利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

16 条记录 (耗时 0.02 秒)

    Interactive speech recognition with varying responses for time of day and environmental conditions
    3.
    发明授权
    Interactive speech recognition with varying responses for time of day and environmental conditions 失效
    互动语音识别，具有时间和环境条件的不同响应

    公开(公告)号：US5802488A

    公开(公告)日：1998-09-01

    申请号：US609336

    申请日：1996-02-29

    申请人： Isao Edatsune

    发明人： Isao Edatsune

    IPC分类号： A63H3/33 ,  A63H5/00 ,  A63H13/02 ,  A63H30/02 ,  G10L13/00 ,  G10L15/00 ,  G10L15/18 ,  G10L15/22 ,  G10L15/24 ,  G10L15/26 ,  G10L15/28 ,  G10L5/06 ,  G10L5/02

    CPC分类号： G10L13/00 ,  G10L15/26 ,  A63H2200/00

    摘要： The invention improves recognition rates by providing an interactive speech recognition device that performs recognition by taking situational and environmental changes into consideration, thus enabling interactions that correspond to situational and environmental changes. The invention comprises a speech analysis unit that creates a speech data pattern corresponding to the input speech; a timing circuit for generating time data, for example, as variable data; a coefficient setting unit receiving the time data from the timing circuit and generating weighting coefficients that change over time, in correspondence to the content of each recognition target speech; a speech recognition unit that receives the speech data pattern of the input speech from the speech analysis unit, and that at the same time obtains a weighting coefficient in effect for a pre-registered recognition target speech at the time from the coefficient setting unit, that computes final recognition data by multiplying the recognition data corresponding to each recognition target speech by its corresponding weighting coefficient, and that recognizes the input speech based on the computed final recognition result; a speech synthesis unit for outputting speech synthesis data based on the recognition data that takes the weighting coefficient into consideration; and a drive control unit for transmitting the output from the speech synthesis unit to the outside.

    摘要翻译： 本发明通过提供通过考虑情境和环境变化来执行识别的交互式语音识别装置来提高识别率，从而实现与情境和环境变化相对应的交互。 本发明包括：语音分析单元，其创建与所述输入语音相对应的语音数据模式; 用于产生时间数据的定时电路，例如作为可变数据; 系数设定单元，根据每个识别目标语音的内容，从定时电路接收时间数据并生成随时间变化的加权系数; 语音识别单元，其从所述语音分析单元接收所述输入语音的语音数据模式，并且同时从所述系数设定单元获取对于预先登录的识别目标语音的加权系数， 通过将对应于每个识别目标语音的识别数据乘以其对应的加权系数来计算最终识别数据，并且基于所计算的最终识别结果识别输入语音; 语音合成单元，用于基于考虑加权系数的识别数据输出语音合成数据; 以及驱动控制单元，用于将来自语音合成单元的输出发送到外部。

    Interactive speech recognition combining speaker-independent and speaker-specific word recognition, and having a response-creation capability
    4.
    发明授权
    Interactive speech recognition combining speaker-independent and speaker-specific word recognition, and having a response-creation capability 失效
    具有独立于扬声器和扬声器特定字识别功能的交互式语音识别功能，具有响应创建能力

    公开(公告)号：US5794204A

    公开(公告)日：1998-08-11

    申请号：US536563

    申请日：1995-09-29

    申请人： Yasunaga Miyazawa ,  Mitsuhiro Inazumi ,  Hiroshi Hasegawa ,  Isao Edatsune

    发明人： Yasunaga Miyazawa ,  Mitsuhiro Inazumi ,  Hiroshi Hasegawa ,  Isao Edatsune

    IPC分类号： G10L15/28 ,  G10L13/00 ,  G10L13/04 ,  G10L15/00 ,  G10L15/06 ,  G10L15/18 ,  G10L9/06 ,  G10L5/02

    CPC分类号： G10L15/075 ,  G10L2015/0638 ,  G10L2015/088

    摘要： A technique for improving speech recognition in low-cost, speech interactive devices. This technique calls for implementing a speaker-specific word enrollment and detection unit in parallel with a word detection unit to permit comprehension of spoken commands or messages issued by binary questions when no recognizable words are found. Preferably, specific speaker detection will be based on the speaker's own personal list of words or expression. Other facets include complementing non-specific pre-registered word characteristic information with individual, speaker-specific verbal characteristics to improve recognition in cases where the speaker has unusual speech mannerisms or accent and response alteration in which speaker-specification registration functions are leveraged to provide access and permit changes to a predefined responses table according to user needs and tastes.

