Back to results
US 2023/0326448 A1Published application
Method, Apparatus, and System for Implementing Simultaneous Interpretation
AssigneeHuawei Cloud Computing Technologies Co., Ltd.
InventorYu Xia
Life of this patent
Estimating the term…
Abstract
A media server receives an audio stream of a conference speaker and an audio stream interpreted based on the audio stream, sends the interpreted audio stream to an artificial intelligence (AI) device to identify a language of the interpreted audio stream, and forwards the interpreted audio stream to a corresponding terminal based on an identification result.
Claims20
A method, comprising:
- receiving a first audio stream and a second audio stream, wherein the second audio stream is based on an interpretation of the first audio stream;
- sending, to an artificial intelligence (AI) device, the second audio stream to identify a first language of the second audio stream;
- and
- sending, to a first terminal based on the first language, the second audio stream.
1 more element
An apparatus, comprising:
- a memory configured to store instructions;
- and
- one or more processors coupled to the memory and configured to execute the instructions to:
- receive a first audio stream and a second audio stream, wherein the second audio stream is based on an interpretation of the first audio stream;
- send, to an artificial intelligence (AI) device, the second audio stream to identify a first language of the second audio stream;
- and
- send, to a first terminal based on the first language, the second audio stream.
4 more elements
A computer program product comprising instructions stored on a non-transitory computer-readable medium that, when executed by one or more processors, cause an apparatus to:
- receive a first audio stream and a second audio stream, wherein the second audio stream is based on an interpretation of the first audio stream;
- send, to an artificial intelligence (AI) device, the second audio stream to identify a first language of the second audio stream;
- and
- send, to a first terminal based on the first language, the second audio stream.
1 more element
Dependencies are inferred from the claim text.