Speech recognition system, speech recognition server, speech recognition client, their control method, and computer readable memory

• US 20020065652A1
• Filed: 11/27/2001
• Published: 05/30/2002
• Est. Priority Date: 11/27/2000
• Status: Active Grant

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Kushida, Akihiro, Kosaka, Tetsuo
• Granted Patent: US 7,099,824 B2
• Time in Patent Office: Days
• US Class Current: 704/231
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications

Abstract

A user dictionary, which is formed by storing pronunciations and notations of target recognition words designated by the user in correspondence with each other, input speech recognition data, and dictionary management data used to determine the recognition field of a recognition dictionary used in recognition of the speech recognition data are sent to a server via a communication module. In the server, a dictionary management unit looks up an identifier table to determine a recognition dictionary corresponding to the dictionary management information received from a client from a plurality of kinds of recognition dictionaries. A speech recognition module recognizes the speech recognition data using at least the determined recognition dictionary. The recognition result is sent to the client via a communication module.

Claims

1. A client-server speech recognition system for recognizing speech input at a client by a server,

the client comprising:

speech input means for inputting speech;

user dictionary holding means for holding a user dictionary formed by registering target recognition words designated by a user; and

transmission means for transmitting speech data input by said speech input means, dictionary management information used to determine a recognition field of a recognition dictionary used to recognize the speech data, and the user dictionary to the server, and

the server comprising;

recognition dictionary holding means for holding a plurality of kinds of recognition dictionaries prepared for respective recognition fields;

determination means for determining one or more recognition dictionary corresponding to the dictionary management information received from the client from the plurality of kinds of recognition dictionaries; and

recognition means for recognizing the speech data using at least the recognition dictionary determined by said determination means.

2. The system according to claim 1, wherein said recognition means recognizes the speech data using the recognition dictionary determined by said determination means, and the user dictionary received from the client.

3. The system according to claim 1,

wherein said speech input means comprises display means for displaying an input form as a target speech input, and

the dictionary management information is an input form identifier that indicates a type of input form.

4. The system according to claim 1, wherein the dictionary management information contains information indicating if the user dictionary is used in recognition of the speech data.

5. The system according to claim 1, wherein the user dictionary is formed by storing pronunciations and notations of the target recognition words in correspondence with each other.

6. The system according to claim 3, wherein the user dictionary is formed by also storing at least one input form identifier and the target recognition words in correspondence with each other.

7. The system according to claim 1, wherein the user dictionary is formed by also storing at least one of recognition dictionary identifiers indicating recognition fields of the plurality of kinds of recognition dictionaries, and the target recognition words.

8. The system according to claim 1, wherein the speech data is data obtained by encoding that speech data.

30. The method according to claim 1, wherein the speech data is data obtained by encoding that speech data.

9. A method of controlling a client-server speech recognition system for recognizing speech input at a client by a server, comprising:

a speech input step of inputting speech;

a user dictionary holding step of holding, in the client, a user dictionary formed by registering target recognition words designated by a user; and

a transmission step of transmitting speech data input in the speech input step, dictionary management information used to determine a recognition field of a recognition dictionary used to recognize the speech data, and the user dictionary to the server;

a recognition dictionary holding step of holding, in the server, a plurality of kinds of recognition dictionaries prepared for respective recognition fields;

a determination step of determining one or more recognition dictionary corresponding to the dictionary management information received from the client from the plurality of kinds of recognition dictionaries; and

a recognition step of recognizing the speech data using at least the recognition dictionary determined in the determination step.

10. The method according to claim 9, wherein the recognition step includes a step of recognizing the speech data using the recognition dictionary determined in the determination step, and the user dictionary received from the client.

11. The method according to claim 9,

wherein the speech input step comprises a display step of displaying an input form as a target speech input, and

the dictionary management information is an input form identifier that indicates a type of input form.

12. The method according to claim 9, wherein the dictionary management information contains information indicating if the user dictionary is used in recognition of the speech data.

13. The method according to claim 9, wherein the user dictionary is formed by storing pronunciations and notations of the target recognition words in correspondence with each other.