    摘要翻译： 一种用于在低成本语音交互设备中改善语音识别的技术。 该技术要求与字检测单元并行地实现与扬声器相关的字注册和检测单元，以便在找不到可识别字时允许理解由二进制问题发出的口语命令或消息。 优选地，具体的说话者检测将基于说话者自己的单词或表达的个人列表。 其他方面包括补充非特定的预先登记的单词特征信息，具有单独的具有说话者的语言特征，以在讲话者具有不寻常的语音方式或重音和响应改变的情况下改善识别，其中利用说话者说明书注册功能来提供访问 并允许根据用户需求和口味对预定义的响应表进行更改。

    Printing apparatus and printing method
    5.
    发明授权
    Printing apparatus and printing method 失效
    印刷装置和印刷方法

    公开(公告)号：US07066665B2

    公开(公告)日：2006-06-27

    申请号：US10805485

    申请日：2004-03-22

    申请人： Isao Edatsune ,  Tatsuya Kitazawa

    发明人： Isao Edatsune ,  Tatsuya Kitazawa

    IPC分类号： B41J5/30

    CPC分类号： H04N1/00148 ,  H04N1/00132 ,  H04N1/00167 ,  H04N1/00188 ,  H04N1/0035

    摘要： Since both an output setting value and an output subject identifier, which are contained by a setting program, are stored as one record into a drawing table, an output condition such as a layout of image data which is designated when a printing operation is carried out can be previously set before the printing operation is carried out. Since photograph numbers of image data stored in a memory card are defined in relation to output subject identifiers, such image data to be printed out can be designated.

    摘要翻译： 由于由设置程序包含的输出设定值和输出对象标识符作为一个记录存储到绘图表中，所以在执行打印操作时指定的图像数据的布局等输出条件 可以在执行打印操作之前预先设置。 由于存储在存储卡中的图像数据的照片号是根据输出对象标识符定义的，因此可以指定要打印出的图像数据。

    Printing apparatus and printing method
    6.
    发明授权
    Printing apparatus and printing method 失效

    公开(公告)号：US06719466B2

    公开(公告)日：2004-04-13

    申请号：US10029155

    申请日：2001-12-28

    申请人： Isao Edatsune ,  Tatsuya Kitazawa

    发明人： Isao Edatsune ,  Tatsuya Kitazawa

    IPC分类号： B41J530

    CPC分类号： H04N1/00148 ,  H04N1/00132 ,  H04N1/00167 ,  H04N1/00188 ,  H04N1/0035

    摘要： Since both an output setting value and an output subject identifier, which are contained by a setting program, are stored as one record into a drawing table, an output condition such as a layout of image data which is designated when a printing operation is carried out can be previously set before the printing operation is carried out. Since photograph numbers of image data stored in a memory card are defined in relation to output subject identifiers, such image data to be printed out can be designated.

    Printer and printing method
    7.
    发明授权
    Printer and printing method 有权
    打印机和打印方式

    公开(公告)号：US06867877B1

    公开(公告)日：2005-03-15

    申请号：US09630409

    申请日：2000-08-01

    申请人： Isao Edatsune ,  Masanori Tanizaki

    发明人： Isao Edatsune ,  Masanori Tanizaki

    IPC分类号： H04N1/387 ,  G06F15/00

    CPC分类号： H04N1/3871

    摘要： A data acquisition portion 7 acquires any one of the composition data from a frame card in a case where the identifier of the whole file represents composition data and acquires image data from a memory card in a case where the identifier of the whole file represents the attributes of image data. A control portion 3 retrieves from ROM each parameter corresponding to the identifier of the composition data acquired from the frame card. With the parameters, the control portion 3 generates printing data by combining the image data acquired from the memory card with the composition data.

