公开(公告)号：US11308937B2

公开(公告)日：2022-04-19

申请号：US16530853

申请日：2019-08-02

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Zhihua Wang ,  Tianxing Yang ,  Zhipeng Wu ,  Bin Peng ,  Chengyuan Zhao

IPC: G10L15/06 ,  G06F40/289 ,  G10L15/26

Abstract: Embodiments of the present disclosure provide a method and an apparatus for identifying a key phrase in audio, a device and a computer readable storage medium. The method for identifying a key phrase in audio includes obtaining audio data to be identified. The method further includes identifying the key phrase in the audio data using a trained key phrase identification model. The key phrase identification model is trained based on first training data for identifying feature information of words in a first training text and second training data for identifying the key phrase in a second training text. In this way, embodiments of the present disclosure can accurately and efficiently identify key information in the audio data.

公开(公告)号：US11410333B2

公开(公告)日：2022-08-09

申请号：US16750403

申请日：2020-01-23

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Xuefei Cui ,  Ye Zhang ,  Chengyuan Zhao ,  Ying Zhu ,  Yilin Zhang ,  Yingjie Shao

IPC: G06T7/77 ,  G06T7/73

Abstract: A method, a device and a computer-readable storage medium for providing a visual representation of a set of objects are provided. The method includes determining a first position in a drawing area, the first position for providing first display information of a first object in the set of objects; determining a usable position associated with the first position from a plurality of preset positions in the drawing area; determining a second object associated with the first object from the set of objects; and providing second display information of the second object in the usable position.