System and method for adding speech recognition capabilities to java

• US 6,456,974 B1
• Filed: 10/03/1997
• Issued: 09/24/2002
• Est. Priority Date: 01/06/1997
• Status: Active Grant

• Current Assignee: Texas Instruments, Inc.
• Original Assignee: Texas Instruments, Inc.
• Inventors: Hemphill, Charles T., Baker, C. Scott
• Primary Examiner(s): Chawan, Vijay B.
• Application Number:
  US08/943,711
• Time in Patent Office: 1,817 Days
• Field of Search: 704/257, 704/243, 704/200, 704/275, 704/270, 704/231, 704/270.1, 395/200.33, 395/706, 395/600, 395/333, 395/708, 707/10, 707/513
• US Class Current: 704/270.1
• CPC Class Codes: G06F 3/16 Sound input; Sound output speech processing G10L
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications

Abstract

In a system (10) for adding speech recognition capabilities to Java, there is provided a speech recognition server (18) coupled to a Java application (24) through an application program interface (20). The Java application (24) dynamically specifies a grammar (56) to the application program interface (20), which communicates the grammar (56) to the speech recognition server (18). The speech recognition server (18) receives the grammar (56) and a speech input (66). Upon receiving the speech input (66), the speech recognition server (18) performs speech recognition and generates a result (58) based on the grammar (56). The application program interface (20) communicates the result (58) to the Java application (24), which performs an action based on the result (58) received.

Claims

1. A system for facilitating a speech interface to Java comprising:

a speech recognition server operable to receive a grammar and a speech input, the speech recognition server further operable to perform speech recognition in response to the speech input and to generate a result based on the grammar;

at least one Java application operable to dynamically specify the grammar, to receive the result and to perform an action based on the result; and

an application program interface operable to receive the grammar, to communicate the grammar to the speech recognition server and, in response to the speech recognition, to receive the result from the speech recognition server and to communicate the result to the Java application.

2. The system of claim 1, wherein the speech recognition server comprises:

a speech engine operable to perform speech recognition; and

a grammar data structure operable to receive and store the grammar.

3. The system of claim 1, wherein the speech recognition server comprises:

a speech engine operable to perform speech recognition and generate the result;

a grammar data structure operable to receive and store the grammar

an application data structure operable to track the status of the Java application, and to track the status of a grammar associated with the Java application.

4. The system of claim 3, wherein the application data structure comprises a speech focus, operable to restrict communication of the result to an intended Java application.

5. The system of claim 1, wherein the speech recognition server comprises:

a speech engine operable to perform speech recognition and generate the result;

an application data structure operable to track the status of the Java application, and to track the status of a grammar associated with the Java application; and

a set of regular grammars in a directed acyclic graph operable to receive the grammar and to dynamically modify the contents of the set of regular grammars in a directed acyclic graph in response to receiving the grammar.

6. The system of claim 5, wherein the application data structure comprises a speech focus, operable to restrict communication of the result to an intended Java application.

7. The system of claim 1, wherein the application program interface comprises a server-side application program interface and an application-side application program interface.

8. The system of claim 1, wherein the application program interface comprises a server-side application program interface and an application-side application program interface;

wherein the server-side application program interface comprises a parser operable to receive the result from the speech recognition server, to parse the result, and to generate a parsed result, wherein the server-side application program interface is further operable to communicate the parsed result to the Java application.

9. The system of claim 1, wherein the application program interface comprises a server-side application program interface and an application-side application program interface;

wherein the server-side application program interface comprises a parametizer operable to receive a parameter value from the Java application and to modify a parameter of the speech recognition server according to the parameter value received.

10. The system of claim 1, wherein the speech recognition server comprises a vocabulary having an arbitrary size, wherein the speech recognition server is speaker independent and supports continuous speech.

11. A method of facilitating a speech interface to Java, the method comprising the steps of:

establishing communication between a speech recognition server and a Java application;

communicating a grammar to the speech recognition server;

performing speech recognition in response to a speech input and generating a result based on the grammar; and

communicating the result to the Java application.

12. The method of claim 11, wherein the step of establishing communication between the speech recognition server and the Java application comprises the step of adding the Java application to an application data structure.

13. The method of claim 11, wherein the step of communicating a grammar to the speech recognition server comprises the steps of:

specifying the grammar to the application program interface;

adding the grammar to a grammar data structure; and

dynamically modifying the grammar data structure in response to the addition of the grammar.

14. The method of claim 11, further comprising the step of communicating an additional grammar to the speech recognition server.

15. The method of claim 11, further comprising the step of parsing the result before it is communicated to the Java application.

16. The method of claim 11, further comprising the steps of:

receiving a parameter value; and

modifying a parameter of the speech recognition server based on the parameter value.

17. The method of claim 11, further comprising the step of giving an intended Java application a speech focus.

18. A method of facilitating a speech interface to a Java application, the method comprising the steps of:

establishing communication between a speech recognition server and a Java application;

specifying a grammar to the application program interface;

communicating the grammar to the speech recognition server;

dynamically modifying a set of regular grammars in a directed acyclic graph in response to receiving the grammar;

performing speech recognition in response to a speech input and generating a result based on the grammar; and

communicating the result to the Java application.

19. The method of claim 18, further comprising:

the steps of specifying a parameter value to the speech recognition server and modifying a parameter of the speech recognition server based on the parameter value received;

the steps of parsing the result generated by the speech recognition server, generating a parsed result and communicating the parsed result to the Java application; and

the step of giving the Java application a speech focus.

20. The method of claim 18, further comprising the steps of:

tracking the status of a plurality of Java applications; and

tracking the status of a grammar associated with the Java application.