专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

WO2016037350A1 LEARNING STUDENT DNN VIA OUTPUT DISTRIBUTION 审中-公开
标题翻译：学习DNN通过输出分配
公开(公告)号：WO2016037350A1
公开(公告)日：2016-03-17
申请号：PCT/CN2014/086397
申请日：2014-09-12
申请人： MICROSOFT CORPORATION , ZHAO, Rui , HUANG, Jui-Ting , LI, Jinyu , GONG, Yifan
发明人： ZHAO, Rui , HUANG, Jui-Ting , LI, Jinyu , GONG, Yifan
IPC分类号： G06K9/66
CPC分类号： G06N3/084 , G06N3/0454 , G06N7/005 , G06N99/005 , G09B5/00
摘要： Systems and methods are provided for generating a DNN classifier by "learning" a "student" DNN model from a larger, more accurate "teacher" DNN model. The student DNN may be trained from unlabeled training data by passing the unlabeled training data through the teacher DNN, which may be trained from labeled data. In one embodiment, an iterative processis applied to train the student DNN by minimizing the divergence of the output distributions from the teacher and student DNN models. For each iteration until convergence, the difference in the outputs of these two DNNsis used to update the student DNN model, and outputs are determined again, using the unlabeled training data. The resulting trained student DNN model may be suitable for providing accurate signal processing applications on devices having limited computational or storage resources such as mobile or wearable devices. In an embodiment, the teacher DNN model comprises an ensemble of DNN models.
摘要翻译：提供了通过从更大，更准确的“教师”DNN模型学习“学生”DNN模型来生成DNN分类器的系统和方法。通过传递未标记的训练数据通过教师DNN，可以从未标记的训练数据训练学生DNN，该DNN可以从标记数据中训练。在一个实施例中，迭代过程被应用于通过最小化来自教师和学生DNN模型的输出分布的差异来训练学生DNN。对于每次迭代直到收敛，这两个DNNsis的输出的差异用于更新学生DNN模型，并且使用未标记的训练数据再次确定输出。所得到的训练有素的学生DNN模型可能适合于在具有有限计算或存储资源的设备（例如移动或可穿戴设备）上提供精确的信号处理应用。在一个实施例中，教师DNN模型包括DNN模型的集合。

2. 发明申请

WO2013134641A3 RECOGNIZING SPEECH IN MULTIPLE LANGUAGES 审中-公开
标题翻译：以多种语言识别语音
公开(公告)号：WO2013134641A3
公开(公告)日：2013-10-24
申请号：PCT/US2013029877
申请日：2013-03-08
申请人： GOOGLE INC , SUNG YUN-HSUAN , BEAUFAYS FRANCOISE , STROPE BRIAN , LIN HUI , HUANG JUI-TING
发明人： SUNG YUN-HSUAN , BEAUFAYS FRANCOISE , STROPE BRIAN , LIN HUI , HUANG JUI-TING
IPC分类号： G10L15/00 , G10L15/183 , G10L15/32
CPC分类号： G10L15/005 , G10L15/183 , G10L15/32
摘要： Speech recognition systems may perform the following operations: receiving audio; recognizing the audio using language models for different languages to produce recognition candidates for the audio, where the recognition candidates are associated with corresponding recognition scores; identifying a candidate language for the audio; selecting a recognition candidate based on the recognition scores and the candidate language; and outputting data corresponding to the selected recognition candidate as a recognized version of the audio.
摘要翻译：语音识别系统可以执行以下操作：接收音频; 使用不同语言的语言模型识别音频以产生音频的识别候选，其中识别候选与相应的识别分数相关联; 识别音频的候选语言; 基于识别分数和候选语言选择识别候选者; 以及输出与所选识别候选对应的数据作为音频的识别版本。

3. 发明申请

WO2013134641A2 RECOGNIZING SPEECH IN MULTIPLE LANGUAGES 审中-公开
标题翻译：在多种语言中识别语音
公开(公告)号：WO2013134641A2
公开(公告)日：2013-09-12
申请号：PCT/US2013/029877
申请日：2013-03-08
申请人： GOOGLE INC. , SUNG, Yun-Hsuan , BEAUFAYS, Francoise , STROPE, Brian , LIN, Hui , HUANG, Jui-Ting
发明人： SUNG, Yun-Hsuan , BEAUFAYS, Francoise , STROPE, Brian , LIN, Hui , HUANG, Jui-Ting
IPC分类号： G10L15/00
CPC分类号： G10L15/005 , G10L15/183 , G10L15/32
摘要： Speech recognition systems may perform the following operations: receiving audio; recognizing the audio using language models for different languages to produce recognition candidates for the audio, where the recognition candidates are associated with corresponding recognition scores; identifying a candidate language for the audio; selecting a recognition candidate based on the recognition scores and the candidate language; and outputting data corresponding to the selected recognition candidate as a recognized version of the audio.
摘要翻译：语音识别系统可以执行以下操作：接收音频; 使用不同语言的语言模型识别音频以产生用于音频的识别候选，其中识别候选者与相应的识别分数相关联; 识别音频的候选语言; 基于识别分数和候选语言选择识别候选; 并输出与所选择的识别候选相对应的数据作为音频的识别版本。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式