishes a fixed period that includes the characteristic components of the input words in the DRNN output. The processor then examines the code data in the established fixed period. Discrimination of input words and words that are similar to the input words is accomplished on the basis of the examination results.
    • 提供了一种使用动态循环神经网络(DRNN)模型执行字识别的方法,其能够以高精度区分经常发生错误识别的相似词。 当输入一些单词的声音时,使用DRNN字模型,通过字检测信号输出分量产生对应于输入字语音数据的DRNN输出,并通过使用码本编码成编码数据。 当来自字检测信号输出分量的DRNN输出具有预定或更高电平的正确性时,处理器建立包括DRNN输出中的输入字的特征分量的固定周期。 然后,处理器在建立的固定时间段内检查代码数据。 根据检查结果,对与输入单词相似的输入单词和单词进行歧视。