Method of testing a vocabulary word being enrolled in a speech
recognition system
    2.
    发明授权
    Method of testing a vocabulary word being enrolled in a speech recognition system 失效
    测试在语音识别系统中登记的词汇单词的方法

    公开(公告)号:US06134527A

    公开(公告)日:2000-10-17

    申请号:US16012

    申请日:1998-01-30

    CPC分类号: G10L15/063 G10L15/187

    摘要: A method of testing a new vocabulary word is performed using any set of enrollment utterances provided by the user or from an available database. The present method preferably does not use separate training and similarity test utterances. This allows any or all available repetitions of a vocabulary word being enrolled to be used for training (204), therefore improving the robustness of the trained models. Likewise, any or all training repetitions can also be utilized for similarity analysis (212), providing additional test samples which should further improve the detection of acoustically similar words. Additionally, the similarity analysis progresses incrementally and does not need to continue if a confusable word is found. Finally, first and second thresholds could be employed (212, 302) to provide greater flexibility for a user training a speech recognition system.

    摘要翻译: 使用由用户提供的任何一组登记话语或从可用数据库来执行测试新词汇词的方法。 本方法优选不使用单独的训练和相似性测试话语。 这允许正在注册的词汇单的任何或所有可用的重复被用于训练(204),从而提高训练模型的鲁棒性。 同样,任何或所有训练重复也可以用于相似性分析(212),提供额外的测试样本,其应该进一步改善声学上类似的词的检测。 另外,相似性分析渐进地进行,并且如果发现可混淆的词,则不需要继续。 最后,可以使用第一和第二阈值(212,302)来为用户训练语音识别系统提供更大的灵活性。

    Speech synthesis
    6.
    发明申请
    Speech synthesis 审中-公开
    语音综合

    公开(公告)号:US20050060156A1

    公开(公告)日:2005-03-17

    申请号:US10914583

    申请日:2004-08-09

    摘要: In a speech synthesis technique used in a network (110, 115), a set of text words is accepted by a speech engine software function (210) in a client device (105). From the set of text words, an invalid subset of text words is determined for which the text words are not in a word synthesis dictionary of the client device. The invalid subset of text words is transmitted over the network to a server device (120), which generates a set of word pronunciations including at least a portion of the text words of the invalid subset of text words and pronunciations associated with each of the text words. The client device uses the pronunciations for speech synthesis and may store them in a local word synthesis dictionary (220) stored in a memory (150) of the client device.

    摘要翻译: 在网络(110,115)中使用的语音合成技术中,一组文本字被客户端设备(105)中的语音引擎软件功能(210)接受。 从文本文本集合中,确定文本字的无效子集,其文本字不在客户端设备的单词合成字典中。 文本字的无效子集通过网络发送到服务器设备(120),该服务器设备生成一组单词发音,其包括文本单词的无效子集的至少一部分文本单词和与每个文本相关联的发音 话。 客户端设备使用用于语音合成的发音,并且可以将它们存储在存储在客户端设备的存储器(150)中的本地单词合成词典(220)中。

    Formulating and sending a message by a personal messaging device
    8.
    发明申请
    Formulating and sending a message by a personal messaging device 审中-公开
    由个人消息传递设备制定和发送消息

    公开(公告)号:US20060123089A1

    公开(公告)日:2006-06-08

    申请号:US11004739

    申请日:2004-12-03

    IPC分类号: G06F15/16

    摘要: Means and method are for sending a wireless message (620) by a personal messaging device (2000) using a message template (305, 400, 500) that is formed by user input. A static component (405), dynamic component (410, 510), and trigger condition (415) of a message template are specified by user input and stored in the personal messaging device. When satisfied, the trigger condition causes one or more wireless messages to be transmitted using the message template. The dynamic component of the message template may include a set of dynamic information (411) obtained from a set of information sources at the occurrence of one or more dynamic events. The one or more dynamic events (412, 512) may be the same as the trigger condition.

    摘要翻译: 方法和方法是使用由用户输入形成的消息模板(305,400,500)由个人消息收发设备(2000)发送无线消息(620)。 消息模板的静态组件(405),动态组件(410,510)和触发条件(415)由用户输入指定并存储在个人消息设备中。 当满足时,触发条件使得使用消息模板发送一个或多个无线消息。 消息模板的动态组件可以包括在一个或多个动态事件发生时从一组信息源获得的一组动态信息(411)。 一个或多个动态事件(412,512)可以与触发条件相同。