公开(公告)号：US20180150605A1

公开(公告)日：2018-05-31

申请号：US15362643

申请日：2016-11-28

Applicant: Google Inc.

Inventor： Christopher S. Co ,  Navdeep Jaitly ,  Lily Hao Yi Peng ,  Katherine Irene Chou ,  Ananth Sankar

IPC: G06F19/00 ,  G06F17/28 ,  G10L15/06 ,  G10L15/14 ,  G10L15/16 ,  G10L15/183

CPC classification number: G06F19/328 ,  G06F17/2836 ,  G06F17/289 ,  G10L15/063 ,  G10L15/142 ,  G10L15/16 ,  G10L15/1822 ,  G10L15/183 ,  G10L15/26

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for speech recognition. One method includes obtaining an input acoustic sequence, the input acoustic sequence representing one or more utterances; processing the input acoustic sequence using a speech recognition model to generate a transcription of the input acoustic sequence, wherein the speech recognition model comprises a domain-specific language model; and providing the generated transcription of the input acoustic sequence as input to a domain-specific predictive model to generate structured text content that is derived from the transcription of the input acoustic sequence.

公开(公告)号：US09916070B1

公开(公告)日：2018-03-13

申请号：US14502369

申请日：2014-09-30

Applicant: Google Inc.

Inventor： Reuel William Nash ,  Christopher S. Co ,  Andrew Kirmse

IPC: G06F3/0484 ,  G06F3/0482

CPC classification number: G06F3/04842 ,  G06F3/0482 ,  G06F3/04847 ,  G06F17/30241 ,  G06F17/30244 ,  G06F17/30247 ,  G06F17/30265 ,  G06F17/3028

Abstract: The present invention pertains to geographical image processing of time-dependent imagery. Various assets acquired at different times are stored and processing according to acquisition date in order to generate one or more image tiles for a geographical region of interest. The different image tiles are sorted based on asset acquisition date. Multiple image tiles for the same region of interest may be available. In response to a user request for imagery as of a certain date, one or more image tiles associated with assets from prior to that date are used to generate a time-based geographical image for the user.

公开(公告)号：US20150154796A1

公开(公告)日：2015-06-04

申请号：US13897553

申请日：2013-05-20

Applicant: Google Inc.

Inventor： Christopher S. Co

IPC: G06T17/10

CPC classification number: G06T17/20 ,  G06T9/001 ,  G06T9/40 ,  G06T17/005

Abstract: Aspects of the present disclosure relate to building volumetric data structures for intersection testing. For example, 3D data may be represented by points associated with triangles. The triangles may be rasterized to a 3D grid. Each cell of the grid may contain a set of triangles. The grid may be used to generate a new grid of larger grid cells, where each larger grid cell represents some portion of cells of the original grid. The triangle data from each new cell may then be encoded as a list of integers including the triangle data. The list of values may be run-length-encoded. The result is a single octree cube. This process may be repeated in order to generate additional octree cubes for the volumetric structure. The volumetric structure may then be used to identify triangles that intersect with a given ray.

Abstract translation: 本公开的方面涉及建立用于交叉测试的体积数据结构。 例如，3D数据可以由与三角形相关联的点来表示。 三角形可以被光栅化到3D网格。 网格的每个单元格可能包含一组三角形。 网格可以用于生成较大网格单元的新网格，其中每个较大的网格单元表示原始网格的单元格的一部分。 然后可以将来自每个新单元的三角形数据编码为包括三角形数据的整数列表。 值列表可以被运行长度编码。 结果是单个八叉树立方体。 可以重复该过程，以便为体积结构生成附加的八叉树立方体。 然后可以使用体积结构来识别与给定射线相交的三角形。

公开(公告)号：US09245383B2

公开(公告)日：2016-01-26

申请号：US13897553

申请日：2013-05-20

Applicant: Google Inc.

Inventor： Christopher S. Co

IPC: G06T17/00 ,  G06T17/20 ,  G06T9/00 ,  G06T9/40

CPC classification number: G06T17/20 ,  G06T9/001 ,  G06T9/40 ,  G06T17/005

Abstract: Aspects of the present disclosure relate to building volumetric data structures for intersection testing. For example, 3D data may be represented by points associated with triangles. The triangles may be rasterized to a 3D grid. Each cell of the grid may contain a set of triangles. The grid may be used to generate a new grid of larger grid cells, where each larger grid cell represents some portion of cells of the original grid. The triangle data from each new cell may then be encoded as a list of integers including the triangle data. The list of values may be run-length-encoded. The result is a single octree cube. This process may be repeated in order to generate additional octree cubes for the volumetric structure. The volumetric structure may then be used to identify triangles that intersect with a given ray.

Abstract translation: 本公开的方面涉及建立用于交叉测试的体积数据结构。 例如，3D数据可以由与三角形相关联的点来表示。 三角形可以被光栅化到3D网格。 网格的每个单元格可能包含一组三角形。 网格可以用于生成较大网格单元的新网格，其中每个较大的网格单元表示原始网格的单元格的一部分。 然后可以将来自每个新单元的三角形数据编码为包括三角形数据的整数列表。 值列表可以被运行长度编码。 结果是单个八叉树立方体。 可以重复该过程，以便为体积结构生成附加的八叉树立方体。 然后可以使用体积结构来识别与给定射线相交的三角形。