ASSISTED LANGUAGE LEARNING

• US 20180089173A1
• Filed: 09/28/2016
• Published: 03/29/2018
• Est. Priority Date: 09/28/2016
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Prendergast, Orla M., Ryan, Michael J.
• Granted Patent: US 10,540,451 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 40/58 Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
• CPC Class Codes: G10L 15/005 Language recognition
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/228 of application context

Abstract

An approach for predictive translation. The approach monitors one or more audio inputs, wherein monitoring the one or more audio inputs includes collecting a plurality of audio input data from one or more audio input devices. The approach determines one or more user triggers, wherein determining includes detecting the one or more user triggers from the one or more of audio input devices. Responsive to detecting the one or more user triggers, the approach determines whether the one or more audio inputs match one or more stored phrases. Responsive to a determination that the one or more audio inputs match at least one of the one or more stored phrases, the approach presents one or more cues to the user via the audio input device.

Claims

1. A method for predictive translation, the method comprising:

monitoring, by one or more computer processors, one or more audio inputs, wherein monitoring the one or more audio inputs includes collecting a plurality of audio input data from one or more audio input devices;

determining, by the one or more computer processors, one or more user triggers, wherein determining includes detecting the one or more user triggers from the one or more of audio input devices;

responsive to detecting the one or more user triggers, determining, by the one or more computer processors, whether the one or more audio inputs match one or more stored phrases; and

responsive to a determination that the one or more audio inputs match at least one of the one or more stored phrases, presenting, by the one or more computer processors, one or more cues to the user via the audio input device.

2. The method of claim 1, further comprising:

responsive to a determination that the one or more audio inputs do not match at least one of the one or more stored phrases, determining, by the one or more computer processors, whether the one or more audio inputs are in a known language of a user;

responsive to a determination that the one or more audio inputs are in a known language of the user, querying, by the one or more computer processors, one or more servers for one or more translations of the known language into a chosen non-native language, wherein querying the one or more servers includes providing the audio input data and the chosen non-native language to the one or more servers and receiving the one or more translation in the chosen non-native language from the one or more servers; and

presenting, by the one or more computer processors, the one or more translations in the chosen non-native language to the user.

3. The method of claim 1, wherein determining whether the one or more audio inputs match one or more stored phrases, further comprises:

responsive to a determination that the one or more audio inputs include content and one or more contextual indicators that relate to the one or more stored phrases, determining, by the one or more computer processors, the one or more audio inputs match the one or more stored phrases.

4. The method of claim 3, wherein determining whether the one or more audio inputs match one or more stored phrases, further comprises:

responsive to a determination that the one or more audio inputs include content and one or more contextual indicators that do not relate to the one or more stored phrases, determining, by the one or more computer processors, the one or more audio inputs do not match the one or more stored phrases.

5. The method of claim 1, wherein presenting one or more cues to the user via the one or more audio input devices, further comprises:

retrieving, by the one or more computer processors, the one or more stored phrases from one or more local storage devices based, at least in part, on one or more contextual indicators, wherein the one or more contextual indicators include one or more location data, one or more calendar entries, one or more spoken phrases, and one or more spoken languages.

6. The method of claim 5, further comprising at least one of:

outputting, by the one or more computer processors, audio of the one or more stored phrases via the one or more audio input devices; and

displaying, by the one or more computer processors, visual text of the one or more stored phrases via the one or more audio input devices.

7. The method of claim 1, wherein the one or more user triggers include at least one of:

one or more trigger words;

one or more mispronounced words;

or

a pause in a conversation exceeding a predetermined threshold of time.

8. A computer program product for predictive translation, the computer program product comprising:

one or more computer readable storage devices and program instructions stored on the one or more computer readable storage devices, the stored program instructions comprising;

program instructions to monitor one or more audio inputs, wherein monitoring the one or more audio inputs includes collecting a plurality of audio input data from one or more audio input devices;

program instructions to determine one or more user triggers, wherein determining includes detecting the one or more user triggers from the one or more of audio input devices;

responsive to detecting the one or more user triggers, program instructions to determine whether the one or more audio inputs match one or more stored phrases; and

responsive to a determination that the one or more audio inputs match at least one of the one or more stored phrases, program instructions to present one or more cues to the user via the audio input device.