    摘要翻译： 在整个文件的标识符表示合成数据的情况下，数据获取部分7从帧卡获取任何一个合成数据，并且在整个文件的标识符表示属性的情况下从存储卡获取图像数据 的图像数据。 控制部分3从ROM检索与从帧卡获取的合成数据的标识符对应的每个参数。 利用参数，控制部3通过将从存储卡获取的图像数据与合成数据组合来生成打印数据。

    Photographic image print system, photographic image printer, and computer-readable recording medium having photographic image print program stored thereon
    8.
    发明授权
    Photographic image print system, photographic image printer, and computer-readable recording medium having photographic image print program stored thereon 有权
    摄影图像打印系统和打印机

    公开(公告)号：US06469770B2

    公开(公告)日：2002-10-22

    申请号：US09441069

    申请日：1999-11-16

    申请人： Masaru Hoshino ,  Isao Edatsune

    发明人： Masaru Hoshino ,  Isao Edatsune

    IPC分类号： G03B2752

    CPC分类号： H04N1/00416 ,  H04N1/00132 ,  H04N1/00161 ,  H04N1/00172 ,  H04N1/00175 ,  H04N1/00188 ,  H04N1/0035 ,  H04N1/00411 ,  H04N1/00432 ,  H04N1/00435 ,  H04N1/00437 ,  H04N1/00453 ,  H04N1/00466 ,  H04N1/00469 ,  H04N1/00472 ,  H04N1/00488 ,  H04N1/32561 ,  H04N2201/0082 ,  H04N2201/0087

    摘要： A photographic image print system and printer enable printing of pictures through simple operation. An automatic setting screen provides choices of voice guide, sources for data, whether to perform index printing, photo selection methods, print sizes, and whether to acknowledge a print. User choices may also be omitted. When a memory card is used as the data source, index printing is omitted, single prints of all pictures are printed in one size, and processing is executed in response of clicking only the “DEFAULT BUTTON” on the start screen and inserting the memory card, whereby all pictures stored in the memory card are printed. Alternatively, when index printing is selected and the default number of prints of all the photo selection methods is 0, processing is effected in response to clicking only the “DEFAULT BUTTON” on the start screen and inserting the memory card.

    摘要翻译： 摄影图像打印系统和打印机能够通过简单的操作来打印图片。 自动设置屏幕提供语音指南，数据来源，是否执行索引打印，照片选择方法，打印尺寸以及是否确认打印的选项。 用户选择也可以省略。 当使用存储卡作为数据源时，省略了索引打印，所有照片的单张打印均以一种尺寸打印，并且响应于仅点击起始屏幕上的“默认按钮”并插入存储卡来执行处理 ，由此存储在存储卡中的所有照片都被打印。 或者，当选择索引打印并且所有照片选择方法的默认打印数量为0时，响应于仅点击起始屏幕上的“默认按钮”并插入存储卡进行处理。

    Copying machine
    9.
    发明授权
    Copying machine 失效
    复印机

    公开(公告)号：US6040918A

    公开(公告)日：2000-03-21

    申请号：US926385

    申请日：1997-09-09

    申请人： Isao Edatsune ,  Hiroshi Kuriyama ,  Osamu Urano

    发明人： Isao Edatsune ,  Hiroshi Kuriyama ,  Osamu Urano

    IPC分类号： B41J3/407 ,  H04N1/00 ,  H04N1/23 ,  G03G15/05

    CPC分类号： H04N1/23 ,  B41J3/4075 ,  H04N1/00278

    摘要： A copying machine of the present invention has a scanner unit (2) for reading an original, a line type thermal head (14) for printing read image data on tape (16) to be used as a recording medium, a tape cartridge (51) for supplying the tape and a tape conveying mechanism. The tape (16) has an image carrying sheet (161), the front surface of which is a printing face to be printed with an image, an adhesive layer (162) formed by applying an adhesive to the back surface of this image carrying sheet and a release sheet (163) releasably stuck to the surface of the adhesive layer. The tape is taken up like a roll and is detachably fitted into the body of the copying machine in the form of the tape cartridge (51). At both ends of the tape, conveyance border portions of a uniform width are formed. In the border portions, engaging holes ( ) are formed at regular intervals in the direction of the length of the tape. The tape conveying mechanism has sprockets (183, 184), on the outer circumferences of which projections being capable of engaging with the engaging holes are formed. The tape can be conveyed with high precision and a desired image can be printed thereon. Thereby, the copying machine of the present invention can easily obtain a tape, which has a desired image copied and is able to be stuck to a desired place.

