-
公开(公告)号:US20210390945A1
公开(公告)日:2021-12-16
申请号:US17221701
申请日:2021-04-02
申请人: Baidu USA, LLC
发明人: Sibo ZHANG , Jiahong YUAN , Miao LIAO , Liangjun ZHANG
IPC分类号: G10L13/08 , G10L13/027 , G06N3/04 , G06N3/08 , G06F40/242 , G10L15/187 , G06F16/783 , G06F16/78
摘要: Presented herein are novel approaches to synthesize video of the speech from text. In a training phase, embodiments build a phoneme-pose dictionary and train a generative neural network model using a generative adversarial network (GAN) to generate video from interpolated phoneme poses. In deployment, the trained generative neural network in conjunction with the phoneme-pose dictionary convert an input text into a video of a person speaking the words of the input text. Compared to audio-driven video generation approaches, the embodiments herein have a number of advantages: 1) they only need a fraction of the training data used by an audio-driven approach; 2) they are more flexible and not subject to vulnerability due to speaker variation; and 3) they significantly reduce the preprocessing, training, and inference times.
-
公开(公告)号:US20210390463A1
公开(公告)日:2021-12-16
申请号:US16900584
申请日:2020-06-12
申请人: Baidu USA LLC
发明人: Yueqiang CHENG , Hefei ZHU
摘要: A method to transfer an artificial intelligence (AI) model includes identifying a plurality of layers of the AI model, the plurality of layers organized in a first ordered list. The method further includes randomizing the plurality of layers by reorganizing the first ordered list into a second ordered list, and transferring the plurality of layers of the AI model to a data processing accelerator in an order defined by the second ordered list.
-
公开(公告)号:US20210390047A1
公开(公告)日:2021-12-16
申请号:US16900597
申请日:2020-06-12
申请人: Baidu USA LLC
发明人: Yueqiang CHENG , Hefei ZHU
摘要: A method to transfer an artificial intelligence (AI) model includes identifying a plurality of layers of an AI model, wherein each layer of the plurality of layers is associated with a memory address. The method further includes randomizing the memory address associated with each layer of the plurality of layers, and transferring the plurality of layers with the randomized memory addresses to a data processing accelerator to execute the AI model.
-
公开(公告)号:US11199842B2
公开(公告)日:2021-12-14
申请号:US16019245
申请日:2018-06-26
申请人: Baidu USA LLC
发明人: Liangliang Zhang , Dong Li , Jiangtao Hu , Jiaming Tao , Yifei Jiang , Fan Zhu
摘要: An autonomous driving vehicle (ADV) may determine a predicted path for a moving obstacle and speeds for different portions of the path. The ADV use multiple threads in parallel to determine the path and speeds for the different portions of the path.
-
95.
公开(公告)号:US11198444B2
公开(公告)日:2021-12-14
申请号:US16510124
申请日:2019-07-12
申请人: Baidu USA LLC
发明人: Tiffany Zhang , Kwan Oh , Manjiang Zhang
摘要: Diagnosing a sensor processing unit of an autonomous driving vehicle is described. An example computer-implemented method can include transmitting an executable image of a sensor processing application from a host system to the sensor processing unit via at least one of a universal asynchronous receiver-transmitter (UART) or an Ethernet connection. The method also includes causing the sensor processing unit to execute and launch the executable image of the sensor processing application in the DRAM from the eMMC storage device. The method also includes transmitting a sequence of predetermined commands to the executed sensor processing application to perform a plurality of sensor data processing operations on sensor data obtained from a plurality of sensors or sensor simulators associated with an autonomous driving vehicle. The method also includes comparing processing results of the sensor processing operations against expected processing results to determine whether the sensor processing application operates properly.
