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

WO2023059402A1 ARRAY GEOMETRY AGNOSTIC MULTI-CHANNEL PERSONALIZED SPEECH ENHANCEMENT 审中-公开
公开(公告)号：WO2023059402A1
公开(公告)日：2023-04-13
申请号：PCT/US2022/040979
申请日：2022-08-22
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC.
发明人： ESKIMEZ, Sefik Emre , YOSHIOKA, Takuya , WANG, Huaming , TAHERIAN, Hassan , CHEN, Zhuo , HUANG, Xuedong
IPC分类号： G10L21/0208 , G10L21/0272 , G10L2021/02082 , G10L2021/02087
摘要： Examples of array geometry agnostic multi-channel personalized speech enhancement (PSE) extract speaker embeddings, which represent acoustic characteristics of one or more target speakers, from target speaker enrollment data. Spatial features (e.g., inter-channel phase difference) are extracted from input audio captured by a microphone array. The input audio includes a mixture of speech data of the target speaker(s) and one or more interfering speaker(s). The input audio, the extracted speaker embeddings, and the extracted spatial features are provided to a trained geometry-agnostic PSE model. Output data is produced, which comprises estimated clean speech data of the target speaker(s) that has a reduction (or elimination) of speech data of the interfering speaker(s), without the trained PSE model requiring geometry information for the microphone array.

2. 发明申请

WO2022094740A1 CONTROLLED TRAINING AND USE OF TEXT-TO-SPEECH MODELS AND PERSONALIZED MODEL GENERATED VOICES 审中-公开
公开(公告)号：WO2022094740A1
公开(公告)日：2022-05-12
申请号：PCT/CN2020/126047
申请日：2020-11-03
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC , ZHAO, Sheng , JIANG, Li , HUANG, Xuedong , QIN, Lijuan , HE, Lei , DING, Binggong , YAN, Bo , MA, Chunling , OBEROI, Raunak
发明人： ZHAO, Sheng , JIANG, Li , HUANG, Xuedong , QIN, Lijuan , HE, Lei , DING, Binggong , YAN, Bo , MA, Chunling , OBEROI, Raunak
IPC分类号： G10L13/02
摘要： Systems are configured for generating text-to-speech data in a personalized voice by training a neural text-to-speech machine learning model on natural speech data collected from a particular user, validating the identity of the user from which data is collected, and authorizing requests from users to use the personalized voice in generating new speech data. The systems are further configured to train a machine learning model as a neural text-to-speech model with generated personalized speech data.

3. 发明申请

WO2019152194A1 ARTIFICIAL INTELLIGENCE SYSTEM UTILIZING MICROPHONE ARRAY AND FISHEYE CAMERA 审中-公开
公开(公告)号：WO2019152194A1
公开(公告)日：2019-08-08
申请号：PCT/US2019/013880
申请日：2019-01-16
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： WANG, Zhenghao , HUANG, Xuedong , QIN, Lijuan , WU, Kun , WANG, Huaming
IPC分类号： G06F3/16
CPC分类号： G06K9/6289 , G06F3/017 , G06F3/16 , G06F3/167 , G06K7/10722 , G06K7/1417 , G06K9/00288 , G06N3/08 , G10L17/22 , H04N5/23216 , H04N5/23238 , H04N5/2628 , H04N13/204 , H04R1/222 , H04R1/2892 , H04R2201/401
摘要： In some embodiments, the disclosed subject matter involves a system and method relating to using an ambient capture device including a fisheye camera and a microphone array to capture audio and video in an environment, for use in an artificial intelligence (AI) application. The device with fisheye camera may provide approximately a 360° audio and video view, at relatively low cost. An embodiment may utilize a speech and vision fusion model component. The speech and vision fusion model may be trained using deep learning to combine features from many different sources, including available sensor data from the capture device. A long short term memory (LSTM) model may infer or identify features such as, but not limited to: audio direction; vision detection and tracking; voice signature; facial signature; gesture recognition; and object identification. The fusion processing may be performed by a cloud server, enabling the capture device to remain less complex.

