利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

62 条记录 (耗时 0.039 秒)

    Speech recognition apparatus
    11.
    发明授权
    Speech recognition apparatus 失效
    语音识别装置

    公开(公告)号：US5390280A

    公开(公告)日：1995-02-14

    申请号：US974230

    申请日：1992-11-10

    申请人： Yasuhiko Kato ,  Masao Watari ,  Miyuki Tanaka ,  Akihiko Fujinaka

    发明人： Yasuhiko Kato ,  Masao Watari ,  Miyuki Tanaka ,  Akihiko Fujinaka

    IPC分类号： G10L15/06 ,  G10L15/20 ,  G10L5/06 ,  G10L9/18

    CPC分类号： G10L15/20

    摘要： A noise signal supplied from a microphone by way of an analog to digital converter is Fourier converted to calculate a power spectrum of the noise signal by a Fourier converting section. A system controller compares an average value of the power spectrum of the signal being outputted from the microphone at present and an average value of the power spectrum of a noise signal stored in a noise memory at present with each other. When the system controller determines that the difference between the average value of the power spectrum of the signal being outputted from the microphone at present and the average value of the power spectrum of the noise signal stored in the noise memory at present is higher than a predetermined reference value, it outputs a controlling signal to a sound storing and reading out section to store the signal being outputted from the microphone at present into the noise memory. Consequently, the signal being outputted from the microphone at present is stored into the noise memory in place of the noise signal stored in the noise signal at present.

    摘要翻译： 通过模数转换器从麦克风提供的噪声信号被傅里叶变换，以通过傅里叶变换部分计算噪声信号的功率谱。 目前，系统控制器将目前从麦克风输出的信号的功率谱的平均值和当前存储在噪声存储器中的噪声信号的功率谱的平均值进行比较。 当系统控制器确定目前从麦克风输出的信号的功率谱的平均值与当前存储在噪声存储器中的噪声信号的功率谱的平均值之间的差异高于预定值 参考值，它将控制信号输出到声音存储和读出部分，以将当前从麦克风输出的信号存储到噪声存储器中。 因此，目前从麦克风输出的信号被代替存储在噪声信号中的噪声信号而被存储在噪声存储器中。

    Speech recognition system
    12.
    发明授权
    Speech recognition system 失效
    语音识别系统

    公开(公告)号：US5355432A

    公开(公告)日：1994-10-11

    申请号：US928448

    申请日：1992-08-12

    申请人： Miyuki Tanaka ,  Masao Watari ,  Yasuhiko Kato

    发明人： Miyuki Tanaka ,  Masao Watari ,  Yasuhiko Kato

    IPC分类号： G10L15/02 ,  G10L15/00 ,  G10L15/10 ,  G10L5/06

    CPC分类号： G10L15/10

    摘要： A speech recognition system includes an acoustic analyzer which produces a time sequence of acoustic parameters from an input speech signal in an utterance boundary thereof, and estimates a trajectory in a parameter space from the time sequence of acoustic parameters. The trajectory is re-sampled in the parameter space at predetermined constant intervals sequentially each time the acoustic parameters are produced by the acoustic analyzing means, thereby producing an input utterance pattern. The input utterance pattern is matched with reference speech patterns to recognize the input speech signal. The speech recognition system also has an utterance boundary detector for detecting the utterance boundary of the input speech signal. The trajectory is re-sampled while the utterance boundary is being detected by the utterance boundary detector.

    摘要翻译： 语音识别系统包括声学分析器，其从其语音边界中的输入语音信号产生声学参数的时间序列，并根据声学参数的时间序列估计参数空间中的轨迹。 每当由声学分析装置产生声学参数时，以预定的恒定间隔在参数空间中重新采样轨迹，从而产生输入的发音模式。 输入语音模式与参考语音模式相匹配，以识别输入语音信号。 语音识别系统还具有用于检测输入语音信号的话语边界的话语边界检测器。 当话语边界检测器检测到话语边界时，重新采样轨迹。

    Speech recognition adapter for telephone system
    13.
    依法登记的发明
    Speech recognition adapter for telephone system 失效
    语音识别适配器电话系统

    公开(公告)号：USH1646H

    公开(公告)日：1997-05-06

    申请号：US59035

    申请日：1993-05-07

    申请人： Yasuhiko Kato ,  Masao Watari ,  Miyuki Tanaka

    发明人： Yasuhiko Kato ,  Masao Watari ,  Miyuki Tanaka

    IPC分类号： G10L19/00 ,  G10L15/00 ,  H04M1/27 ,  H04M1/64 ,  H04M1/652 ,  H04M1/26

    CPC分类号： H04M1/652 ,  H04M1/271

    摘要： A voice responsive telephone adapter, or speech recognition adapter, for use with a telephone set having for example, telephone answering capabilities. The voice responsive telephone adapter may be used to dial telephone numbers or control auxiliary functional capabilities relating the message playback, for example in response to recognized verbal commands, such as, for example, names or operational functions.

