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

WO2022261808A1 CONTEXTUAL SPELLING CORRECTION (CSC) FOR AUTOMATIC SPEECH RECOGNITION (ASR) 审中-公开
公开(公告)号：WO2022261808A1
公开(公告)日：2022-12-22
申请号：PCT/CN2021/099993
申请日：2021-06-15
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC , WANG, Xiaoqiang , LIU, Yanqing , ZHAO, Sheng , LI, Jinyu
发明人： WANG, Xiaoqiang , LIU, Yanqing , ZHAO, Sheng , LI, Jinyu
IPC分类号： G10L15/18 , G06F40/295
摘要： Novel solutions for speech recognition provide contextual spelling correction (CSC) for automatic speech recognition (ASR). Disclosed examples include receiving an audio stream; performing an ASR process on the audio stream to produce an ASR hypothesis; receiving a context list; and, based on at least the ASR hypothesis and the context list, performing spelling correction to produce an output text sequence. A contextual spelling correction (CSC) model is used on top of an ASR model, precluding the need for changing the original ASR model. This permits run-time user customization based on contextual data, even for large-size context lists. Some examples include filtering ASR hypotheses for the audio stream and, based on at least the ASR hypotheses filtering, determining whether to trigger spelling correction for the ASR hypothesis. Some examples include generating text to speech (TTS) audio using preprocessed transcriptions with context phrases to train the CSC model.

2. 发明申请

WO2022252116A1 ABSORBENT ARTICLE COMPRISING AN INTERMEDIATE LAYER 审中-公开
公开(公告)号：WO2022252116A1
公开(公告)日：2022-12-08
申请号：PCT/CN2021/097695
申请日：2021-06-01
申请人： THE PROCTER & GAMBLE COMPANY , ERDEM, Gueltekin , YUAN, Yi , LI, Jinyu , LIU, Hui , BIANCHI, Ernesto Gabriel , SURUSHE, Abhishek Prakash , KREISEL, Sascha
发明人： ERDEM, Gueltekin , YUAN, Yi , LI, Jinyu , LIU, Hui , BIANCHI, Ernesto Gabriel , SURUSHE, Abhishek Prakash , KREISEL, Sascha
IPC分类号： A61F13/537 , A61F13/514 , D04H1/435 , D04H1/541 , D04H1/4382 , D04H1/55 , D04H1/74
摘要： The present invention relates to an absorbent article comprising a topsheet, a backsheet, and a layer of absorbent material disposed between the topsheet and the backsheet wherein the layer of absorbent material comprises superabsorbent polymer, and an intermediate layer comprising a nonwoven web, the intermediate layer being disposed between the layer of absorbent material and the backsheet, wherein the intermediate layer has a MD tensile/basis weight no greater than about 0.75 N/5cm/g/m 2 as measured according to Tensile Strength Test, and a thickness/basis weight no less than about 0.078mm/g/m 2, as measured FTT Test; a nonwoven comprising a MD tensile/basis weight no greater than about 0.75 N/5cm/g/m 2 as measured according to Tensile Strength Test, and a thickness/basis weight no less than about 0.078mm/g/m 2, as measured FTT Test; and a process for producing nonwoven comprising supplying a nonwoven web comprising first thermoplastic fibers having a first melting temperature and second thermoplastic fibers having a second melting temperature, wherein the second melting temperature is at least about 40℃higher than the first melting temperature and, applying heat to the nonwoven web so that at least part of the first thermoplastic fibers are heat-fused one another, wherein the heat has a temperature between the first melting temperature and lower than the second melting temperature.

