Framework to enable multimodal access to applications

• US 20060015335A1
• Filed: 07/13/2004
• Published: 01/19/2006
• Est. Priority Date: 07/13/2004
• Status: Abandoned Application

• Current Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Original Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Inventors: Vennelakanti, Ravigopal, Agarwal, Tushar
• Application Number:
  US10/889,760
• Publication Number:
  US 20060015335A1
• Time in Patent Office: Days
• US Class Current: 704/235
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: H04M 3/4938 comprising a voice browser which renders and interprets, e.g. VoiceXML

Abstract

A technique to link an audio enabled device with a speech driven application without specifying the specific ones of the audio enabled device-independent, speech driven application-independent, and speech application platform independent parameters. In one example embodiment, this is accomplished by using voice framework that receives and transmits digitized speech audio without specifying the specific ones of the audio enabled device-independent and speech application platform-independent parameters. The voice framework then converts the received digital speech audio to computer readable text. Further, the voice framework receives and transmits the computer readable text to the speech driven application without specifying the specific ones of the speech driven application-independent and speech application platform-independent parameters. The voice framework then converts the computer readable text to the digital speech audio.

Claims

1. A voice framework to link an audio enabled device with a speech driven application without specifying the specific ones of the audio enabled device-independent and speech application platform-independent parameters, and further without specifying the specific ones of the speech driven application-independent and speech application platform-independent parameters.

2. The voice framework of claim 1, wherein the voice framework to link the audio enabled device with the speech driven application without specifying the specific ones of the audio enabled device-independent and speech application-independent parameters comprises:

an audio enabled device adapter for receiving and transmitting a digitized speech audio without specifying the specific ones of the audio enabled device-independent and speech application platform-independent parameters.

3. The voice framework of claim 2, wherein the voice framework to link the audio enabled device with the speech driven application without specifying the specific ones of the speech driven application and speech application-independent parameters comprises:

a speech driven application adapter for receiving and transmitting a computer readable text from the speech driven application without specifying the specific ones of the speech driven application-independent and platform-independent parameters.

4. The voice framework of claim 3, comprises:

a speech engine hub for converting the received digitized speech audio to the computer readable text and for converting the received computer readable text to the digitized speech audio, wherein the speech engine hub is speech engine independent.

5. The voice framework of claim 4, wherein the speech engine hub comprises:

a speech recognition engine to convert the received digitized speech audio to computer readable text; and

a text-to-speech (TTS) engine to convert computer readable text to the digitized speech audio.

6. A system comprising:

a speech engine hub;

an audio enabled device adapter for providing an audio enabled device independent interface between a specific audio enabled device and the speech engine hub, wherein the audio enabled device adapter to receive digitized speech audio from the specific audio enabled device without specifying the specific ones of the audio enabled device-independent and software platform-independent parameters, wherein the speech engine hub is communicatively coupled to the audio enabled device adapter to convert the digitized audio speech to computer readable text; and

a speech driven application adapter communicatively coupled to the speech engine hub for providing a speech driven application independent interface between a speech driven application and the speech engine hub, wherein the speech engine hub to transmit the computer readable text to the speech driven application adapter, wherein the speech driven application adapter to transmit the digitized audio speech to a specific speech driven application without specifying the specific ones of the speech driven application-independent and software platform independent parameters.

7. The system of claim 6, wherein the speech driven application adapter to receive the computer readable text from a specific speech driven application without specifying the specific ones of the speech driven application-independent and software platform independent parameters, wherein the speech engine hub to convert the computer readable text received from the speech driven application adapter to the digitized speech audio.

8. The system of claim 7, wherein the speech engine hub to transmit the digitized speech audio to the audio enabled device adapter, wherein the audio enabled device adapter to transmit the digitized speech audio to a specific audio enabled device without specifying the specific ones of the audio enabled device-independent and software platform-independent parameters.

9. The system of claim 6, wherein the speech engine hub comprises:

a speech recognition engine, wherein the speech recognition engine converts the digitized speech audio to computer readable text; and

a TTS engine, wherein the TTS engine converts the computer readable text to the digitized speech audio.

10. The system of claim 9, wherein the speech engine hub further comprising:

a speech register for loading a specific speech engine service by activating and configuring the speech engine hub based on application needs.

11. The system of claim 6, further comprising:

a markup interpreters module coupled to the speech engine hub for enabling speech driven applications and audio enabled devices to communicate with the voice framework via industry compliant instruction sets and markup languages, wherein the markup interpreters module includes one or more interpreters for markup languages, wherein the one or more interpreters are selected from the group consisting of a Voice XML interpreter, a SALT interpreter, and a proprietary instruction interpreter.

12. A system comprising:

an audio enabled device adapter for transporting digitized speech audio without specifying the specific ones of the audio enabled device-independent and software platform-independent parameters;

a speech engine hub communicatively coupled to the audio enabled device adapter for converting the digitized audio speech to computer readable text; and

a speech driven application adapter communicatively coupled to the speech engine hub for transporting the computer readable text without specifying the specific ones of the speech driven application-independent and software platform independent parameters, and wherein the speech engine hub converts the computer readable text to the digitized audio speech.

13. The system of claim 12, further comprising an audio enabled device communicatively coupled to the audio enabled device adapter via a network, wherein the audio enabled device comprises a device selected from the group consisting of a telephone, a cell phone, a PDA, a laptop computer, a smart phone, a tablet PC, and a desktop computer.

14. The system of claim 13, wherein the audio enabled device adapter comprises an audio enabled device adapter selected from the group consisting of a telephony adapter, a PDA adapter, a Web adapter, a laptop computer adapter, a smart phone adapter, a tablet PC adapter, a VoIP adapter, a DTMF adapter, a embedded system adapter, and a desktop computer adapter.

