SPEECH RECOGNITION SYSTEM, SPEECH RECOGNITION RESULT OUTPUT METHOD, AND SPEECH RECOGNITION RESULT OUTPUT PROGRAM

• US 20100217598A1
• Filed: 02/22/2007
• Published: 08/26/2010
• Est. Priority Date: 02/23/2006
• Status: Active Grant

• Current Assignee: NEC Corporation
• Original Assignee: NEC Corporation
• Inventors: Adachi, Fumihiro
• Granted Patent: US 8,756,058 B2
• Time in Patent Office: Days
• US Class Current: 704/254
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/32 Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems
• CPC Class Codes: G10L 2015/027 Syllables being the recognition units

Abstract

A speech recognition system in which, even when the user makes an utterance including a word that satisfies a predetermined condition such as an unknown word, such a fact can be presented to the user, and the user can confirm the fact easily, is provided. The speech recognition system includes a word speech recognition section that converts input speech to a recognition result word sequence by using a predetermined word dictionary for recognition, a syllable recognition section that converts input speech to a recognition result syllable sequence, a segment determination section that determines a segment that corresponds to a predetermined condition which is a ground for estimating that a word in the converted recognition result word sequence is an unknown word, and an output section that obtains a partial syllable sequence from the recognition result syllable sequence corresponding to the determined segment, and outputs one or more word entries, which are in the vicinity of a position at which the partial syllable sequence is arranged in the word dictionary for recognition in which words are arranged in the order defined for word entries, together with the recognition result word sequence.

Claims

1. A speech recognition system, comprising:

a word speech recognition section that converts input speech to a recognition result word sequence by using a predetermined word dictionary for recognition;

a syllable recognition section that converts the input speech to a recognition result syllable sequence;

a segment determination section that determines a segment that corresponds to a predetermined condition which is a ground for estimating an unknown word in the converted recognition result word sequence; and

an output section that obtains a partial syllable sequence from the recognition result syllable sequence corresponding to the determined segment, and outputs one or more word entries which are in the vicinity of a position at which the partial syllable sequence is arranged in the word dictionary for recognition, in which words are arranged in the order defined for word entries, together with the recognition result word sequence.

2. The speech recognition system according to claim 1, wherein

the syllable recognition section uses a predetermined syllable dictionary for recognition to convert the input speech to the recognition result syllable sequence.

3. The speech recognition system according to claim 1, wherein

the output section outputs the recognition result word sequence after replacing the recognition result word sequence with the partial syllable sequence with respect to the segment determined by the segment determination section.

4. The speech recognition system according to claim 1, wherein

the output section outputs the segment determined by the segment determination section after highlighting the segment.

5. The speech recognition system according to claim 1, wherein

the defined order is the Japanese syllabary order.

6. The speech recognition system according to claim 1, wherein

the output section includes a function of changing the word entries of the word dictionary for recognition output in accordance with an instruction of the user.

7. The speech recognition system according to claim 1, wherein

the output section operates when the user selects a word entry in the word dictionary for recognition, and includes a function of replacing a character sequence displayed in the segment determined by the segment determination section with a character sequence for display of the selected word entry.

8. The speech recognition system according to claim 1, wherein

the output section includes a function of changing a range of the segment determined by the segment determination section by an instruction of the user.

9. The speech recognition system according to claim 8, wherein

the output section includes a function of changing an output content in accordance with a new segment obtained by changing the range in accordance with the instruction of the user.

10. A speech recognition result output method, comprising:

a word speech recognition step of converting input speech to a recognition result word sequence by using a predetermined word dictionary for recognition;

a syllable recognition step of converting the input speech to a recognition result syllable sequence;

a segment determination step of determining a segment that corresponds to a predetermined condition which is a ground for estimating an unknown word in the converted recognition result word sequence; and

an output step of obtaining a partial syllable sequence from the recognition result syllable sequence corresponding to the determined segment, and outputting one or more word entries which are in the vicinity of a position at which the partial syllable sequence is arranged in the word dictionary for recognition, in which words are arranged in the order defined for word entries, together with the recognition result word sequence.

11. The speech recognition result output method according to claim 10, wherein

in the speech recognition step, a predetermined syllable dictionary for recognition is used to convert the input speech to the recognition result syllable sequence.

12. The speech recognition result output method according to claim 10, wherein

in the output step, the recognition result word sequence is output after the recognition result word sequence is replaced with the partial syllable sequence with respect to the segment determined by the segment determination section.

13. The speech recognition result output method according to claim 10, wherein

in the output step, the segment determined by the segment determination section is output after highlighting the segment.

14. The speech recognition result output method according to claim 10, wherein

the defined order is the Japanese syllabary order.

15. The speech recognition result output method according to claim 10, wherein

in the output step, the word entries of the word dictionary for recognition output are changed in accordance with an instruction of the user.

16. The speech recognition result output method according to claim 10, wherein

in the output step, when the user selects a word entry in the word dictionary for recognition, and a character sequence displayed in the segment determined by the segment determination section is replaced with a character sequence for display of the selected word entry.

17. The speech recognition result output method according to claim 10, wherein

in the output step, a range of the segment determined by the segment determination section is changed in accordance with the instruction of the user.

18. The speech recognition result output method according to claim 17, wherein

in the output step, an output content is changed in accordance with a new segment obtained by changing the range in accordance with the instruction of the user.

19. A speech recognition result output program allowing a computer to execute:

word speech recognition processing for converting input speech to a recognition result word sequence by using a predetermined word dictionary for recognition;

syllable recognition processing for converting the input speech to a recognition result syllable sequence;

segment determination processing for determining a segment that corresponds to a predetermined condition which is a ground for estimating an unknown word in the converted recognition result word sequence; and

output processing for obtaining a partial syllable sequence from the recognition result syllable sequence corresponding to the determined segment, and outputting one or more word entries which are in the vicinity of a position at which the partial syllable sequence is arranged in the word dictionary for recognition, in which words are arranged in the order defined for word entries, together with the recognition result word sequence.

20. The speech recognition result output program according to claim 19, wherein

in the syllable recognition processing, a predetermined syllable dictionary for recognition is used to convert the input speech to the recognition result syllable sequence.

21. The speech recognition result output program according to claim 19, wherein

in the output processing, the recognition result word sequence is output after the recognition result word sequence is replaced with the partial syllable sequence with respect to the segment determined by the segment determination section.

22. The speech recognition result output program according to claim 19, wherein

in the output processing, the segment determined by the segment determination section is output after highlighting the segment.

23. The speech recognition result output program according to claim 19, wherein

the defined order is the Japanese syllabary order.

24. The speech recognition result output program according to claim 19, wherein

in the output processing, the word entries of the word dictionary for recognition output is changed in accordance with an instruction of the user.

25. The speech recognition result output program according to claim 19, wherein

in the output processing, when the user selects a word entry in the word dictionary for recognition, a character sequence displayed in the segment determined by the segment determination section is replaced with a character sequence for display of the selected word entry.

26. The speech recognition result output program according to claim 19, wherein

in the output processing, a range of the segment determined by the segment determination section is changed in accordance with the instruction of the user.

27. The speech recognition result output program according to claim 26, wherein

an output content is changed in accordance with a new segment obtained by changing the range in accordance with the instruction of the user the output processing.