Dynamic switching between local and remote speech rendering

• US 20060122836A1
• Filed: 12/08/2004
• Published: 06/08/2006
• Est. Priority Date: 12/08/2004
• Status: Active Grant

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Cross, Charles W. Jr., McCobb, Gerald M., Jaramillo, David
• Granted Patent: US 8,024,194 B2
• Time in Patent Office: Days
• US Class Current: 704/260
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: H04M 1/72445 for supporting Internet browser applications
• CPC Class Codes: H04M 2250/74 with voice recognition means voice activated dialling H04M1/271; voice recognition algorithms G10L15/00
• CPC Class Codes: H04M 3/493 Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals

Abstract

A multimodal browser for rendering a multimodal document on an end system defining a host can include a visual browser component for rendering visual content, if any, of the multimodal document, and a voice browser component for rendering voice-based content, if any, of the multimodal document. The voice browser component can determine which of a plurality of speech processing configuration is used by the host in rendering the voice-based content. The determination can be based upon the resources of the host running the application. The determination also can be based upon a processing instruction contained in the application.

Claims

1. A computer-based method of running an application distributed from a server to an end system defining a host, the method comprising:

automatically selecting a speech processing configuration for rendering voice-based content of the application if the application includes voice-based content, the selection of the speech processing configuration being based upon a processing instruction contained in the application and the processing resources available to the host;

loading at least one speech processing engine based upon the selected speech processing configuration; and

rendering the voice-based content using the at least one speech processing engine.

2. The method of claim 1, further comprising dynamically switching between a plurality of different speech processing configurations for rendering voice-based content associated with different applications.

3. The method of claim 1, wherein the speech processing configuration comprises one of a local text-to-speech (TTS) engine with a local speech recognition engine configuration, a local TTS engine with a remote speech recognition engine, and a remote TTS engine with a remote speech recognition engine.

4. The method of claim 1, further comprising providing an error indication if the host lacks speech processing resources for rendering the voice-based content according to the processing instruction.

5. The method of claim 1, wherein the application comprises a Web-based application and the server comprises a Web server.

6. The method of claim 5, wherein the Web-based application comprises at least one multimodal Web page.

7. The method of claim 6, wherein the multimodal Web page is an XML document that specifies how a user interacts with the host and application using at least one of a graphical user interface (GUI) and speech.

8. A multimodal browser for rendering a multimodal document on an end system defining a host, the multimodal browser comprising:

a visual browser component for rendering visual content of the multimodal document; and

a voice browser component for rendering voice-based content of the multimodal document, the voice browser component determining which of a plurality of speech processing configurations is used in rendering the voice-based content, the determination being based upon a processing instruction contained in the application and the processing resources available to the host.

9. The multimodal browser of claim 8, wherein the voice browser dynamically switches between a plurality of different speech processing configurations for rendering voice-based content associated with different applications.

10. The multimodal browser of claim 8, wherein the plurality of speech rendering engines comprises a local text-to-speech (TTS) engine with a local speech recognition engine configuration, a local TTS engine with a remote speech recognition engine, and a remote TTS engine with a remote speech recognition engine.

11. The multimodal browser of claim 8, wherein the voice browser component determines an error occurrence if the host lacks processing resources for rendering voice-based content using a speech rendering engine in accordance with the instruction.

12. The multimodal browser of claim 8, wherein the voice browser component determines which of a plurality of speech rendering engines is used based upon a speech location property contained in a configuration file stored in the host.

13. The multimodal browser of claim 8, wherein the multimodal document comprises a multimodal Web page containing an XML processing instruction, and wherein the voice browser component determines which of a plurality of speech rendering engines is used based on the XML processing instruction.

14. A computer readable storage medium for use in running an application distributed from a server to an end system defining a host, the storage medium comprising computer instructions for:

selecting a speech processing configuration for rendering voice-based content of the application if the application includes voice-based content, the selection of the speech processing configuration being based upon a processing instruction contained in the application and the processing resources available to the host; and

utilizing at least one speech processing engine to render the voice-based content according to the selected speech processing configuration.

15. The computer readable storage medium of claim 14, wherein selecting comprises dynamically switching between a plurality of different speech processing configurations for rendering voice-based content associated with different applications..

16. The computer readable storage medium of claim 14, wherein the speech processing configuration comprises at least one of a local text-to-speech (TTS) engine with a local speech recognition engine configuration, a local TTS engine with a remote speech recognition engine, and a remote TTS engine with a remote speech recognition engine.

17. The computer readable storage medium of claim 14, further comprising indicating an error if the host lacks speech processing resources for rendering the voice-based content according to the processing instruction.

18. The computer readable storage medium of claim 14, wherein the application comprises a Web-based application and the server comprises a Web server.

19. The computer readable storage medium of claim 18, wherein the Web-based application comprises at least one multimodal document.

20. The computer readable storage medium of claim 19, wherein the multimodal document is an XML document that specifies how a user interacts with the host and application using at least one of a graphical user interface or speech.