Speech complementing apparatus, method and recording medium

• US 20020007275A1
• Filed: 12/28/2000
• Published: 01/17/2002
• Est. Priority Date: 07/13/2000
• Status: Active Grant

• Current Assignee: National Institute of Advanced Industrial Science and Technology (Government of Japan)
• Original Assignee: National Institute of Advanced Industrial Science and Technology (Government of Japan)
• Inventors: Itou, Katunobu, Goto, Masataka
• Granted Patent: US 6,876,967 B2
• Time in Patent Office: Days
• US Class Current: 704/251
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding

Abstract

An apparatus that recognizes inputted speech and complements the result of the speech recognition just before a filled pause when the filled pause is detected.

Claims

1. A speech complementing apparatus comprising:

speech input means for inputting a speech;

speech recognition means for recognizing the inputted speech;

detecting means for detecting a word fragment in the result of recognizing by said speech recognition means, the fragment giving information about which part to be complemented; and

complementing means for complementing the result of recognizing by said speech recognition means based on the detected word fragment.

2. The speech complementing apparatus as claimed in claim 1, wherein in said detecting means, the word fragment to be complemented is specified by detecting the period of the filled pause in the inputted speech from said speech input means.

3. The speech complementing apparatus as claimed in claim 2, wherein said word fragment is the result of recognizing before said period of the filled pause.

4. The speech complementing apparatus as claimed in claim 1, wherein in said detecting means, the word fragment to be complemented is specified by detecting a predefined key-word string in the result of recognizing by said speech recognition means.

5. The speech complementing apparatus as claimed in claim 4, wherein said word fragment is the result of recognizing after said predefined key-word string.

6. The speech complementing apparatus as claimed in claim 1, further comprising selecting means for selecting a complementary candidate when said word fragment is complemented and a plurality of complementary candidates are existing.

7. A speech complementing method comprising:

a speech input step for inputting a speech;

a speech recognition step for recognizing the inputted speech;

a detecting step for detecting a word fragment in the result of recognizing by said speech recognition step, the fragment giving information about which part to be complemented; and

a complementing step for complementing the result of recognizing by said speech recognition step based on the detected word fragment.

8. The speech complementing method as claimed in claim 7, wherein in said detecting step, the word fragment to be complemented is specified by detecting the period of the filled pause in the inputted speech in said speech input step.

9. The speech complementing method as claimed in claim 8, wherein said word fragment is the result of recognizing before said period of the filled pause.

10. The speech complementing method as claimed in claim 7, wherein in said detecting step, the word fragment to be complemented is specified by detecting a predefined key-word string in the result of recognizing in said speech recognition step.

11. The speech complementing method as claimed in claim 10, wherein said word fragment is the result of recognizing after said predefined key-word string.

12. The speech complementing method as claimed in claim 7, further comprising a selecting step for selecting a complementary candidate when said word fragment is complemented and a plurality of complementary candidates are existing.

13. A recording medium which stores a program executed in a complementing apparatus, said program comprising:

a speech input step for inputting a speech;

a speech recognition step for recognizing the inputted speech;

a detecting step for detecting a word fragment in the result of recognizing by said speech recognition step, the fragment giving information about which part to be complemented; and

a complementing step for complementing the result of recognizing by said speech recognition step based on the detected word fragment.

14. The recording medium as claimed in claim 13, wherein in said detecting step, the word fragment to be complemented is specified by detecting the period of the filled pause in the inputted speech in said speech input step.

15. The recording medium as claimed in claim 14, wherein said word fragment is the result of recognizing before said period of the filled pause.

16. The recording medium as claimed in claim 13, wherein in said detecting step, the word fragment to be complemented is specified by detecting a predefined key-word string in the result of recognizing in said speech recognition step.

17. The recording medium as claimed in claim 16, wherein said word fragment is the result of recognizing after said predefined key-word string.

18. The recording medium as claimed in claim 13, said program further comprises a selecting step for selecting a complementary candidate when said word fragment is complemented and a plurality of complementary candidates are existing.