公开(公告)号：US20210295857A1

公开(公告)日：2021-09-23

申请号：US17035548

申请日：2020-09-28

Applicant: Beijing Baidu Netcom Science and Technology Co., Ltd.

Inventor： Nengjun OUYANG ,  Junhua XU ,  Zhengbin SONG ,  Danqing YANG ,  Gang XU

IPC: G10L21/0216 ,  B60R16/037 ,  G10L15/20

Abstract: This application discloses a voice recognition method, a voice recognition apparatus, an electronic device and a computer readable storage medium, and relates to the field of voice recognition technology. A specific implementation is: performing a latency estimation according to a first microphone signal and a first reference signal in a preset time period to obtain a latency value; acquiring a system audio signal, and processing the system audio signal by using the latency value to obtain a second reference signal; performing de-noising processing on a collected second microphone signal according to the second reference signal, to obtain a to-be-recognized voice signal; and performing recognition on the to-be-recognized voice signal.

公开(公告)号：US20210390947A1

公开(公告)日：2021-12-16

申请号：US17117786

申请日：2020-12-10

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

Inventor： Nengjun OUYANG ,  Ke ZHAO ,  Rong LIU

IPC: G10L15/05 ,  G10L15/06 ,  G10L17/04

Abstract: A method and an apparatus for outputting information are provided. The method includes acquiring voice information received within a preset time period before a device is awakened, where the device is provided with a wake-up model for outputting preset response information when a preset wake-up word is received; performing speech recognition on the voice information to obtain a recognition result; extracting feature information of the voice information in response to determining that the recognition result does not include a preset wake-up word; generating a counterexample training sample according to the feature information; and training the wake-up model using a counter-example training sample, and outputting the trained wake-up model.