15. The system of claim 12, further comprising a speech driven applications module communicatively coupled to the speech driven application adapter via a network, wherein the speech driven applications module comprises one or more enterprise applications selected from the group consisting of telephone applications, customized applications, portals, web applications, CRM systems, knowledge management systems, interactive speech enabled voice response systems, and multimodal access enabled portals.

16. The system of claim 15, wherein the speech driven application adapter comprises one or more applications adapters selected from the group consisting of a Web/HTML adapter, a database adapter, a legacy applications adapter, and a web services adapter.

17. The system of claim 12, further comprising:

a head end server for launching and managing the speech driven application adapter;

a configuration manager for maintaining configuration information pertaining to the voice framework;

a log manager that keeps track of operation of the voice framework and wherein the log manager logs operational messages and generates reports of the logged operational messages;

a privilege server coupled to the data server and the head end server for authenticating, authorizing, and granting privileges to a client to access the voice framework;

a data server coupled to the speech engine hub for interfacing data storage systems and retrieval systems with the speech engine hub; and

an alert manager for posting alerts within the voice framework.

18. The system of claim 17, further comprising:

a capability negotiator coupled to the audio enabled device adapter for negotiating capabilities of the audio enabled device;

an audio streamer coupled to the audio enabled device adapter for providing a continuous stream of audio data to the audio enabled device;

a raw audio adapter coupled to the audio streamer and the audio enabled device adapter for storing the audio data in a neutral format and for converting the audio data to a required audio format; and

language translator module coupled to the raw audio adapter and the audio enabled device adapter for translating a text received in one language to another language.

19. A method comprising:

transporting digital audio speech between a specific audio enabled device and a specific speech driven application using a voice framework that provides audio enabled device and speech driven application independent methods, wherein the audio enabled device not specifying the audio enabled device-independent and platform-independent parameters necessary to transport digital audio speech between the specific audio enabled device and the specific speech driven application, and wherein the speech driven application not specifying the speech driven application-independent and platform-independent parameters necessary to transport the digital audio speech between the speech driven application and the audio enabled device.

20. The method of claim 19, further comprising:

receiving and converting the digital speech audio to computer readable text; and

receiving and converting the computer readable text to the digital speech audio.

21. The method of claim 20, further comprising:

transporting the digital speech audio to the specific audio enabled device via a network; and

transporting the computer readable text to the specific speech driven application via the network.

22. A method for linking an audio enabled device to a speech driven application comprising:

receiving digitized speech audio from a specific audio enabled device without specifying the specific ones of the audio enabled device-independent parameters and platform-independent parameters;

converting the digitized speech audio to computer readable text using a speech engine hub; and

transporting the computer readable text to a specific speech driven application without specifying the specific ones of the speech driven application-independent parameters and platform-independent parameters necessary to transport the computer readable text.

23. The method of claim 22, further comprising:

receiving computer readable text from a specific speech driven application without specifying the specific ones of the speech driven application-independent parameters and platform-independent parameters; and

converting the computer readable text received from the specific speech driven application to the digitized speech audio using the speech engine hub; and

transporting the digitized speech audio to the specific audio enabled device without specifying the specific ones of the speech driven application-independent parameters and platform-independent parameters necessary to transport the computer readable text.

24. The method of claim 22, further comprising:

configuring an input buffer to receive the digitized speech audio from the specific audio enabled device; and

configuring an output buffer to transmit the digitized speech audio to the specific audio enabled device.

25. A method for linking a specific audio enabled device with a speech driven application comprising:

receiving digitized speech audio from a specific audio enabled device via the audio enabled device-independent and platform-independent methods that do not require a device specific and speech application platform specific configurations, respectively;

converting the digitized speech audio to computer readable text; and

transporting the computer readable text to a specific speech driven application via the speech driven application-independent platform-independent methods that do not require a speech application specific and speech application platform specific configurations, respectively.

26. The method of claim 25, further comprising:

receiving computer readable text from a specific speech driven application via the speech driven application-independent and platform-independent methods that do not require a speech driven application-independent specific and speech application platform-independent configurations, respectively; and

converting the computer readable text received from the specific speech driven application to the digitized speech audio; and

transporting the digitized speech audio to the specific audio enabled device via the audio enabled device-independent and platform-independent methods that do not require a device specific and speech application platform specific configurations, respectively.

27. The method of claim 26, further comprising:

configuring an input buffer to receive the digitized speech audio from the specific audio enabled device; and

configuring an output buffer to transmit the digitized speech audio to the specific audio enabled device.

28. An article comprising:

a storage medium having instructions that, when executed by a computing platform, result in execution of a method comprising;

receiving digitized speech audio from a specific audio enabled device via the audio enabled device-independent and platform-independent methods that do not require a device specific and speech application platform specific configurations, respectively;

converting the digitized speech audio to computer readable text; and

transporting the computer readable text to a specific speech driven application via the speech driven application-independent platform-independent methods that do not require a speech application specific and speech application platform specific configurations, respectively.

29. The article of claim 28, further comprising:

receiving computer readable text from a specific speech driven application via the speech driven application-independent and platform-independent methods that do not require a speech driven application-independent specific and speech application platform-independent configurations, respectively;

converting the computer readable text received from the specific speech driven application to the digitized speech audio; and

transporting the digitized speech audio to the specific audio enabled device via the audio enabled device-independent and platform-independent methods that do not require a device specific and speech application platform specific configurations, respectively.

30. The article of claim 29, further comprising:

configuring an input buffer to receive the digitized speech audio from the specific audio enabled device; and

configuring an output buffer to transmit the digitized speech audio to the specific audio enabled device.