Training speech recognition by matching audio segment frequency of
occurrence with frequency of words and letter combinations in a corpus
    11.
    发明授权
    Training speech recognition by matching audio segment frequency of occurrence with frequency of words and letter combinations in a corpus 失效
    通过将音频段的出现频率与语料库中的单词和字母组合的频率相匹配来训练语音识别

    公开(公告)号:US6009392A

    公开(公告)日:1999-12-28

    申请号:US7478

    申请日:1998-01-15

    IPC分类号: G01L9/00

    摘要: A method is provided which trains acoustic models in an automatic speech recognizer ("ASR") without explicitly matching decoded scripts with correct scripts from which acoustic training data is generated. In the method, audio data is input and segmented to produce audio segments. The audio segments are clustered into groups of clustered audio segments such that the clustered audio segments in each of the groups have similar characteristics. Also, the groups respectively form audio similarity classes. Then, audio segment probability distributions for the clustered audio segments in the audio similarity classes are calculated, and audio segment frequencies for the clustered audio segments are determined based on the audio segment probability distributions. The audio segment frequencies are matched to known audio segment frequencies for at least one of letters, combination of letters, and words to determine frequency matches, and a textual corpus of words is formed based on the frequency matches. Then, acoustic models of the automatic speech recognizer are trained based on the textual corpus. In addition, the method may receive and cluster video or biometric data, and match such data to the audio data to more accurately cluster the audio segments into the groups of audio segments. Also, an apparatus for performing the method is provided.

    摘要翻译: 提供了一种在自动语音识别器(“ASR”)中训练声学模型的方法,而没有将解码的脚本与产生声学训练数据的正确脚本明确匹配。 在该方法中,音频数据被输入和分段以产生音频段。 音频段被聚集成群集的音频段,使得每个组中的群集音频段具有相似的特征。 此外,各组分别形成音频相似性类。 然后,计算音频相似度类别中的聚集音频段的音频段概率分布,并且基于音频段概率分布确定用于聚集音频段的音频段频率。 音频段频率与已知的音频段频率匹配用于字母,字母和字的组合中的至少一个以确定频率匹配,并且基于频率匹配形成文本语言语料库。 然后,基于文本语料库训练自动语音识别器的声学模型。 此外,该方法可以接收和聚集视频或生物特征数据,并且将这样的数据与音频数据相匹配,以便将音频段更精确地聚集到音频段组中。 此外,提供了一种用于执行该方法的装置。

    Real-time interactive authorization for enterprise search
    13.
    发明授权
    Real-time interactive authorization for enterprise search 有权
    企业搜索的实时互动授权

    公开(公告)号:US09020913B2

    公开(公告)日:2015-04-28

    申请号:US11924219

    申请日:2007-10-25

    摘要: Techniques for providing at least one user access to one or more documents in a collaborative computing environment in accordance with a search engine are provided. The user is presented with search results, wherein the search results comprise at least one document comprising at least one portion to which the user has no access. A request from the user for access to the at least one document is received. A supervising entity is then notified of the user request to access the at least one document. An instruction from the supervising entity is then received. In accordance with the received instruction, the user is granted access to the at least one document.

    摘要翻译: 提供了用于根据搜索引擎向协作计算环境中的一个或多个文档提供至少一个用户访问的技术。 向用户呈现搜索结果,其中搜索结果包括至少一个文档,该文档包括用户无法访问的至少一个部分。 接收来自用户访问该至少一个文档的请求。 然后向监督实体通知用户访问该至少一个文档的请求。 然后收到监督实体的指示。 根据接收到的指令,允许用户访问至少一个文档。

    Real-Time Interactive Authorization for Enterprise Search
    14.
    发明申请
    Real-Time Interactive Authorization for Enterprise Search 有权
    企业搜索的实时互动授权

    公开(公告)号:US20090112868A1

    公开(公告)日:2009-04-30

    申请号:US11924219

    申请日:2007-10-25

    IPC分类号: G06F17/30

    摘要: Techniques for providing at least one user access to one or more documents in a collaborative computing environment in accordance with a search engine are provided. The user is presented with search results, wherein the search results comprise at least one document comprising at least one portion to which the user has no access. A request from the user for access to the at least one document is received. A supervising entity is then notified of the user request to access the at least one document. An instruction from the supervising entity is then received. In accordance with the received instruction, the user is granted access to the at least one document.

    摘要翻译: 提供了用于根据搜索引擎向协作计算环境中的一个或多个文档提供至少一个用户访问的技术。 向用户呈现搜索结果,其中搜索结果包括至少一个文档,该文档包括用户无法访问的至少一个部分。 接收来自用户访问该至少一个文档的请求。 然后向监督实体通知用户访问该至少一个文档的请求。 然后收到监督实体的指示。 根据接收到的指令,允许用户访问至少一个文档。