利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

13 条记录 (耗时 0.014 秒)

    COMPUTING SYSTEM FOR TRAINING NEURAL NETWORKS
    1.
    发明公开
    COMPUTING SYSTEM FOR TRAINING NEURAL NETWORKS 审中-公开
    训练神经网络计算系统

    公开(公告)号：EP3192016A1

    公开(公告)日：2017-07-19

    申请号：EP14901717.0

    申请日：2014-09-12

    申请人： Microsoft Technology Licensing, LLC

    发明人： LANGFORD, John ,  LI, Gang ,  SEIDE, Frank Torsten Bernd ,  DROPPO, James ,  YU, Dong

    IPC分类号： G06N3/08

    CPC分类号： G06N3/08 ,  G06N3/04 ,  G06N3/0454 ,  G06N3/084 ,  G06N7/005

    摘要： Techniques and constructs can reduce the time required to determine solutions to optimization problems such as training of neural networks. Modifications to a computational model can be determined by a plurality of nodes operating in parallel. Quantized modification values can be transmitted between the nodes to reduce the volume of data to be transferred. The quantized values can be as small as one bit each. Quantization-error values can be stored and used in quantizing subsequent modifications. The nodes can operate in parallel and overlap computation and data transfer to further reduce the time required to determine solutions. The quantized values can be partitioned and each node can aggregate values for a corresponding partition.

    摘要翻译： 技术和结构可以减少确定解决优化问题所需的时间，例如神经网络的训练。 对计算模型的修改可以由多个并行操作的节点来确定。 量化的修改值可以在节点之间传输，以减少要传输的数据量。 量化值可以小至每个一位。 量化误差值可被存储并用于量化随后的修改。 节点可以并行运行并重叠计算和数据传输，以进一步缩短确定解决方案所需的时间。 量化值可以进行分区，每个节点可以汇总相应分区的值。

    MULTILINGUAL DEEP NEURAL NETWORK
    2.
    发明公开
    MULTILINGUAL DEEP NEURAL NETWORK 审中-公开
    MULTILINGUAL深层神经网络

    公开(公告)号：EP2973546A1

    公开(公告)日：2016-01-20

    申请号：EP14711122.3

    申请日：2014-03-05

    申请人： Microsoft Technology Licensing, LLC

    发明人： HUANG, Jui-Ting ,  LI, Jinyu ,  YU, Dong ,  DENG, Li ,  GONG, Yifan

    IPC分类号： G10L15/16

    摘要： Described herein are various technologies pertaining to a multilingual deep neural network (MDNN). The MDNN includes a plurality of hidden layers, wherein values for weight parameters of the plurality of hidden layers are learned during a training phase based upon training data in terms of acoustic raw features for multiple languages. The MDNN further includes softmax layers that are trained for each target language separately, making use of the hidden layer values trained jointly with multiple source languages. The MDNN is adaptable, such that a new softmax layer may be added on top of the existing hidden layers, where the new softmax layer corresponds to a new target language.

    MIXED SPEECH SIGNALS RECOGNITION
    6.
    发明授权
    MIXED SPEECH SIGNALS RECOGNITION 有权
    混合语音信号识别

    公开(公告)号：EP3123466B1

    公开(公告)日：2017-11-15

    申请号：EP15714120.1

    申请日：2015-03-19

    申请人： Microsoft Technology Licensing, LLC

    发明人： YU, Dong ,  WENG, Chao ,  SELTZER, Michael L. ,  DROPPO, James

    IPC分类号： G10L15/16 ,  G10L15/06 ,  G10L15/20

    CPC分类号： G10L15/16 ,  G10L15/063 ,  G10L15/20 ,  G10L17/18 ,  G10L25/21 ,  G10L25/84 ,  G10L25/90

    摘要： The claimed subject matter includes a system and method for recognizing mixed speech from a source. The method includes training a first neural network to recognize the speech signal spoken by the speaker with a higher level of a speech characteristic from a mixed speech sample. The method also includes training a second neural network to recognize the speech signal spoken by the speaker with a lower level of the speech characteristic from the mixed speech sample. Additionally, the method includes decoding the mixed speech sample with the first neural network and the second neural network by optimizing the joint likelihood of observing the two speech signals considering the probability that a specific frame is a switching point of the speech characteristic.

    MIXED SPEECH RECOGNITION
    7.
    发明公开
    MIXED SPEECH RECOGNITION 有权
    GEMISCHTE SPRACHERKENNUNG

    公开(公告)号：EP3123466A1

    公开(公告)日：2017-02-01

    申请号：EP15714120.1

    申请日：2015-03-19

    申请人： Microsoft Technology Licensing, LLC

    发明人： YU, Dong ,  WENG, Chao ,  SELTZER, Michael L. ,  DROPPO, James

    IPC分类号： G10L15/16 ,  G10L15/06 ,  G10L15/20

    CPC分类号： G10L15/16 ,  G10L15/063 ,  G10L15/20 ,  G10L17/18 ,  G10L25/21 ,  G10L25/84 ,  G10L25/90

    摘要： The claimed subject matter includes a system and method for recognizing mixed speech from a source. The method includes training a first neural network to recognize the speech signal spoken by the speaker with a higher level of a speech characteristic from a mixed speech sample. The method also includes training a second neural network to recognize the speech signal spoken by the speaker with a lower level of the speech characteristic from the mixed speech sample. Additionally, the method includes decoding the mixed speech sample with the first neural network and the second neural network by optimizing the joint likelihood of observing the two speech signals considering the probability that a specific frame is a switching point of the speech characteristic.

    摘要翻译： 所要求保护的主题包括用于从源识别混合语音的系统和方法。 该方法包括训练第一神经网络以从混合语音样本中识别具有较高级别的语音特征的扬声器所说出的语音信号。 该方法还包括训练第二神经网络以从混合语音样本中以较低级别的语音特征来识别由扬声器所说出的语音信号。 此外，该方法包括：考虑到特定帧是语音特征的切换点的概率，通过优化观察两个语音信号的联合似然度来解码具有第一神经网络和第二神经网络的混合语音样本。