3. 发明申请

WO2017070920A1 SPOOFED FACE DETECTION 审中-公开
标题翻译： SPOOFED脸部检测
公开(公告)号：WO2017070920A1
公开(公告)日：2017-05-04
申请号：PCT/CN2015/093334
申请日：2015-10-30
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC , LI, Jinyu , WEN, Fang , WEI, Yichen , CONRAD, Michael John , CHU, Chun-Te , JAWAID, Aamir
发明人： LI, Jinyu , WEN, Fang , WEI, Yichen , CONRAD, Michael John , CHU, Chun-Te , JAWAID, Aamir
IPC分类号： G06K9/00
CPC分类号： G06K9/00899 , G06K9/4652 , G06K9/6269
摘要： Examples are disclosed herein that relate to detecting spoofed human faces. One example provides a computing device comprising a processor configured to compute a first feature distance between registered image data of a human face in a first spectral region and test image data of the human face in the first spectral region, compute a second feature distance between the registered image data and test image data of the human face in a second spectral region, compute a test feature distance between the test image data in the first spectral region and the test image data in the second spectral region, determine, based on a predetermined relationship, whether the human face to which the test image data in the first and second spectral regions corresponds is a real human face or a spoofed human face, and modify a behavior of the computing device.
摘要翻译：这里公开了与检测伪造的人脸有关的示例。一个示例提供了一种计算设备，该计算设备包括处理器，该处理器被配置为计算第一光谱区域中的人脸的登记图像数据与第一光谱区域中的人脸的测试图像数据之间的第一特征距离，计算第二特征距离在第二光谱区域中记录人脸的登记图像数据和测试图像数据，计算第一光谱区域中的测试图像数据和第二光谱区域中的测试图像数据之间的测试特征距离，基于预定关系，第一和第二光谱区域中的测试图像数据所对应的人脸是否是真人脸或欺骗人脸，并且修改计算设备的行为。

4. 发明申请

WO2016037311A1 VARIABLE-COMPONENT DEEP NEURAL NETWORK FOR ROBUST SPEECH RECOGNITION 审中-公开
标题翻译：可变组件深度神经网络，用于强大的语音识别
公开(公告)号：WO2016037311A1
公开(公告)日：2016-03-17
申请号：PCT/CN2014/086121
申请日：2014-09-09
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC , LI, Jinyu , ZHAO, Rui , GONG, Yifan
发明人： LI, Jinyu , ZHAO, Rui , GONG, Yifan
IPC分类号： G10L15/20 , G10L15/06
CPC分类号： G10L15/20 , G10L15/16 , G10L19/24 , G10L25/84
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：提供了包含环境变量的语音识别系统和方法。该系统包括：语音捕获设备（202）; 特征提取模块（204）; 环境变量模块（206），其中所述环境变量模块确定环境变量的值; 和语音识别解码器（208），其中所述语音识别解码器利用深神经网络（DNN）来识别由所述语音捕获设备捕获的语音，其中所述DNN的一个或多个组件被建模为所述环境的一组功能变量。

5. 发明申请

WO2023272466A1 CANONICAL TRAINING FOR HIGHLY CONFIGURABLE MULTILINGUAL SPEECH RECOGNTION 审中-公开
公开(公告)号：WO2023272466A1
公开(公告)日：2023-01-05
申请号：PCT/CN2021/102947
申请日：2021-06-29
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC , LI, Jinyu , ZHOU, Long , SUN, Xie , LIU, Shujie
发明人： LI, Jinyu , ZHOU, Long , SUN, Xie , LIU, Shujie
IPC分类号： G10L15/00 , G10L15/32 , G10L15/16
摘要： Embodiments are provided for building a configurable multilingual model. A computing system obtains a plurality of language-specific automatic speech recognition modules and a universal automatic speech recognition module trained on a multi-language training dataset comprising training data corresponding to each of the plurality of different languages. The computing system then compiles the universal automatic speech recognition module with the plurality of language-specific automatic speech recognition modules to generate a configurable multilingual model that is configured to selectively and dynamically utilize a sub-set of the plurality of language-specific automatic speech recognition modules with the universal automatic speech recognition module to process audio content in response to user input identifying one or more target languages associated with the audio content.

6. 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。

7. 发明申请

WO2003001507A1 HIDDEN MARKOV MODEL WITH FRAME CORRELATION 审中-公开
标题翻译：隐藏MARKOV模型与框架相关
公开(公告)号：WO2003001507A1
公开(公告)日：2003-01-03
申请号：PCT/CN2001/001037
申请日：2001-06-22
申请人： INTEL CORPORATION , INTEL CHINA LTD. , LI, Jinyu , JIA, Ying
发明人： LI, Jinyu , JIA, Ying
IPC分类号： G10L15/14
CPC分类号： G10L15/142 , G10L25/12
摘要： A method and system for incorporating frame correlation in a hidden Markov model is disclosed. The method includes calculating frame independent parts of a speech, inputting the frame independent parts to a Gaussian model, and computing frame probability. Auto-regressive coefficients are then computed from the frame probability.
摘要翻译：公开了一种在隐马尔可夫模型中并入帧相关的方法和系统。该方法包括计算语音的独立于帧的部分，将与帧无关的部分输入到高斯模型，以及计算帧概率。然后根据帧概率计算自回归系数。

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