Speech recognition system, speech recognition method and storage medium

• US 20060212291A1
• Filed: 06/24/2005
• Published: 09/21/2006
• Est. Priority Date: 03/16/2005
• Status: Active Grant

• Current Assignee: Fujitsu Limited
• Original Assignee: Fujitsu Limited
• Inventors: Matsuo, Naoshi
• Granted Patent: US 8,010,359 B2
• Time in Patent Office: Days
• US Class Current: 704/231
• CPC Class Codes: G10L 2015/228 of application context
• CPC Class Codes: G10L 21/028 using properties of sound source

Abstract

Provided are a speech recognition system, a method and a storage medium capable of, even in a case where plural speakers input superimposed speeches, recognizing a speech of an individual each speaker and making a single application program sharable among the speakers in execution. In a speech recognition system receiving speeches of plural speakers to execute a predetermined application program, the received speeches are separated according to the respective speakers if necessary, the received speeches of individual speakers are speech-recognized, results of speech recognition are matched with data items necessary for executing the application program, one of results of recognition of plural speeches which are found as a result of the matching to be overlapping is selected, and the results of recognition of plural speeches which are found as a result of the matching not to be overlapping are linked to the selected result of speech recognition.

Claims

1. A speech recognition system wherein speeches of plural speakers are received and a predetermined application program is executed based on results of speech recognition of the received speeches, comprising:

speech recognition means for speech-recognizing a speech received from each speaker;

matching means for matching the results of speech recognition with data items necessary for executing the application program;

selecting means for selecting one of the results of recognition of plural speeches which are found as a result of the matching to be overlapping in a data item necessary for executing the application program as a result of the matching; and

linkage means for linking the selected result of speech recognition the results of recognition of the plural speeches which are found as a result of the matching not to be overlapping in data items necessary for executing the application program.

2. The speech recognition system of claim 1, wherein the speech recognition means calculates an evaluation value representing a degree of coincidence with a speech pattern stored in advance and outputs a character sequence having a largest calculated evaluation value as a result of recognition, and

the selecting means selects a result of speech recognition having the largest evaluation value among overlapping results of speech recognition of plural speeches.

3. The speech recognition system of claim 1, wherein the selecting means preferentially selects a result of speech recognition of a speech uttered later.

4. The speech recognition system of claim 2, wherein the selecting means preferentially selects a result of speech recognition of a speech uttered later.

5. The speech recognition system of claim 1, wherein a priority level showing a precedence in selection of a result of speech recognition for each speaker is stored or a priority level is specified in order of utterance and

the selecting means preferentially selects a result of speech recognition of a speech uttered by a speaker with a highest priority level stored in advance.

6. The speech recognition system of claim 1, comprising speech separation means for separating received speeches according to the respective speakers.

7. A speech recognition system receiving speeches of plural speakers to execute a predetermined application program based on results of recognition of the received speeches, comprising a processor capable of performing the operations of:

speech-recognizing received speeches of individual speakers;

matching results of speech recognition with data items necessary for executing the application program;

selecting one of results of recognition of plural speeches which are found as a result of the matching to be overlapping in a data item necessary for execution of the application program; and

linking the selected result of speech recognition the results of recognition of plural speeches which are found as a result of the matching not to be overlapping in data items necessary for executing the application program.

8. The speech recognition system of claim 7, comprising a processor further capable of performing the operations of:

calculating an evaluation value representing a degree of coincidence with a speech pattern stored in advance;

outputting a character sequence having a largest calculated evaluation value, and

selecting a result of speech recognition having the largest evaluation value among overlapping results of recognition of plural speeches.

9. The speech recognition system of claim 7, comprising a processor further capable of performing the operation of:

preferentially selecting a result of recognition of a speech uttered later.

10. The speech recognition system of claim 8, comprising a processor further capable of performing the operation of:

preferentially selecting a result of recognition of a speech uttered later.

11. The speech recognition system of claim 7, comprising a processor further capable of performing the operations of:

storing a priority level indicating a precedence in selection of a result of speech recognition for each speaker or specifying a priority level in order of utterance, and

preferentially selecting a result of speech recognition of a speech uttered by a speaker with a higher priority level.

12. The speech recognition system of claim 7, comprising a processor further capable of performing the operations of:

separating received speeches according to the respective speakers.

13. A speech recognition method, comprising the following steps of:

speech-recognizing received speeches of individual speakers, matching results of recognition of speeches with plural data items necessary for executing the application program;

selecting one of results of recognition of plural speeches which are found as a result of the matching to be overlapping in a data item necessary for execution of the application program; and

linking a selected result of speech recognition the results of recognition of plural speeches which are found as a result of the matching not to be overlapping in data items necessary for executing the application program.

14. The speech recognition method of claim 13, comprising the further steps of:

in a case where results of recognition of plural speeches overlapping in data items necessary for executing the application program are to be selected,

calculating an evaluation value representing a degree of coincidence with a speech pattern stored in advance;

outputting a character sequence having a largest calculated evaluation value, and

selecting a result of speech recognition having the largest evaluation value among overlapping results of recognition of plural speeches.

15. The speech recognition method of claim 13, comprising the further steps of:

storing a priority level indicating a precedence in selection of a result of speech recognition for each speaker or specifying a priority level in order of utterance, and

preferentially selecting a result of speech recognition of a speech uttered by a speaker with a higher priority level.

16. The speech recognition method of claim 13, comprising the further steps of:

separating received speeches according to the respective speakers.

17. A storage medium, storing a computer program for a computer which receives speeches of plural speakers and executes a predetermined application program based on results of recognition of the received speeches, wherein

the computer program stored in the storage medium comprises the steps of:

causing the computer to speech-recognize received speeches of individual speakers;

causing the computer to match results of recognition of speeches with data items necessary for executing the application program;

causing the computer to select one of results of recognition of plural speeches which are found as a result of the matching to be overlapping in a data item necessary for executing the application program; and

causing the computer to link the selected result of speech recognition the results of recognition of plural speeches which are found as a result of the matching not to be overlapping in data items necessary for executing the application program.

18. The storage medium of claim 17, storing the computer program comprising the further steps of:

causing the computer to calculate an evaluation value representing a degree of coincidence with a speech pattern stored in advance;

causing the computer to output a character sequence having a largest calculated evaluation value; and

causing the computer to select a result of speech recognition having the largest evaluation value among overlapping results of recognition of plural speeches.

19. The storage medium of claim 17, storing the computer program comprising the further step of:

causing the computer to separate received speeches according to the respective speakers.

20. The storage medium of claim 18, storing the computer program comprising the further step of:

causing the computer to separate received speeches according to the respective speakers.