公开(公告)号：US20210365285A1

公开(公告)日：2021-11-25

申请号：US17396544

申请日：2021-08-06

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

Inventor： Jingwei PENG ,  Shengyong ZUO ,  Yi ZHOU ,  Qie YIN

IPC: G06F9/48 ,  G06F9/54 ,  G10L15/00

Abstract: The present application discloses a voice data processing method, an apparatus, a device and a storage media. The specific implementation solution is: starting a microphone management thread to collect audio data acquired by a microphone in a process of a voice interactive application, and when the voice interactive application is in a non-wake-up state, starting a wake-up thread to perform wake-up processing on the voice interactive application according to the audio data, there is no need to request the microphone separately by a recognition engine which performs voice recognition on the audio data collected by the microphone management thread, thereby realizing the wake-up engine and the recognition engine in the same process. The wake-up engine and the recognition engine avoid a problem of losing part of data due to waiting for preparation of the microphone, and improve efficiency and accuracy of the voice interactive application.

公开(公告)号：US20210193143A1

公开(公告)日：2021-06-24

申请号：US17128994

申请日：2020-12-21

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

Inventor： Yi ZHOU ,  Qie YIN ,  Long ZHANG ,  Zhen CHEN

IPC: G10L15/22 ,  G10L15/26 ,  G10L25/51 ,  G06F16/33 ,  G06F16/2458

Abstract: The present application discloses a speech recognition method, apparatus, device and readable storage medium, and relates to the technical field of artificial intelligence. A specific implementation includes: an electronic device recognizes a speech signal to obtain a first text; if a first pinyin sequence corresponding to the first text exists in the database, the electronic device uses a correct text corresponding to the first pinyin sequence as the speech recognition result; otherwise, the electronic device performs a fuzzy matching on the first pinyin sequence to obtain multiple second pinyin sequences and second texts corresponding to the second pinyin sequences, and selects the speech recognition result from the multiple second texts.