利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

5 条记录 (耗时 0.015 秒)

    Language model data collection
    1.
    发明授权
    Language model data collection 有权
    语言模型数据收集

    公开(公告)号：US09047868B1

    公开(公告)日：2015-06-02

    申请号：US13563648

    申请日：2012-07-31

    申请人： Jeffrey C. O'Neill ,  Ryan P. Thomas

    发明人： Jeffrey C. O'Neill ,  Ryan P. Thomas

    IPC分类号： G10L21/00 ,  G10L15/197

    CPC分类号： G10L15/197 ,  G10L15/30

    摘要： A specific language model for speech recognition may be built. In some embodiments, the specific language model is associated with a user and built using a corpus of text obtained from a user computing device. In some embodiments, a sequence of words is constructed from the corpus of text. The sequence of words may be obfuscated, and the obfuscated sequence of words may be stored in the specific language model. A server or a user device may use the specific language model in conjunction with a general language model to perform speech recognition on an utterance made by the user.

    摘要翻译： 可以构建用于语音识别的特定语言模型。 在一些实施例中，特定语言模型与用户相关联并且使用从用户计算设备获得的文本语料库构建。 在一些实施例中，从文本语料库构建单词序列。 单词的序列可能被模糊化，并且混淆的单词序列可以存储在特定的语言模型中。 服务器或用户设备可以结合通用语言模型使用特定语言模型，以在由用户做出的话语上执行语音识别。

    Ball screw assembly and spacer elements therefor
    2.
    发明授权
    Ball screw assembly and spacer elements therefor 失效
    滚珠丝杠总成及间隔元件

    公开(公告)号：US07640820B1

    公开(公告)日：2010-01-05

    申请号：US11271270

    申请日：2005-11-10

    申请人： Ryan B. West ,  Bir Inder Singh ,  Stephen R. Ahlers ,  Ryan P. Thomas ,  Gwo-Shum Burt Shiu

    发明人： Ryan B. West ,  Bir Inder Singh ,  Stephen R. Ahlers ,  Ryan P. Thomas ,  Gwo-Shum Burt Shiu

    IPC分类号： F16H1/24 ,  F16H55/02 ,  F16C29/06 ,  F16C19/00

    CPC分类号： F16C33/3706 ,  F16H25/2214 ,  F16H25/2238 ,  Y10T74/19749 ,  Y10T74/19767 ,  Y10T74/19777

    摘要： A ball screw assembly has an axially extending screw with an external helical groove and a nut with a through bore for receipt of the screw. The through bore has an internal helical groove adapted for cooperation with the external helical groove to define a ball raceway. A plurality of load bearing balls is disposed in the raceway for rolling contact with the internal and external grooves. A spacer is disposed between adjacent ones of the load bearing balls to prevent the balls from contacting one another. Each of the spacers has at least three pairs of diametrically opposite concave dimples adapted for contact with the load bearing balls at separate times from one another.

    摘要翻译： 滚珠丝杠组件具有带有外部螺旋槽的轴向延伸的螺钉和具有用于接收螺钉的通孔的螺母。 通孔具有适于与外部螺旋槽配合的内部螺旋槽，以形成滚珠滚道。 多个承载滚珠设置在滚道内，用于与内槽和外槽滚动接触。 间隔件设置在相邻的承载球之间以防止球彼此接触。 每个间隔件具有至少三对直径相对的凹坑，其适于在彼此分开的时间与承载滚珠接触。

    Identifying candidate passwords from captured audio
    3.
    发明授权
    Identifying candidate passwords from captured audio 有权
    从捕获的音频识别候选密码

    公开(公告)号：US08898064B1

    公开(公告)日：2014-11-25

    申请号：US13424104

    申请日：2012-03-19

    申请人： Ryan P. Thomas ,  Nikko Strom

    发明人： Ryan P. Thomas ,  Nikko Strom

    IPC分类号： G10L21/00 ,  G10L25/00 ,  G10L17/00

    CPC分类号： G10L15/08 ,  G06F3/167 ,  G06F21/32 ,  G10L2015/086

    摘要： A computing device configured to request a password from a user, capture audio after issuing the request, and determine a number of alternative candidate passwords most likely represented by the audio. After identifying the number of candidate passwords, the computing device may submit these candidate passwords, one at a time, to an entity until the entity grants the device access to an account associated with the user or until the device has submitted each candidate password. The account may comprise a network account (e.g., a wired or wireless network account), an online account (e.g., an email account, an account an online merchant, etc.), or the like.

    摘要翻译： 一种计算设备，被配置为从用户请求密码，在发出请求之后捕获音频，并且确定最可能由音频表示的替代候选密码的数量。 在识别候选密码的数量之后，计算设备可以将这些候选密码一次一个地提交给实体，直到实体授予设备对与用户相关联的帐户的访问，或者直到该设备已经提交了每个候选密码。 帐户可以包括网络帐户（例如，有线或无线网络帐户），在线帐户（例如，电子邮件帐户，在线商家帐户等）等。

    Transmission of noise parameters for improving automatic speech recognition
    4.
    发明授权
    Transmission of noise parameters for improving automatic speech recognition 有权
    传输噪声参数，以改善自动语音识别

    公开(公告)号：US08983844B1

    公开(公告)日：2015-03-17

    申请号：US13562476

    申请日：2012-07-31

    申请人： Ryan P. Thomas ,  Nikko Strom

    发明人： Ryan P. Thomas ,  Nikko Strom

    IPC分类号： G10L21/00

    CPC分类号： G10L15/30 ,  G10L15/065 ,  G10L15/20 ,  G10L21/0208

    摘要： Methods and systems for transmission of noise parameters for improving automatic speech recognition are disclosed. A system includes one or more microphones, wherein each microphone is configured to produce an audio signal. The system also includes a noise reduction module configured to generate a noise-reduced audio signal and a noise parameter. Furthermore, the system includes a transmitter configured to transmit, to a computing device, the noise-reduced audio signal and a noise parameter. The computing device may use the noise parameter in obtaining a model to use for performing automatic speech recognition.

    摘要翻译： 公开了用于传输用于改善自动语音识别的噪声参数的方法和系统。 系统包括一个或多个麦克风，其中每个麦克风被配置为产生音频信号。 该系统还包括被配置为产生噪声降低的音频信号和噪声参数的降噪模块。 此外，该系统包括被配置为向计算设备发送噪声降低的音频信号和噪声参数的发射机。 计算设备可以使用噪声参数来获得用于执行自动语音识别的模型。