VARIABLE-COMPONENT DEEP NEURAL NETWORK FOR ROBUST SPEECH RECOGNITION
    12.
    发明公开
    VARIABLE-COMPONENT DEEP NEURAL NETWORK FOR ROBUST SPEECH RECOGNITION 审中-公开
    用于鲁棒语音识别的变分量深度神经网络

    公开(公告)号:EP3192071A1

    公开(公告)日:2017-07-19

    申请号:EP14901500.0

    申请日:2014-09-09

    IPC分类号: G10L15/20 G10L15/06

    摘要: System and method for speech recognition incorporating environmental variables are provided. The system comprises: a speech capture device (202); a feature extraction module (204); an environment variable module (206), wherein the environment variable module determines a value for an environment variable; and a speech recognition decoder (208), wherein the speech recognition decoder utilizes a deep neural network (DNN) to recognize speech captured by the speech capture device, wherein one or more components of the DNN are modeled as a set of functions of the environment variable.

    摘要翻译: 提供了结合环境变量的语音识别系统和方法。 该系统和方法捕捉到需要识别的语音。 然后使用可变分量深度神经网络(DNN)识别语音。 可变组件DNN通过合并环境变量来处理捕获的语音。 环境变量可以是取决于环境条件或用户,客户端设备和环境的关系的任何变量。 例如,环境变量可以基于环境噪声并表示为信噪比。 可变组件DNN可以以不同方式结合环境变量。 例如,可以将环境变量并入DNN的加权矩阵和偏差,DNN的隐藏层的输出或DNN的节点的激活功能。

    LOW-FOOTPRINT ADAPTATION AND PERSONALIZATION FOR A DEEP NEURAL NETWORK
    18.
    发明公开
    LOW-FOOTPRINT ADAPTATION AND PERSONALIZATION FOR A DEEP NEURAL NETWORK 有权
    适应和个性化的小体积FOR A深层神经网络

    公开(公告)号:EP3114680A1

    公开(公告)日:2017-01-11

    申请号:EP15717284.2

    申请日:2015-02-27

    IPC分类号: G10L15/07 G10L15/16

    摘要: The adaptation and personalization of a deep neural network (DNN) model for automatic speech recognition is provided. An utterance which includes speech features for one or more speakers may be received in ASR tasks such as voice search or short message dictation. A decomposition approach may then be applied to an original matrix in the DNN model. In response to applying the decomposition approach, the original matrix may be converted into multiple new matrices which are smaller than the original matrix. A square matrix may then be added to the new matrices. Speaker-specific parameters may then be stored in the square matrix. The DNN model may then be adapted by updating the square matrix. This process may be applied to all of a number of original matrices in the DNN model. The adapted DNN model may include a reduced number of parameters than those received in the original DNN model.

    摘要翻译: 用于自动语音识别的深层神经网络(DNN)模型的适配和个性化设置。 如语音搜索或短信听写:其中包括一个或多个扬声器的语音功能的话语可以在ASR任务接收。 甲分解方法可接着在DNN模型被应用到原始矩阵。 响应于施加的分解的方法中,原始矩阵可以被转换成多个新的矩阵,它们比原矩阵小。 然后,方阵可被添加到新的矩阵。 说话者特定参数然后可被存储在方阵。 DNN的模型然后可以通过更新方阵来适配。 此过程可被应用到所有的数在DNN模型原始矩阵的。 该angepasst DNN模型可以包括的参数比在原始DNN模型接收到的减少数目。