公开(公告)号：US20210312926A1

公开(公告)日：2021-10-07

申请号：US17351140

申请日：2021-06-17

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

Inventor： Xingbiao Li ,  Hanmei Xie ,  Huimin Fan ,  Huibin Zhao ,  Meiyuan Ding ,  Lina Hu

IPC: G10L15/26 ,  G10L15/30 ,  G06F40/166 ,  G06F40/149 ,  G10L15/22 ,  G10L25/51 ,  G06Q10/10 ,  G06N20/00

Abstract: The present disclosure discloses a method, apparatus, system and electronic device for processing information and storage medium, relates to artificial intelligence technology fields such as speech recognition, speech synthesis and natural language processing. An implementation solution is: receiving audio data of a corresponding role sent by each client, and determining a role identifier of each of the audio data and starting time of each of the audio data; converting each of the received audio data to generate each text information; performing merging operation, in response to receiving a merging operation instruction and not meeting a merging stop condition, on all text information to generate each first text; and performing integration operation, in response to meeting the merging stop condition, on each of the first text to generate a second text corresponding to each of the first text.

公开(公告)号：US11488603B2

公开(公告)日：2022-11-01

申请号：US16711310

申请日：2019-12-11

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

Inventor： Wanqi Tang ,  Jiamei Kang ,  Lixia Zeng ,  Yijing Zhou ,  Hanmei Xie ,  Lina Zhu

IPC: G10L15/04 ,  G10L15/22 ,  G10L15/26

Abstract: Embodiments of the present disclosure provide a method and apparatus for processing a speech. The method may include: acquiring an original speech; performing speech recognition on the original speech, to obtain an original text corresponding to the original speech; associating a speech segment in the original speech with a text segment in the original text; recognizing an abnormal segment in the original speech and/or the original text; and processing a text segment indicated by the abnormal segment in the original text and/or the speech segment indicated by the abnormal segment in the original speech, to generate a final speech. A speech segment in the original speech is associated with a text segment in the original text to realize visual processing of the speech.