    摘要翻译： 语音应答电话适配器或语音识别适配器，用于具有例如电话应答功能的电话机。 语音应答电话适配器可以用于拨打电话号码或控制与消息回放相关的辅助功能能力，例如响应于所识别的口头命令，例如姓名或操作功能。

    Audio processor
    17.
    发明授权
    Audio processor 失效
    音频处理器

    公开(公告)号：US08107617B2

    公开(公告)日：2012-01-31

    申请号：US11681025

    申请日：2007-03-01

    申请人： Yohei Sakuraba ,  Yasuhiko Kato ,  Nobuyuki Kihara

    发明人： Yohei Sakuraba ,  Yasuhiko Kato ,  Nobuyuki Kihara

    IPC分类号： H04M9/08

    CPC分类号： H04M9/082

    摘要： An audio processor of a loud speech communication system including a speaker and a microphone is provided. The audio processor includes: an adaptive filter wherein an amount of update in a learning event is set to an arbitrary value, and a filter coefficient is serially determined corresponding to the set amount of update; a semi-fixed filter adapted to an echo cancellation process of an audio input signal input from the microphone; adaptive filter assessment unit that calculates a length of an update vector based on the filter coefficient determined by the adaptive filter and a length of an update vector based on a filter coefficient set in the semi-fixed filter and that performs assessment of the filter coefficients in accordance with the update vectors; and coefficient specifying unit that sets an optimal filter coefficient among the filter coefficients into the semi-fixed filter in accordance with the result of the assessment of the filter coefficients performed by the adaptive filter assessment unit.

    摘要翻译： 提供了包括扬声器和麦克风的大声语音通信系统的音频处理器。 音频处理器包括：自适应滤波器，其中将学习事件中的更新量设置为任意值，并且根据设定的更新量对滤波器系数进行串行确定; 适用于从麦克风输入的音频输入信号的回波消除处理的半固定滤波器; 自适应滤波器评估单元，其基于由所述自适应滤波器确定的滤波器系数和基于在所述半固定滤波器中设置的滤波器系数的更新向量的长度来计算更新向量的长度，并且执行所述滤波器系数的估计 按照更新向量; 以及系数指定单元，其根据由自适应滤波器评估单元执行的滤波器系数的评估结果，将滤波器系数中的最佳滤波器系数设置为半固定滤波器。

    Microphone apparatus
    18.
    发明授权
    Microphone apparatus 失效
    麦克风设备

    公开(公告)号：US07991166B2

    公开(公告)日：2011-08-02

    申请号：US11353088

    申请日：2006-02-14

    申请人： Nobuyuki Kihara ,  Yoshikazu Takahashi ,  Yasuhiko Kato

    发明人： Nobuyuki Kihara ,  Yoshikazu Takahashi ,  Yasuhiko Kato

    IPC分类号： H04R3/00 ,  H04R1/02 ,  G10L11/00 ,  G10L19/00

    CPC分类号： H04R1/406 ,  H04R19/016 ,  H04R2201/401 ,  H04R2430/20

    摘要： A microphone apparatus for processing and outputting an output signal of a microphone array including at least nine microphones includes a directivity function processing circuit that converts the output signal of the microphone array into a unidirectional signal and that outputs the unidirectional signal. The directivity function processing circuit expands a directivity function whose variable is an incident angle of an acoustic wave into a Fourier series up to at least third order. The variable in the expanded expression is produced from output signals of the microphones forming the microphone array.