    摘要翻译： 本发明的复印机具有用于读取原稿的扫描器单元（2），用于将要用作记录介质的带（16）上的读取图像数据打印的线型热敏头（14），带盒（51） ）和带输送机构。 带（16）具有图像承载片（161），其前表面是要印刷图像的印刷面，通过将粘合剂施加到该图像承载片的背面而形成的粘合层（162） 以及可释放地粘附到粘合剂层的表面上的剥离片（163）。 胶带以卷状卷取，并且以带盒（51）的形式可拆卸地装配到复印机的主体中。 在带的两端形成均匀宽度的输送边界部分。 在边界部分中，沿带的长度方向以规则的间隔形成接合孔（）。 带传送机构具有链轮（183,184），在其外周上形成能够与接合孔接合的突起。 可以高精度地传送带子，并且可以在其上印刷期望的图像。 因此，本发明的复印机可以容易地获得具有所需图像的胶带，并且能够粘贴到期望的位置。

    Cartridge-based, interactive speech recognition method with a response creation capability
    10.
    发明授权
    Cartridge-based, interactive speech recognition method with a response creation capability 有权
    基于墨盒的交互式语音识别方法，具有响应创造能力

    公开(公告)号：US5946658A

    公开(公告)日：1999-08-31

    申请号：US165512

    申请日：1998-10-02

    申请人： Yasunaga Miyazawa ,  Mitsuhiro Inazumi ,  Hiroshi Hasegawa ,  Isao Edatsune ,  Osamu Urano

    发明人： Yasunaga Miyazawa ,  Mitsuhiro Inazumi ,  Hiroshi Hasegawa ,  Isao Edatsune ,  Osamu Urano

    IPC分类号： G10L15/00 ,  G10L15/06 ,  G10L15/26 ,  G10L9/06 ,  G10L5/02

    CPC分类号： G10L15/26 ,  G10L2015/0638 ,  G10L2015/088

    摘要： A technique for improving speech recognition in low-cost, speech interactive devices. This technique calls for selectively implementing a speaker-specific word enrollment and detection unit in parallel with a word detection unit to permit comprehension of spoken commands or messages when no recognizable words are found. Preferably, specific speaker detection will be based on the speaker's own personal list of words or expression. Other facets include complementing non-specific pre-registered word characteristic information with individual, speaker-specific verbal characteristics to improve recognition in cases where the speaker has unusual speech mannerisms or accent and response alteration in which speaker-specification registration functions are leveraged to provide access and permit changes to a predefined responses table according to user needs and tastes. Also disclosed is the externalization and modularization of non-specific speaker recognition, action and response information to enhance adaptability of the speech recognizer without sacrificing product cost competitiveness or overall device responsiveness.

    摘要翻译： 一种用于在低成本语音交互设备中改善语音识别的技术。 该技术要求与字检测单元并行地选择性地实现与扬声器特定的单词注册和检测单元，以便在找不到可识别的单词时允许理解口语命令或消息。 优选地，具体的说话者检测将基于说话者自己的单词或表达的个人列表。 其他方面包括补充非特定的预先登记的单词特征信息，具有单独的具有说话者的语言特征，以在讲话者具有不寻常的语音方式或重音和响应改变的情况下改善识别，其中利用说话者说明书注册功能来提供访问 并允许根据用户需求和口味对预定义的响应表进行更改。 还公开了非特定说话人识别，动作和响应信息的外部化和模块化，以增强语音识别器的适应性，而不牺牲产品成本竞争力或整体设备响应性。