4. 发明申请

WO2021225894A1 MICROSEGMENT SECURE SPEECH TRANSCRIPTION 审中-公开
公开(公告)号：WO2021225894A1
公开(公告)日：2021-11-11
申请号：PCT/US2021/030208
申请日：2021-04-30
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： MALHOTRA, Hemant , HUANG, Xuedong , JIANG, Li , GARCIA DOS SANTOS, Ivo Jose , LI, Dong , CHANG, Shuangyu
IPC分类号： G10L15/06 , G06F21/62
摘要： Embodiments are provided for securing data access to machine learning training data at a plurality of distributed computing devices. Electronic content including original data that corresponds to a preferred data security level is divided into a plurality of microsegments. The plurality of microsegments is restrictively distributed to a plurality of computing devices which apply transcription labels to the plurality of microsegments. The labeled microsegments are reconstructed into training data which is then used to train a machine learning model while facilitating an improvement in data security of the original data included with the training data from the reconstructed microsegments.

5. 发明申请

WO2016053822A1 NATURAL MOTION-BASED CONTROL VIA WEARABLE AND MOBILE DEVICES 审中-公开
标题翻译：基于自动运动的控制通过可移动和移动设备
公开(公告)号：WO2016053822A1
公开(公告)日：2016-04-07
申请号：PCT/US2015/052542
申请日：2015-09-28
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： WANG, Jiaping , LI, Yujia , HUANG, Xuedong , WU, Lingfeng , XIONG, Wei , YAO, Kaisheng , ZWEIG, Geoffrey
IPC分类号： G06F3/01 , G06F3/0346 , H04M1/725
CPC分类号： G06F3/011 , G06F1/163 , G06F3/014 , G06F3/017 , G06F3/0346 , H04M1/7253 , H04M2250/12
摘要： A "Natural Motion Controller" identifies various motions of one or more parts of a user's body to interact with electronic devices, thereby enabling various natural user interface (NUI) scenarios. The Natural Motion Controller constructs composite motion recognition windows by concatenating an adjustable number of sequential periods of inertial sensor data received from a plurality of separate sets of inertial sensors. Each of these separate sets of inertial sensors are coupled to, or otherwise provide sensor data relating to, a separate user worn, carried, or held mobile computing device. Each composite motion recognition window is then passed to a motion recognition model trained by one or more machine-based deep learning processes. This motion recognition model is then applied to the composite motion recognition windows to identify a sequence of one or more predefined motions. Identified motions are then used as the basis for triggering execution of one or more application commands.
摘要翻译： “自然运动控制器”识别用户身体的一个或多个部分与电子设备交互的各种运动，从而实现各种自然用户界面（NUI）场景。自然运动控制器通过连接从多个独立的惯性传感器组接收的可调节数量的惯性传感器数据的连续周期来构建复合运动识别窗口。这些单独的惯性传感器组中的每一个耦合到或者提供与单独的用户佩戴，携带或保持的移动计算设备有关的传感器数据。然后将每个复合运动识别窗口传递到由一个或多个基于机器的深度学习过程训练的运动识别模型。然后将该运动识别模型应用于复合运动识别窗口以识别一个或多个预定运动的序列。然后将识别的运动用作触发一个或多个应用程序命令的执行的基础。

6. 发明申请

WO2016048763A1 UNIVERSAL INTERACTION FOR CAPTURING CONTENT TO PERSISTENT STORAGE 审中-公开
标题翻译：通用互动捕获内存到持久存储
公开(公告)号：WO2016048763A1
公开(公告)日：2016-03-31
申请号：PCT/US2015/050542
申请日：2015-09-17
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： DIXIT, Madhur , VAISHAMPAYAN, Chinmay , GEORGE, Justin Varacheril , KAMDAR, Nirav Ashwin , MENON, Deepak Achuthan , THIRUMALAI-ANANDANPILLAI, Srinivasa V. , KHATRA, Ramindar Singh , HUANG, Xuedong , VISWANATHAN, Akshad
IPC分类号： G06F9/44 , G06F9/54 , G06F3/0484
CPC分类号： G06F17/30589 , G06F3/0481 , G06F3/0488 , G06F9/451 , G06F9/543 , H04L67/1097
摘要： Systems and methods for enhanced content capture on a computing device are presented. In operation, a user interaction is detected on a computing device with the intent to capture content to a content store associated with the computer user operating the computing device. A content capture service is executed to capture content to the content store, comprising the following: applications executing on the computing device are notified to suspend output to display views corresponding to the applications; content to be captured to the content store is identified and obtained; the applications executing on the computing device are notified to resume output to display views; and automatically storing the obtained content in a content store associated with the computer user.
摘要翻译：提出了用于在计算设备上增强内容捕获的系统和方法。在操作中，在计算设备上检测到用户交互，意图将内容捕获到与操作计算设备的计算机用户相关联的内容存储。执行内容捕获服务以将内容捕获到内容存储，包括以下：通知在计算设备上执行的应用程序挂起输出以显示与应用相对应的视图; 识别并获取要捕获到内容商店的内容; 通知计算装置上执行的应用程序恢复输出以显示视图; 并将获得的内容自动存储在与计算机用户相关联的内容存储器中。

