Method and system of configuring a speech recognition system

• US 20010047258A1
• Filed: 03/16/2001
• Published: 11/29/2001
• Est. Priority Date: 09/22/1998
• Status: Active Grant

• Current Assignee: Nokia Technologies Oy (Nokia Corporation)
• Original Assignee: Nokia Corporation
• Inventors: Rodrigo, Anthony
• Granted Patent: US 7,212,970 B2
• Time in Patent Office: Days
• US Class Current: 704/256
• CPC Class Codes: H04L 67/01 Protocols
• CPC Class Codes: H04L 67/04 specially adapted for terminals or networks with limited capabilities; specially adapted for terminal portability
• CPC Class Codes: H04L 67/75 Indicating network or usage conditions on the user display
• CPC Class Codes: H04L 69/329 in the application layer [OSI layer 7]
• CPC Class Codes: H04L 9/40 Network security protocols
• CPC Class Codes: H04W 4/18 Information format or content conversion, e.g. adaptation by the network of the transmitted or received information for the purpose of wireless delivery to users or terminals

Abstract

A speech control system and method is described, wherein a state definition information is loaded from a network application server. The state definition information defines possible states of the network application server and is used for determining a set of valid commands of the network application server, such that a validity of a text command obtained by converting an input speech command can be checked by comparing said text command with said determined set of valid commands. Thereby, a transmission of erroneous text commands to the network application server can be prevented so as to reduce total processing time and response delays.

Claims

1. Speech control system for a telecommunication network (4), comprising:

a) loading means for loading a state definition information from a network application server (5), wherein said state definition information defines possible states of the network application server (5);

b) determining means for determining a set of valid commands for said network application server (5) on the basis of said state definition information; and

c) checking means for checking a validity of a text command, obtained by converting an input speech command to be used for controlling said network application server (5), by comparing said text command with said determined set of valid commands.

2. System according to

claim 1

, wherein said loading means is arranged to load a grammar and/or vocabulary information which specifies a total set of valid commands supported by said network application server, wherein said determining means is arranged to determine said set of valid commands on the basis of said total set of valid commands and a state transition information included in said state definition information.

3. System according to

claim 1

, wherein said determining means is arranged to cause said loading means to load a state-dependent grammar file defining a set of valid commands for a specific state of the network application server (5), when said determining means determines a state change on the basis of a state transition information included in said state definition information.

4. System according to any one of the preceding claims, wherein said speech control system comprises a speech recognition means (6) for converting an input speech command received from a subscriber terminal (1) into said text command to be supplied to said network application server (5).

5. System according to any one of

claims 1

to

3

, wherein said telecommunication network (4) is a mobile network and said speech control system is implemented in a Wireless Telephony Application (WTA) server (7), and wherein said WTA server (7) is arranged to receive said text command from a network speech recognition means (6) for converting an input speech command received from a subscriber terminal (1) into said text command.

6. System according to any one of

claims 1

to

3

, wherein said speech control system comprises a subscriber terminal (1) having an input means for inputting a speech command, a transmitting means for transmitting said speech command to a speech recognition means (6) of said telecommunication network (4), and a receiving means for receiving said text command from the speech recognition means (6), wherein said transmitting means is arranged to transmit the received text command to said network application server (5).

7. System according to

claim 3

, wherein said state definition information includes a load instruction for loading the state-dependent grammar file.

8. System according to any of the preceding claims, wherein said state definition information is a data file.

9. System according to

claim 8

, wherein said data file is a WML file.

10. System according to

claim 8

, wherein said data file is a HTML file.

11. System according to

claim 9

or

10

, wherein said data file is sent on-line to said speech control system as a part of a standard information sent by said network application server (5).

12. System according to

claim 1

, wherein said state definition information is provided by said network application server (5) at a setup time.

13. System according to

claim 4

, wherein said state definition information is stored together with a command set information in a network server running on a hardware of said speech control system.

14. System according to

claim 4

or

6

, wherein said speech control system comprises a plurality of vendor-specific speech recognition means, and wherein corresponding parameters of said plurality of vendor-specific speech recognition means are defined in said state definition information.

15. Speech control method for a telecommunication network, comprising the steps of:

a) loading a state definition information from a network application, wherein said state definition information defines possible states of said network application;

b) determining a set of valid commands for said network application on the basis of said state definition information; and

c) checking a validity of a text command, obtained by converting a speech command to be used or controlling said network application, by comparing said text command with said determined set of valid commands.

16. Method according to

claim 15

, further comprising the steps of loading a grammar and/or vocabulary information which specifies a total set of valid commands for said network application, wherein said determining step is performed on the basis of said total set of valid commands and a state transition information included in said state definition information.

17. Method according to

claim 15

, further comprising the step of loading a state-dependent grammar file defining a set of valid commands for a specific state of said network application, when a state change has been determined on the basis of the state transition information included in said state definition information.