Back to results
US 12,518,739 B2Granted
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;
- sending, to a first terminal based on the first language, the second audio stream;
- sending, to the AI device, the first audio stream to identify a second language of the first audio stream;
- sending, to a second terminal based on the second language, the first audio stream;
- and
- sending, to a third terminal based on a language identification result and a first interpretation capability parameter, the first audio stream,
- wherein the language identification result is of the first audio stream and is from the AI device,
- wherein the first interpretation capability parameter indicates that a first interpreter that uses the third terminal comprises interpreting the first language into the second language, and
- wherein receiving the second audio stream comprises receiving, from the third terminal, the second audio stream.
7 more elements
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;
- send, to a first terminal based on the first language, the second audio stream;
- send, to the AI device, the first audio stream to identify a second language of the first audio stream;
- send, to a second terminal based on the second language, the first audio stream;
- and
- send, to a third terminal based on a language identification result and a first interpretation capability parameter, the first audio stream,
- wherein the language identification result is of the first audio stream and is from the AI device,
- wherein the first interpretation capability parameter indicates that a first interpreter that uses the third terminal comprises interpreting the first language into the second language, and
- wherein receiving the second audio stream comprises receiving, from the third terminal, the second audio stream.
10 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;
- send, to a first terminal based on the first language, the second audio stream;
- send, to the AI device, the first audio stream to identify a second language of the first audio stream;
- send, to a second terminal based on the second language, the first audio stream;
- and
- send, to a third terminal based on a language identification result and a first interpretation capability parameter, the first audio stream,
- wherein the language identification result is of the first audio stream and is from the AI device,
- wherein the first interpretation capability parameter indicates that a first interpreter that uses the third terminal comprises interpreting the first language into the second language, and
- wherein receiving the second audio stream comprises receiving, from the third terminal, the second audio stream.
7 more elements
Dependencies are inferred from the claim text.