VOICE RECOGNITION SYSTEM, VOICE RECOGNITION METHOD, AND VOICE RECOGNITION PROCESSING PROGRAM

• US 20100324899A1
• Filed: 03/14/2008
• Published: 12/23/2010
• Est. Priority Date: 03/14/2007
• Status: Active Grant

• Current Assignee: NEC Corporation
• Original Assignee: NEC Corporation
• Inventors: Yamabana, Kiyoshi
• Granted Patent: US 8,676,582 B2
• Time in Patent Office: Days
• US Class Current: 704/251
• CPC Class Codes: G10L 15/07 to the speaker

Abstract

A speech recognition system for rapidly performing recognition processing while maintaining quality of speech recognition in a speech recognition device, are provided. A speech recognition system includes a speech input device which inputs speech and displays a recognition result, and a speech recognition device which receives the speech from the speech input device, performs recognition processing, and sends back the speech to the speech input device. The speech input device includes a user dictionary section which stores words used for recognizing the input speech, and a reduced user dictionary creation unit which extracts words corresponding to the input speech from the user dictionary and creates a reduced user dictionary. The speech recognition device has a speech recognition unit which inputs the input speech and the reduced user dictionary from the speech input/output device and recognizes the input speech based on the reduced user dictionary and a system dictionary provided beforehand.

Claims

1. A speech recognition system for recognizing an input speech converted into an electric signal, comprising:

a user dictionary section which stores a user dictionary to be used for speech recognition;

a reduced user dictionary creation unit which creates a reduced user dictionary by eliminating a word determined as unnecessary for recognizing the input speech from the user dictionary; and

a speech recognition unit which recognizes the input speech based on the system dictionary and the reduced user dictionary.

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

the user dictionary section and the reduced user dictionary creation unit are provided to a client terminal device, and

the speech recognition unit is provided to a server capable of communicating with the client terminal device.

3. The speech recognition system, according to claim 2, wherein the client terminal transmits the input speech and the reduced user dictionary to the speech recognition unit.

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

the reduced user dictionary is a dictionary in which a word having a possibility of being included in the input speech is selected from words in the user dictionary.

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

the reduced user dictionary creation unit compares a word in the user dictionary and the input speech, calculates a likelihood that the word appears in the input speech, and based on a calculation result, selects a word having a high likelihood to thereby create the reduced user dictionary.

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

the reduced user dictionary creation unit creates the reduced user dictionary by means of a word spotting method using the user dictionary.

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

the reduced user dictionary creation unit includes:

a comparing section which compares the input speech and a word in the user dictionary and compiles a likelihood of each word appearing in the input speech,

a word temporarily storing section which temporarily stores a set of each word and a corresponding likelihood complied, and

a word selection section which selects one or a plurality of words having high usage from the word temporarily storing section to thereby create the reduced user dictionary.

8. A speech recognition method for recognizing an input speech converted into an electric signal, comprising:

creating a reduced user dictionary by eliminating a word determined as unnecessary for recognizing the input speech from a user dictionary; and

adding the reduced user dictionary to a system dictionary previously provided, and recognizing the input speech based on the system dictionary and the reduced user dictionary.

9. The speech recognition method, according to claim 8, further comprising:

creating the reduced user dictionary from the user dictionary in a client; and

transmitting data of the input speech and the reduced user dictionary to a server capable of communicating with a terminal of the client, and recognizing the input speech in the server using the system dictionary and the reduced user dictionary.

10. The speech recognition method, according to claim 8, further comprising:

comparing words included in the user dictionary and the input speech, calculating a likelihood that each of the words appears in the input speech, selecting a word having a high likelihood based on a calculation result, and thereby creating the reduced user dictionary.

11. The speech recognition method, according to claim 8, wherein the reduced user dictionary is created from the user dictionary by word spotting.

12. The speech recognition method, according to claim 8, further comprising:

comparing the input speech and words in the user dictionary, calculating a likelihood that each of the word appears in the input speech, temporarily storing a set of a calculated likelihood and a corresponding word, selecting one or more words having high likelihoods from temporarily stored words and creating a reduced user dictionary, and editing selected words to be in a form of a dictionary and creating the reduced user dictionary.

13. A computer readable recording medium storing a speech recognition program for recognizing an input speech converted into an electric signal by a client terminal device and a server which are connected in a communicable manner, the program,

causing a computer of the client terminal device to perform a function of creating a reduced user dictionary by eliminating a word determined as unnecessary for recognizing the input speech from a user dictionary, and

causing a computer of the server to perform a function of adding the reduced user dictionary to a system dictionary provided beforehand, and recognizing the input speech based on the reduced user dictionary and the system dictionary.

14. The computer readable recording medium storing the speech recognition program, according to claim 13, further causing the computer of the client terminal device to perform a function of outputting a command to transmit the input speech and the reduced user dictionary to the server.

15. The computer readable recording medium storing the speech recognition program, according to claim 13, further causing the computer of the client terminal device to perform a function of comparing words included in the user dictionary and the input speech and calculating a likelihood that each of the words appears in the input speech, and selecting a word having a high likelihood based on a calculation result and creating the reduced user dictionary.

16. The computer readable recording medium storing the speech recognition program, according to claim 13, further causing the computer of the client terminal device to perform a function of creating the reduced user dictionary from the user dictionary by word spotting.

17. The computer readable recording medium storing the speech recognition program, according to claim 13, further causing the computer of the client terminal device to perform a function of comparing the input speech and words in the user dictionary and calculating a likelihood that each of the words appears in the input speech, temporarily storing a set of a calculated likelihood and a corresponding word, selecting one or a plurality of words having high likelihoods from the words which are temporarily stored and creating a reduced user dictionary, and editing selected words to be in a dictionary form and creating the reduced user dictionary.

18. A speech recognition system for recognizing an input speech converted into an electric signal, comprising:

user dictionary means for storing a user dictionary to be used for speech recognition;

reduced user dictionary creation means for creating a reduced user dictionary by eliminating a word determined as unnecessary for recognizing the input speech from the user dictionary; and

speech recognition means for recognizing the input speech based on the system dictionary and the reduced user dictionary.