Translation techniques with adjustable utterance gaps

Patent metadata

Field	Value
Publication number	US-11227125-B2
Application number	US-201916594971-A
Country	US
Kind code	B2
Filing date	Oct 7, 2019
Priority date	Sep 27, 2016
Publication date	Jan 18, 2022
Grant date	Jan 18, 2022

Abstract

A plurality of utterances of a first user from the language of the first user is translated into a language of a second user. The confidence scores associated with the translated utterances are compared with a confidence threshold. A predetermined utterance gap is adjusted based on the comparison. The predetermined utterance gap is a duration of time that occurs between utterances.

First claim

What is claimed is:

1. A method, comprising:
receiving a plurality of utterances of a first person in a first language;
detecting an utterance gap between sequential utterances of the plurality of utterances;
translating the plurality of utterances from the first language to a second language to produce a plurality of translated utterances;
determining a translation confidence score for each utterance of the plurality of translated utterances, to produce accrued translation confidence scores for the plurality of utterances;
determining whether a percentage of the accrued translation confidence scores is:
less than a confidence threshold; or
greater than the confidence threshold;

in accordance with a determination that the percentage of the accrued translation scores is less than the confidence threshold, increasing the utterance gap; and
in accordance with a determination that the percentage of the accrued translation scores is greater than the confidence threshold, decreasing the utterance gap.

2. The method of claim 1 , wherein decreasing the utterance gap results at least in part in increasing a number of translated utterances that are output.

3. The method of claim 1 , wherein decreasing the utterance gap results at least in part in increasing a rate at which translated utterances are output.

4. The method of claim 1 , wherein increasing the utterance gap results at least in part in decreasing a number of translated utterances that are output.

5. The method of claim 1 , wherein increasing the utterance gap results at least in part in decreasing a rate at which translated utterances are output.

6. The method of claim 1 , further comprising:
determining whether the percentage of the accrued translation confidence scores is equal to the confidence threshold; and
in accordance with a determination that the accrued translation confidence scores is equal to the confidence threshold, decreasing the utterance gap.

7. The method of claim 1 , wherein the confidence threshold corresponds to a percentage of accurate translations.

8. A system, comprising:
a processor configured for:
receiving a plurality of utterances of a first person in a first language;
detecting an utterance gap between sequential utterances of the plurality of utterances;
translating the plurality of utterances from the first language to a second language to produce a plurality of translated utterances;
determining a translation confidence score for each utterance of the plurality of translated utterances, to produce accrued translation confidence scores for the plurality of utterances;
determining whether a percentage of the accrued translation confidence scores is:
less than a confidence threshold; or
greater than the confidence threshold;

in accordance with a determination that the percentage of the accrued translation score is less than the confidence threshold, increasing the utterance gap; and
in accordance with a determination that the percentage of the accrued translation score is greater than the confidence threshold, decreasing the utterance gap.

9. The system of claim 8 , wherein the processor is configured for increasing a number of translated utterances that are output in conjunction with decreasing the utterance gap.

10. The system of claim 8 , wherein the processor is configured for increasing a rate at which translated utterances are output in conjunction with decreasing the utterance gap.

11. The system of claim 8 , wherein the processor is configured for decreasing a number of translated utterances that are output in conjunction with increasing the utterance gap.

12. The system of claim 8 , wherein the processor is configured for decreasing a rate at which translated utterances are output in conjunction with increasing the utterance gap.

13. The system of claim 8 , wherein the processor is configured for:
determining whether the percentage of the accrued translation confidence scores is equal to the confidence threshold; and
in accordance with a determination that the percentage of the accrued translation score is equal to the confidence threshold, decreasing the utterance gap.

14. The system of claim 8 , wherein the confidence threshold corresponds to a percentage of accurate translations.

15. A computer program product, the computer program product being embodied in a non-transitory computer readable storage medium and comprising computer instructions for:
receiving a plurality of utterances of a first person in a first language;
detecting an utterance gap between sequential utterances of the plurality of utterances;
translating the plurality of utterances from the first language to a second language to produce a plurality of translated utterances;
determining a translation confidence score for each utterance of the plurality of translated utterances, to produce accrued translation confidence scores for the plurality of utterances;
determining whether a percentage of the accrued translation confidence scores is:
less than a confidence threshold; or
greater than the confidence threshold;

in accordance with a determination that the percentage of the accrued translation score is less than the confidence threshold, decreasing the utterance gap; and
in accordance with a determination that the percentage of the accrued translation score is greater than the confidence threshold, decreasing the utterance gap.

16. The computer program product of claim 15 , further comprising computer instructions for increasing a number of translated utterances that are output in conjunction with decreasing the utterance gap.

17. The computer program product of claim 15 , further comprising computer instructions for increasing a rate at which translated utterances are output in conjunction with decreasing the utterance gap.

18. The computer program product of claim 15 , further comprising computer instructions for decreasing a number of translated utterances that are output in conjunction with increasing the utterance gap.

19. The computer program product of claim 15 , further comprising computer instructions for decreasing a rate at which translated utterances are output in conjunction with increasing the utterance gap.

20. The computer program product of claim 15 , wherein the confidence threshold corresponds to a percentage of accurate translations.

Assignees

• Dolby Laboratories Licensing Corp

Inventors

• Baker Jeffrey
• Garcia Sal Gregory
• Long Paul Anthony

Classifications

• G06F40/263 Primary

  Language identification · CPC title

• H04R3/005

  for combining the signals of two or more microphones (specially adapted for hearing aids H04R25/407) · CPC title

• G10L13/00

  Speech synthesis; Text to speech systems · CPC title

• G06F40/47 Primary

  Machine-assisted translation, e.g. using translation memory · CPC title

• G10L15/26

  Speech to text systems (G10L15/08 takes precedence) · CPC title