9. The computer program product of claim 8, further comprising:

responsive to a determination that the one or more audio inputs do not match at least one of the one or more stored phrases, program instructions to determine whether the one or more audio inputs are in a known language of a user;

responsive to a determination that the one or more audio inputs are in a known language of the user, program instructions to query one or more servers for one or more translations of the known language into a chosen non-native language, wherein querying the one or more servers includes providing the audio input data and the chosen non-native language to the one or more servers and receiving the one or more translation in the chosen non-native language from the one or more servers; and

program instructions to present the one or more translations in the chosen non-native language to the user.

10. The computer program product of claim 8, wherein determining whether the one or more audio inputs match one or more stored phrases, further comprises:

responsive to a determination that the one or more audio inputs include content and one or more contextual indicators that relate to the one or more stored phrases, program instructions to determine the one or more audio inputs match the one or more stored phrases.

11. The computer program product of claim 10, wherein determining whether the one or more audio inputs match one or more stored phrases, further comprises:

responsive to a determination that the one or more audio inputs include content and one or more contextual indicators that do not relate to the one or more stored phrases, program instructions to determine the one or more audio inputs do not match the one or more stored phrases.

12. The computer program product of claim 8, wherein presenting one or more cues to the user via the one or more audio input devices, further comprises:

program instructions to retrieve the one or more stored phrases from one or more local storage devices based, at least in part, on one or more contextual indicators, wherein the one or more contextual indicators include one or more location data, one or more calendar entries, one or more spoken phrases, and one or more spoken languages.

13. The computer program product of claim 12, further comprising at least one of:

program instructions to output audio of the one or more stored phrases via the one or more audio input devices; and

program instructions to display visual text of the one or more stored phrases via the one or more audio input devices.

14. The computer program product of claim 8, wherein the one or more user triggers include at least one of:

one or more trigger words;

one or more mispronounced words;

or

a pause in a conversation exceeding a predetermined threshold of time.

15. A computer system for predictive translation, the computer system comprising:

one or more computer processors;

one or more computer readable storage devices;

program instructions stored on the one or more computer readable storage devices for execution by at least one of the one or more computer processors, the stored program instructions comprising;

program instructions to monitor one or more audio inputs, wherein monitoring the one or more audio inputs includes collecting a plurality of audio input data from one or more audio input devices;

program instructions to determine one or more user triggers, wherein determining includes detecting the one or more user triggers from the one or more of audio input devices;

responsive to detecting the one or more user triggers, program instructions to determine whether the one or more audio inputs match one or more stored phrases; and

responsive to a determination that the one or more audio inputs match at least one of the one or more stored phrases, program instructions to present one or more cues to the user via the audio input device.

16. The computer system of claim 15, further comprising:

responsive to a determination that the one or more audio inputs do not match at least one of the one or more stored phrases, program instructions to determine whether the one or more audio inputs are in a known language of a user;

responsive to a determination that the one or more audio inputs are in a known language of the user, program instructions to query one or more servers for one or more translations of the known language into a chosen non-native language, wherein querying the one or more servers includes providing the audio input data and the chosen non-native language to the one or more servers and receiving the one or more translation in the chosen non-native language from the one or more servers; and

program instructions to present the one or more translations in the chosen non-native language to the user.

17. The computer system of claim 15, wherein determining whether the one or more audio inputs match one or more stored phrases, further comprises:

responsive to a determination that the one or more audio inputs include content and one or more contextual indicators that relate to the one or more stored phrases, program instructions to determine the one or more audio inputs match the one or more stored phrases.

18. The computer system of claim 17, wherein determining whether the one or more audio inputs match one or more stored phrases, further comprises:

responsive to a determination that the one or more audio inputs include content and one or more contextual indicators that do not relate to the one or more stored phrases, program instructions to determine the one or more audio inputs do not match the one or more stored phrases.

19. The computer system of claim 15, wherein presenting one or more cues to the user via the one or more audio input devices, further comprises:

program instructions to retrieve the one or more stored phrases from one or more local storage devices based, at least in part, on one or more contextual indicators, wherein the one or more contextual indicators include one or more location data, one or more calendar entries, one or more spoken phrases, and one or more spoken languages.

20. The computer system of claim 19, further comprising at least one of:

program instructions to output audio of the one or more stored phrases via the one or more audio input devices; and

program instructions to display visual text of the one or more stored phrases via the one or more audio input devices.