14. The method according to claim 11, wherein the user dictionary is formed by also storing at least one input form identifier and the target recognition words in correspondence with each other.

15. The method according to claim 9, wherein the user dictionary is formed by also storing at least one of recognition dictionary identifiers indicating recognition fields of the plurality of kinds of recognition dictionaries, and the target recognition words.

16. The method according to claim 9, wherein the speech data is data obtained by encoding that speech data.

19. The server according to claim 18, wherein said recognition means recognizes the speech data using the recognition dictionary determined by said determination means, and the user dictionary received from the client.

20. The server according to claim 18, wherein the speech data is data obtained by encoding that speech data.

17. A computer readable memory that stores a program code of control of a client-server speech recognition system for recognizing speech input at a client by a server, comprising:

a program code of a speech input step of inputting speech;

a program code of a user dictionary holding step of holding, in the client, a user dictionary formed by registering target recognition words designated by a user; and

a program code of a transmission step of transmitting speech data input in the speech input step, dictionary management information used to determine a recognition field of a recognition dictionary used to recognize the speech data, and the user dictionary to the server;

a program code of a recognition dictionary holding step of holding, in the server, a plurality of kinds of recognition dictionaries prepared for respective recognition fields;

a program code of a determination step of determining one or more recognition dictionary corresponding to the dictionary management information received from the client from the plurality of kinds of recognition dictionaries; and

a program code of a recognition step of recognizing the speech data using at least the recognition dictionary determined in the determination step.

18. A speech recognition server for recognizing speech input at a client, and sending a recognition result to the client, comprising:

reception means for receiving, from the client, speech data, dictionary management information used to determine a recognition field of a recognition dictionary used to recognize the speech data, and a user dictionary formed by registering target recognition words designated by a user;

recognition dictionary holding means for holding a plurality of kinds of recognition dictionaries prepared for respective recognition fields;

determination means for determining one or more recognition dictionary corresponding to the dictionary management information received from the client from the plurality of kinds of recognition dictionaries; and

recognition means for recognizing the speech data using at least the recognition dictionary determined by said determination means.

21. A speech recognition client for sending input speech to be recognized to a server, and receiving a recognition result of that speech, comprising:

speech input means for inputting speech;

user dictionary holding means for holding a user dictionary formed by registering target recognition words designated by a user; and

transmission means for transmitting speech data input by said speech input means, dictionary management information used to determine a recognition field of a recognition dictionary used to recognize the speech data, and the user dictionary to the server.

22. The client according to claim 21,

wherein said speech input means comprises display means for displaying an input form as a target speech input, and

the dictionary management information is an input form identifier that indicates a type of input form.

23. The client according to claim 21, wherein the dictionary management information contains information indicating if the user dictionary is used in recognition of the speech data.

24. The client according to claim 21, wherein the user dictionary is formed by storing pronunciations and notations of the target recognition words in correspondence with each other.

25. The client according to claim 22, wherein the user dictionary is formed by also storing at least one input form identifier and the target recognition words in correspondence with each other.

26. The client according to claim 21, wherein the user dictionary is formed by also storing at least one of recognition dictionary identifiers indicating recognition fields of the plurality of kinds of recognition dictionaries, and the target recognition words.

27. The client according to claim 21, wherein the speech data is data obtained by encoding that speech data.

29. The method according to claim 28, wherein the recognition step includes a step of recognizing the speech data using the recognition dictionary determined in the determination step, and the user dictionary received from the client.

28. A method of controlling a speech recognition server for recognizing speech input at a client, and sending a recognition result to the client, comprising:

a reception step of receiving, from the client, speech data, dictionary management information used to determine a recognition field of a recognition dictionary used to recognize the speech data, and a user dictionary formed by registering target recognition words designated by a user;

a recognition dictionary holding step of holding a plurality of kinds of recognition dictionaries prepared for respective recognition fields;

a determination step of determining one or more recognition dictionary corresponding to the dictionary management information received from the client from the plurality of kinds of recognition dictionaries; and

a recognition step of recognizing the speech data using at least the recognition dictionary determined in the determination step.