    摘要翻译： 用于处理和输出包括至少九个麦克风的麦克风阵列的输出信号的麦克风装置包括将麦克风阵列的输出信号转换为单向信号并输出​​单向信号的方向性功能处理电路。 指向性函数处理电路将可变为声波的入射角的方向性函数扩展为至少三阶的傅里叶级数。 扩展表达式中的变量由形成麦克风阵列的麦克风的输出信号产生。

    SOUND SIGNAL PROCESSOR AND DELAY TIME SETTING METHOD
    19.
    发明申请
    SOUND SIGNAL PROCESSOR AND DELAY TIME SETTING METHOD 审中-公开
    声信号处理器和延迟时间设置方法

    公开(公告)号：US20100183163A1

    公开(公告)日：2010-07-22

    申请号：US12663332

    申请日：2008-06-05

    申请人： Takeshi Matsui ,  Yasuhiko Kato ,  Nobuyuki Kihara ,  Hideki Kishi ,  Yasuhiro Kodama ,  Yohei Sakuraba

    发明人： Takeshi Matsui ,  Yasuhiko Kato ,  Nobuyuki Kihara ,  Hideki Kishi ,  Yasuhiro Kodama ,  Yohei Sakuraba

    IPC分类号： H04B3/20

    CPC分类号： H04R3/02 ,  H04M9/082

    摘要： An echo canceller formed of an adaptive filter is designed such that even under a condition where a system transmission delay is undefined, an appropriate delay time can be set in a delay circuit that absorbs a system delay, and that an effective echo cancellation effect can always be achieved. A time difference of a transmission path until a reproduction audio signal input to the delay circuit is input as a processing target signal of an adaptive filter system through a space between a speaker and a microphone is determined, and the delay time corresponding to this time difference is set in the delay circuit. At this time, the speaker and the microphone are placed so that the distance therebetween is small, and the delay time of the delay circuit is set to 0. Thus, the determined time difference indicates a system transmission delay in the above transmission path. That is, an accurate delay time corresponding to the system transmission delay can be set in the delay circuit.

    摘要翻译： 由自适应滤波器构成的回波消除器被设计成即使在系统传输延迟未定义的条件下，也可以在吸收系统延迟的延迟电路中设置适当的延迟时间，并且有效的回波消除效果可以始终 实现。 确定通过扬声器和麦克风之间的空间输入到延迟电路输入的再现音频信号之间的传输路径的时间差作为自适应滤波器系统的处理目标信号，并且确定对应于该时间差的延迟时间 被设置在延迟电路中。 此时，扬声器和麦克风被放置成使得它们之间的距离小，并且延迟电路的延迟时间被设置为0.因此，所确定的时间差表示上述传输路径中的系统传输延迟。 也就是说，可以在延迟电路中设置与系统传输延迟相对应的准确的延迟时间。

    Information processing apparatus and method, recording medium, and program for converting text data to audio data
    20.
    发明授权
    Information processing apparatus and method, recording medium, and program for converting text data to audio data 失效
    信息处理装置和方法，记录介质和用于将文本数据转换为音频数据的程序

    公开(公告)号：US07676368B2

    公开(公告)日：2010-03-09

    申请号：US10188711

    申请日：2002-07-02

    申请人： Utaha Shizuka ,  Satoshi Fujimura ,  Yasuhiko Kato

    发明人： Utaha Shizuka ,  Satoshi Fujimura ,  Yasuhiko Kato

    IPC分类号： G10L13/08 ,  G10L21/00 ,  G10L21/06

    CPC分类号： G10L13/00 ,  H04M3/4938 ,  H04M3/5322 ,  H04M2201/60

    摘要： The present invention is intended to perform text-to-speech conversion by replacing URLs and electronic mail addresses included in the text data of electronic mail by registered predetermined words. A mail watcher application control section executes the processing for converting electronic mail received by a MAPI mailer into speech data. The mail watcher application control section outputs URLs and electronic mail addresses included in the text data of electronic mail supplied from the MAPI mailer to a URL and mail address filter to replace them by registered predetermined names. Of the entered texts, the URL and mail address filter compares the URL or mail address included in the entered text with those registered in the URL and mail address table. If a the URL or mail address of the entered text is found matching, the URL and mail address filter replace it by the registered name and outputs it to the mail watcher application control section.

    摘要翻译： 本发明旨在通过用注册的预定字替换包括在电子邮件的文本数据中的URL和电子邮件地址来执行文本到语音转换。 邮件观察者应用程序控制部分执行将由MAPI邮寄员接收的电子邮件转换为语音数据的处理。 邮件观察者应用程序控制部分输出从MAPI邮寄者提供的电子邮件的文本数据中包含的URL和电子邮件地址到URL和邮件地址过滤器，以通过登记的预定名称替换它们。 在输入的文本中，URL和邮件地址过滤器将输入的文本中包含的URL或邮件地址与URL和邮件地址表中注册的URL进行比较。 如果输入的文本的URL或邮件地址匹配，URL和邮件地址过滤器将其替换为注册名称，并将其输出到邮件观察器应用程序控制部分。