7. 发明申请

WO2021242399A1 AUTOMATED MEETING MINUTES GENERATOR 审中-公开
公开(公告)号：WO2021242399A1
公开(公告)日：2021-12-02
申请号：PCT/US2021/025286
申请日：2021-04-01
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： ZHU, Chenguang , SHI, Yu , HINTHORN, William Isaac , ZENG, Nanshan , XU, Ruochen , LU, Liyang , HUANG, Xuedong
IPC分类号： G10L15/26 , G06F40/211 , G06F40/247 , G06F40/253 , G06F40/56 , H04L12/18 , G06F16/34
摘要： A transcription of audio speech included in electronic content associated with a meeting is created by an ASR model trained on speech-to-text data. The transcription is post-processed by modifying text included in the transcription, for example, by modifying punctuation, grammar, or formatting introduced by the ASR model and by changing or omitting one or more words that were included in both the audio speech and the transcription. After the transcription is post-processed, output based on the post-processed transcription is generated in the form of a meeting summary and/or template.

8. 发明申请

WO2017210095A3 NO LOSS-OPTIMIZATION FOR WEIGHTED TRANSDUCER 审中-公开
公开(公告)号：WO2017210095A3
公开(公告)日：2017-12-07
申请号：PCT/US2017/034598
申请日：2017-05-26
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： WANG, Zhenghao , HUANG, Xuedong , WANG, Huaming
IPC分类号： G10L15/183 , G10L15/14
摘要： Techniques and architectures may be used to generate and perform a process using weighted finite-state transducers involving generic input search graphs. The process need not pursue theoretical optimality and instead search graphs may be optimized without an a priori optimization step. The process may result in an automatic speech recognition (ASR) decoder that is substantially faster than ASR decoders the include the optimization step.

9. 发明申请

WO2022026021A1 DYNAMIC GRADIENT AGGREGATION FOR TRAINING NEURAL NETWORKS 审中-公开
公开(公告)号：WO2022026021A1
公开(公告)日：2022-02-03
申请号：PCT/US2021/030760
申请日：2021-05-05
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： DIMITRIADIS, Dimitrios B. , KUMATANI, Kenichi , GMYR, Robert Peter , ITAGAKI, Masaki , GAUR, Yashesh , ZENG, Nanshan , HUANG, Xuedong
IPC分类号： G06N3/04 , G06N3/08
摘要： The disclosure herein describes training a global model based on a plurality of data sets. The global model is applied to each data set of the plurality of data sets and a plurality of gradients is generated based on that application. At least one gradient quality metric is determined for each gradient of the plurality of gradients. Based on the determined gradient quality metrics of the plurality of gradients, a plurality of weight factors is calculated. The plurality of gradients is transformed into a plurality of weighted gradients based on the calculated plurality of weight factors and a global gradient is generated based on the plurality of weighted gradients. The global model is updated based on the global gradient, wherein the updated global model, when applied to a data set, performs a task based on the data set and provides model output based on performing the task.

10. 发明申请

WO2019212920A1 COMPUTERIZED INTELLIGENT ASSISTANT FOR CONFERENCES 审中-公开
公开(公告)号：WO2019212920A1
公开(公告)日：2019-11-07
申请号：PCT/US2019/029517
申请日：2019-04-27
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： DIAMANT, Adi , MASTER BEN-DOR, Karen , KRUPKA, Eyal , HALALY, Raz , SMOLIN, Yoni , GURVICH, Ilya , HURVITZ, Aviv , QIN, Lijuan , XIONG, Wei , ZHANG, Shixiong , WU, Lingfeng , XIAO, Xiong , LEICHTER, Ido , DAVID, Moshe , HUANG, Xuedong , AGARWAL, Amit Kumar
IPC分类号： H04N7/14
摘要： A method for facilitating a remote conference includes receiving a digital video and a computer-readable audio signal. A face recognition machine is operated to recognize a face of a first conference participant in the digital video, and a speech recognition machine is operated to translate the computer-readable audio signal into a first text. An attribution machine attributes the text to the first conference participant. A second computer-readable audio signal is processed similarly, to obtain a second text attributed to a second conference participant. A transcription machine automatically creates a transcript including the first text attributed to the first conference participant and the second text attributed to the second conference participant.

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