-
公开(公告)号:US11194860B2
公开(公告)日:2021-12-07
申请号:US15207445
申请日:2016-07-11
申请人: Baidu USA, LLC
发明人: Erheng Zhong , Chaochun Liu , Yusheng Xie , Nan Du , Hongliang Fei , Yi Zhen , Yu Cao , Richard Chun Ching Wang , Dawen Zhou , Wei Fan
IPC分类号: G06F16/901 , G16H50/70 , G16H10/20 , G16H50/30 , G16H50/20
摘要: Systems and methods are disclosed for question generation to obtain more related medical information based on observed symptoms from a patient. In embodiments, possible diseases associated with the observed symptoms are generated by querying a knowledge graph. In embodiments, candidate symptoms associated with the possible diseases are also identified and are combined with the observed symptoms to obtain combined symptom sets. In embodiments, discriminative scores for the candidate symptom sets are determined and candidate symptoms with top discriminative scores are selected. In embodiments, these selected candidate symptoms may be checked for conflicts with observed symptoms and removed from further consideration if a conflict exists. In embodiments, one or more questions may be generated based on the remaining selected candidate systems to aid in collecting information about the patient. In embodiments, the process may be repeated with the updated observed symptoms.
-
公开(公告)号:US20210378141A1
公开(公告)日:2021-12-02
申请号:US16884969
申请日:2020-05-27
申请人: Baidu USA LLC
发明人: Shuai Shao , Tianyi Gao
摘要: A holder for an electronic rack includes a pivot point and a first end of the holder having a first blind-mate connector to be coupled to a second blind-mate connector at a first engagement interface. The first blind-mate connector and the second blind-mate connector are coupled in response to the holder moving to the second position in response to contact with the electronic rack. The holder additionally includes a second end of the holder having a third blind-mate connector to be coupled to a fourth blind-mate connector at a second engagement interface. The third blind-mate connector and the fourth blind-mate connector are coupled in response to the holder moving to the second position in response to contact with the electronic rack.
-
98.
公开(公告)号:US20210373161A1
公开(公告)日:2021-12-02
申请号:US16337390
申请日:2019-01-30
发明人: Weixin LU , Yao ZHOU , Guowei WAN , Shenhua HOU , Shiyu SONG
IPC分类号: G01S17/89 , G01S17/931 , G05D1/02 , G06T7/73 , G06N3/08
摘要: In one embodiment, a method for solution inference using neural networks in LiDAR localization includes constructing a cost volume in a solution space for a predicted pose of an autonomous driving vehicle (ADV), the cost volume including a number of sub volumes, each sub volume representing a matching cost between a keypoint from an online point cloud and a corresponding keypoint on a pre-built point cloud map. The method further includes regularizing the cost volume using convention neural networks (CNNs) to refine the matching costs; and inferring, from the regularized cost volume, an optimal offset of the predicted pose. The optimal offset can be used to determining a location of the
-
99.
公开(公告)号:US20210365712A1
公开(公告)日:2021-11-25
申请号:US16337387
申请日:2019-01-30
发明人: Weixin LU , Yao ZHOU , Guowei WAN , Shenhua HOU , Shiyu SONG
摘要: In one embodiment, a method for extracting point cloud features for use in localizing an autonomous driving vehicle (ADV) includes selecting a first set of keypoints from an online point cloud, the online point cloud generated by a LiDAR device on the ADV for a predicted pose of the ADV; and extracting a first set of feature descriptors from the first set of keypoints using a feature learning neural network running on the ADV, The method further includes locating a second set of keypoints on a pre-built point cloud map, each keypoint of the second set of keypoints corresponding to a keypoint of the first set of keypoint; extracting a second set of feature descriptors from the pre-built point cloud map; and estimating a position and orientation of the ADV based on the first set of feature descriptors, the second set of feature descriptors, and a predicted pose of the ADV.
-
公开(公告)号:US11182917B2
公开(公告)日:2021-11-23
申请号:US16483399
申请日:2017-12-08
发明人: Le Kang , Yupeng Li , Wei Qi , Yingze Bao
摘要: Described herein are systems and methods that allow for dense depth map estimation given input images. In one or more embodiments, a neural network model was developed that significantly differs from prior approaches. Embodiments of the deep neural network model comprises more computationally efficient structures and fewer layers but still produces good quality results. Also, in one or more embodiments, the deep neural network model may be specially configured and trained to operate using a hardware accelerator component or components that can speed computation and produce good results, even if lower precision bit representations are used during computation at the hardware accelerator component.
-
-
-
-
-
-
-
-
-