31. A method of controlling a speech recognition client for sending input speech to be recognized to a server, and receiving a recognition result of that speech, comprising:

a speech input step of inputting speech;

a user dictionary holding step of holding a user dictionary formed by registering target recognition words designated by a user; and

a transmission step of transmitting speech data input in the speech input step, dictionary management information used to determine a recognition field of a recognition dictionary used to recognize the speech data, and the user dictionary to the server.

32. The method according to claim 31,

wherein the speech input step comprises a display step of displaying an input form as a target speech input, and

the dictionary management information is an input form identifier that indicates a type of input form.

33. The method according to claim 31, wherein the dictionary management information contains information indicating if the user dictionary is used in recognition of the speech data.

34. The method according to claim 31, wherein the user dictionary is formed by storing pronunciations and notations of the target recognition words in correspondence with each other.

35. The method according to claim 32, wherein the user dictionary is formed by also storing at least one input form identifier and the target recognition words in correspondence with each other.

36. The method according to claim 31, wherein the user dictionary is formed by also storing at least one of recognition dictionary identifiers indicating recognition fields of the plurality of kinds of recognition dictionaries, and the target recognition words.

37. The method according to claim 31, wherein the speech data is data obtained by encoding that speech data.

38. A computer readable memory that stores a program code of control of a speech recognition server for recognizing speech input at a client, and sending a recognition result to the client, comprising:

a program code of a reception step of receiving, from the client, speech data, dictionary management information used to determine a recognition field of a recognition dictionary used to recognize the speech data, and a user dictionary formed by registering target recognition words designated by a user;

a program code of a recognition dictionary holding step of holding a plurality of kinds of recognition dictionaries prepared for respective recognition fields;

a program code of a determination step of determining one or more recognition dictionary corresponding to the dictionary management information received from the client from the plurality of kinds of recognition dictionaries; and

a program code of a recognition step of recognizing the speech data using at least the recognition dictionary determined in the determination step.

39. A computer readable memory that stores a program code of control of a speech recognition client for sending input speech to be recognized to a server, and receiving a recognition result of that speech, comprising:

a program code of a speech input step of inputting speech;

a program code of a user dictionary holding step of holding a user dictionary formed by registering target recognition words designated by a user; and

a program code of a transmission step of transmitting speech data input in the speech input step, dictionary management information used to determine a recognition field of a recognition dictionary used to recognize the speech data, and the user dictionary to the server.

40. A client-server speech recognition system for recognizing speech input at a client by a server,

the client comprising:

a speech input unit inputs speech;

a user dictionary holding a user dictionary formed by registering target recognition words designated by a user; and

a transmitter transmits speech data input by said speech input means, dictionary management information used to determine a recognition field of a recognition dictionary used to recognize the speech data, and the user dictionary to the server, and

the server comprising;

a recognition dictionary holding a plurality of kinds of recognition dictionaries prepared for respective recognition fields;

a determination unit determines one or more recognition dictionary corresponding to the dictionary management information received from the client from the plurality of kinds of recognition dictionaries; and

a recognition unit recognizes the speech data using at least the recognition dictionary determined by said determination means.

41. A speech recognition server for recognizing speech input at a client, and sending a recognition result to the client, comprising:

a receiver receives, from the client, speech data, dictionary management information used to determine a recognition field of a recognition dictionary used to recognize the speech data, and a user dictionary formed by registering target recognition words designated by a user;

a recognition dictionary holding a plurality of kinds of recognition dictionaries prepared for respective recognition fields;

a determination unit determines one or more recognition dictionary corresponding to the dictionary management information received from the client from the plurality of kinds of recognition dictionaries; and

a recognition unit recognizes the speech data using at least the recognition dictionary determined by said determination means.

42. A speech recognition client for sending input speech to be recognized to a server, and receiving a recognition result of that speech, comprising:

a speech input unit inputs speech;

a user dictionary holding a user dictionary formed by registering target recognition words designated by a user; and

a transmitter transmits speech data input by said speech input means, dictionary management information used to determine a recognition field of a recognition dictionary used to recognize the speech data, and the user dictionary to the server.