Method and apparatus for translating natural-language speech using multiple output phrases

• US 6,859,778 B1
• Filed: 03/16/2000
• Issued: 02/22/2005
• Est. Priority Date: 03/16/2000
• Status: Expired due to Term

• Current Assignee: International Business Machines Corporation, Oipenn Incorporated
• Original Assignee: International Business Machines Corporation, Oipenn Incorporated
• Inventors: Novak, Miroslav, Meisel, William Stuart, Whitaker, Ridley M., Picheny, Michael, Epstein, Mark Edward, Bakis, Raimo
• Primary Examiner(s): MCFADDEN, SUSAN IRIS
• Application Number:
  US09/526,985
• Time in Patent Office: 1,804 Days
• Field of Search: 704/2, 704/3, 704/4, 704/8, 704/9, 704/231, 704/235, 704/256, 704/266, 704/270, 704/277
• US Class Current: 704/277
• 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 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 17/26 Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices

Abstract

A multi-lingual translation system that provides multiple output sentences for a given word or phrase. Each output sentence for a given word or phrase reflects, for example, a different emotional emphasis, dialect, accents, loudness or rates of speech. A given output sentence could be selected automatically, or manually as desired, to create a desired effect. For example, the same output sentence for a given word or phrase can be recorded three times, to selectively reflect excitement, sadness or fear. The multi-lingual translation system includes a phrase-spotting mechanism, a translation mechanism, a speech output mechanism and optionally, a language understanding mechanism or an event measuring mechanism or both. The phrase-spotting mechanism identifies a spoken phrase from a restricted domain of phrases. The language understanding mechanism, if present, maps the identified phrase onto a small set of formal phrases. The translation mechanism maps the formal phrase onto a well-formed phrase in one or more target languages. The speech output mechanism produces high-quality output speech. The speech output may be time synchronized to the spoken phrase using the output of the event measuring mechanism.

Claims

1. A system for translating a source language into at least one of a plurality of target languages, comprising:

a phrase-spotting system for identifying a spoken phrase from a restricted domain of phrases;

a plurality of prerecorded translations in a plurality of target languages, wherein each of said prerecorded translations corresponds to one of said plurality of target languages; and

wherein each of said prerecorded translations corresponds to a different speech characteristic; and

a playback mechanism for reproducing said spoken phrase in said at least one of a plurality of target languages.

2. The system of claim 1, wherein each of said prerecorded translations corresponds to a varying degree of emphasis.

3. The system of claim 2, wherein said varying degree of emphasis corresponds to a variable loudness.

4. The system of claim 2, wherein said varying degree of emphasis corresponds to a variable pitch.

5. The system of claim 2, wherein said varying degree of emphasis corresponds to a variable manner of speaking.

6. The system of claim 1, wherein each of said prerecorded translations corresponds to a varying degree of emotion.

7. The system of claim 1, wherein each of said prerecorded translations corresponds to a different dialect.

8. The system of claim 1, wherein each of said prerecorded translations corresponds to a different loudness.

9. The system of claim 1, wherein each of said prerecorded translations corresponds to a different speed of speech.

10. The system of claim 1, wherein each of said prerecorded translations corresponds to a different accent.

11. The system of claim 1, further comprising a mechanism for manual selection of one of said prerecorded translations.

12. A method for translating a source language into at least one of a plurality of target languages, comprising:

providing a plurality of prerecorded translations in a plurality of target languages, wherein each of said prerecorded translations corresponds to one of said plurality of target languages; and

wherein each of said prerecorded translations corresponds to a different speech characteristic;

identifying a spoken phrase from a restricted domain of phrases; and

reproducing said spoken phrase in said at least one of a plurality of target languages.

13. The method of claim 12, wherein each of said prerecorded translations corresponds to a varying degree of emphasis.

14. The method of claim 13, wherein said varying degree of emphasis corresponds to a variable loudness.

15. The method of claim 13, wherein said varying degree of emphasis corresponds to a variable pitch.

16. The method of claim 13, wherein said varying degree of emphasis corresponds to a variable manner of speaking.

17. The method of claim 12, wherein each of said prerecorded translations corresponds to a varying degree of emotion.

18. The method of claim 12, wherein each of said prerecorded translations corresponds to a different dialect.

19. The method of claim 12, wherein each of said prerecorded translations corresponds to a different loudness.

20. The method of claim 12, wherein each of said prerecorded translations corresponds to a different speed of speech.

21. The method of claim 12, wherein each of said prerecorded translations corresponds to a different accent.

22. The method of claim 12, further comprising the step of receiving a manual selection of one of said prerecorded translations.

23. A system for translating a source language into at least one of a plurality of target languages, comprising:

a memory that stores computer-readable code; and

a processor operatively coupled to said memory, said processor configured to implement said computer-readable code, said computer-readable code configured to;

provide a plurality of prerecorded translations in a plurality of target languages, wherein each of said prerecorded translations corresponds to one of said plurality of target languages; and

wherein each of said prerecorded translations corresponds to a different speech characteristic;

identify a spoken phrase from a restricted domain of phrases; and

reproduce said spoken phrase in said at least one of a plurality of target languages.

24. An article of manufacture, comprising:

a computer readable medium having computer readable code means embodied thereon, said computer readable program code means comprising;

a step to provide a plurality of prerecorded translations in a plurality of target languages, wherein each of said prerecorded translations corresponds to one of said plurality of target languages; and

wherein each of said prerecorded translations corresponds to a different speech characteristic;

a step to identify a spoken phrase from a restricted domain of phrases; and

a step to reproduce said spoken phrase in said at least one of a plurality of target languages.

25. A method for translating a source language into at least one of a plurality of target languages, comprising:

providing a plurality of prerecorded translations, wherein each of said prerecorded translations corresponds to a different speech characteristic;

identifying a spoken phrase from a restricted domain of phrases; and

reproducing said spoken phrase in said at least one of a plurality of target languages.

26. The method of claim 25, wherein each of said prerecorded translations corresponds to a varying degree of emphasis.

27. The method of claim 26, wherein said varying degree of emphasis corresponds to a variable loudness.

28. The method of claim 26, wherein said varying degree of emphasis corresponds to a variable pitch.

29. The method of claim 26, wherein said varying degree of emphasis corresponds to a variable manner of speaking.

30. The method of claim 25, wherein each of said prerecorded translations corresponds to a varying degree of emotion.

31. The method of claim 25, wherein each of said prerecorded translations corresponds to a different dialect.

32. The method of claim 25, wherein each of said prerecorded translations corresponds to a different loudness.

33. The method of claim 25, wherein each of said prerecorded translations corresponds to a different speed of speech.

34. The method of claim 25, wherein each of said prerecorded translations corresponds to a different accent.

35. The method of claim 25, further comprising the step of receiving a manual selection of one of said prerecorded translations.