Techniques for real-time translation of a media feed from a speaker computing device and distribution to multiple listener computing devices in multiple different languages

Patent metadata

Field	Value
Publication number	US-9542486-B2
Application number	US-201414289928-A
Country	US
Kind code	B2
Filing date	May 29, 2014
Priority date	May 29, 2014
Publication date	Jan 10, 2017
Grant date	Jan 10, 2017

Abstract

A computer-implemented technique can include receiving a media feed from a speaker computing device representing speech of a speaker user captured by the speaker computing device. The technique can include receiving a plurality of translation requests, each translation request being received from a listener computing device associated with a listener user and corresponding to a request to obtain a translated version of the media feed into a preferred language of the listener user. The technique can include determining the preferred language for each listener user. The technique can include obtaining a machine translated media feed for each of the translation requests, the machine translated media feed corresponding to a translation of the media feed from the source language to the preferred language of the listener user associated with the translation request. The technique can also include outputting the machine translated media feeds to the listener computing devices.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
receiving, at a server having one or more processors, a media feed from a speaker computing device, the media feed corresponding to a representation of speech of a speaker user in a source language that is captured by the speaker computing device;
receiving, at the server, a plurality of translation requests, each translation request being received from a listener computing device associated with a listener user and corresponding to a request to obtain a translated version of the media feed into a target language of the listener user;
determining, at the server, a preferred language for each listener user;
obtaining, at the server, a machine translated media feed for each of the translation requests, the machine translated media feed corresponding to a translation of the media feed from the source language to the preferred language of the listener user associated with the translation request; and
outputting, from the server, the machine translated media feeds to the listener computing devices.

2. The computer-implemented method of claim 1 , further comprising receiving, at the server from the speaker computing device, an initialization request for the server to provide the machine translated media feeds in response to the translation requests.

3. The computer-implemented method of claim 2 , further comprising outputting, from the server, a unique identifier in response to receiving the initialization request, wherein each of the translation requests are generated in response to inputting the unique identifier at the respective listener computing devices.

4. The computer-implemented method of claim 3 , wherein the unique identifier is a unique uniform resource locator (URL) or a unique two-dimensional barcode.

5. The computer-implemented method of claim 1 , wherein receiving each translation request at the server includes receiving, at the server, each translation request from the speaker computing device in response to the speaker computing device receiving each translation request from its respective listener computing device via short-range wireless communication.

6. The computer-implemented method of claim 5 , wherein outputting each machine translated media feed to its respective listener computing device includes transmitting, from the server, each machine translated media feed to the speaker computing device, wherein receiving each translated media feed causes the speaker computing device to transmit each machine translated media feed to its respective listener computing device via short-range wireless communication.

7. The computer-implemented method of claim 1 , wherein the media feed includes at least one of (i) an audio stream in the source language and (ii) text in the source language transcribed from the audio stream.

8. The computer-implemented method of claim 1 , wherein the machine translated media feed includes at least one of (i) an audio stream in the target language and (ii) text in the target language transcribed from the audio stream.

9. The computer-implemented method of claim 1 , wherein the speaker computing device is a mobile computing device.

10. The computer-implemented method of claim 9 , wherein the mobile computing device is wearable, computer-implemented eyewear.

11. A system including a server having one or more processors configured to perform operations comprising:
receiving a media feed from a speaker computing device, the media feed corresponding to a representation of speech of a speaker user in a source language that is captured by the speaker computing device;
receiving a plurality of translation requests, each translation request being received from a listener computing device associated with a listener user and corresponding to a request to obtain a translated version of the media feed into a target language of the listener user;
determining a preferred language for each listener user;
obtaining a machine translated media feed for each of the translation requests, the machine translated media feed corresponding to a translation of the media feed from the source language to the preferred language of the listener user associated with the translation request; and
outputting the machine translated media feeds to the listener computing devices.

12. The system of claim 11 , wherein the operations further comprise receiving, from the speaker computing device, an initialization request for the server to provide the machine translated media feeds in response to the translation requests.

13. The system of claim 12 , wherein the operations further comprise outputting a unique identifier in response to receiving the initialization request, wherein each of the translation requests are generated in response to inputting the unique identifier at the respective listener computing devices.

14. The system of claim 13 , wherein the unique identifier is a unique uniform resource locator (URL) or a unique two-dimensional barcode.

15. The system of claim 11 , wherein receiving each translation request at the server includes receiving each translation request from the speaker computing device in response to the speaker computing device receiving each translation request from its respective listener computing device via short-range wireless communication.

16. The system of claim 15 , wherein outputting each machine translated media feed to its respective listener computing device includes transmitting each machine translated media feed to the speaker computing device, wherein receiving each translated media feed causes the speaker computing device to transmit each machine translated media feed to its respective listener computing device via short-range wireless communication.

17. The system of claim 11 , wherein the media feed includes at least one of (i) an audio stream in the source language and (ii) text in the source language transcribed from the audio stream.

18. The system of claim 11 , wherein the machine translated media feed includes at least one of (i) an audio stream in the target language and (ii) text in the target language transcribed from the audio stream.

19. The system of claim 11 , wherein the speaker computing device is a mobile computing device.

20. The system of claim 19 , wherein the mobile computing device is wearable, computer-implemented eyewear.

Assignees

• Google Inc

Inventors

• Cuthbert Alexander Jay
• Estelle Joshua James

Classifications

• G06F40/58

  Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation · CPC title

• G06F16/683 Primary

  using metadata automatically derived from the content · CPC title

• G06F40/45

  Example-based machine translation; Alignment · CPC title

• G06F40/55

  Rule-based translation · CPC title

• G06F17/30743 Primary

  Physics · mapped topic