Device-independent speech audio system for linking a speech driven application to specific audio input and output devices

• US 6,631,350 B1
• Filed: 08/28/2000
• Issued: 10/07/2003
• Est. Priority Date: 08/28/2000
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Lucas, Bruce D., Gavagni, Brett, Leontiades, Leo, Celi, Joseph Jr.
• Primary Examiner(s): MCFADDEN, SUSAN IRIS
• Application Number:
  US09/649,189
• Time in Patent Office: 1,135 Days
• Field of Search: 704/270, 704/275, 379/88.1, 434/185
• US Class Current: 704/270
• CPC Class Codes: G06F 3/16 Sound input; Sound output speech processing G10L
• CPC Class Codes: H04M 3/4938 comprising a voice browser which renders and interprets, e.g. VoiceXML

Abstract

A device-independent speech audio system for linking a speech driven application to specific audio input and output devices can include a media framework for transporting digitized speech audio between speech driven applications and a plurality of audio input and output devices. The media framework can include selectable device-dependent parameters which can enable the transportation of the digitized speech to and from the plurality of audio input and output devices. The device-independent speech audio system also can include an audio abstractor configurable to provide specific ones of the selectable device-dependent parameters according to the specific audio input and output devices. Hence, the audio abstractor can provide a device-independent interface to the speech driven application for linking the speech driven application to the specific audio input and output devices.

Claims

1. A device-independent speech audio system for linking a speech driven application to specific audio input and output devices comprising:

a media framework for transporting digitized speech audio between speech driven applications and a plurality of audio input and output devices, said media framework comprising selectable device-dependent parameters for enabling said transportation of said digitized speech to and from said plurality of audio input and output devices; and

,

an audio abstractor configurable to provide specific ones of said selectable device-dependent parameters according to the specific audio input and output devices;

said audio abstractor providing a device-independent interface to the speech driven application for linking the speech driven application to the specific audio input and output devices.

2. The system of claim 1, further comprising:

a speech recognition engine communicatively linked to said device-independent interface of said audio abstractor;

said speech recognition engine receiving said digitized speech audio from a specific audio input device via said audio abstractor without specifying said specific ones of said device-dependent parameters;

said speech recognition engine converting said received digitized speech audio to computer readable text and providing said converted computer readable text to the speech driven application.

3. The system of claim 1, further comprising:

a text-to-speech (TTS) engine communicatively linked to said device-independent interface of said audio abstractor;

said TTS engine transmitting said digitized speech audio to a specific audio output device via said audio abstractor without specifying said specific ones of said device-dependent parameters;

said TTS engine converting computer readable text received from the speech driven application into said digitized speech audio.

4. The system of claim 1, wherein said interface comprises:

a device-independent method for opening a buffer for receiving said digitized speech audio from a specific audio input source.

5. The system of claim 1, wherein said interface comprises:

a device-independent method for opening a buffer for transmitting said digitized speech audio to a specific audio output source.

6. The system of claim 5, wherein said interface further comprises:

a device-independent method for opening a buffer for receiving said digitized speech audio from a specific audio input source.

7. The system of claim 1, wherein said device-dependent parameters comprise:

encoding type.

8. The system of claim 7, wherein said device-dependent parameters further comprise:

sample rate;

sample size; and

,

channels.

9. The system of claim 8, wherein said device-dependent parameters further comprise:

byte order; and

,

signed/unsigned format.

10. The system of claim 9, wherein said device-dependent parameters further comprise:

frame size;

frame rate; and

,

data type.

11. The system of claim 1, wherein said media framework comprises a Java Media Framework (JMF).

12. The system of claim 1, wherein said specific audio input and output devices are remotely positioned from the speech driven application in a computer communications network.

13. The system of claim 1, wherein the speech driven application is employed in an IVR system in a node in a computer communications network.

14. The system of claim 12, wherein said specific audio input and output devices are configured to place and receive telephone calls.

15. The system of claim 14, wherein said telephone calls are converted to digitized speech audio through a telephony interface to said computer communications network.

16. A method for linking a speech driven application to specific audio input and output devices comprising:

configuring an input buffer to receive digitized speech audio from a specific audio input device;

configuring an output buffer to transmit digitized speech audio to a specific audio output device;

providing device-independent methods for accessing said buffers; and

,

transporting digitized speech audio between the speech driven application and said specific audio input and output devices through said buffers via said device-independent methods, the speech driven application not specifying device-dependent parameters necessary to transport said digitized speech audio between said audio input and output sources.

17. The method of claim 16, wherein said step of configuring comprises:

selecting in said device-independent methods at least one method in a media framework for configuring said buffers according to device-dependent parameters necessary to transport said digitized speech audio between said specific audio input and output devices.

18. The method of claim 16, further comprising:

communicatively linking a speech recognition engine to said input buffer;

transporting said digitized speech audio from said specific audio input device to said speech recognition engine through said input buffer without specifying said device-dependent parameters;

converting said digitized speech audio to text in said speech recognition engine and providing said converted text to the speech driven application.

19. The method of claim 16, further comprising:

communicatively linking a text-to-speech (TTS) engine to said output buffer;

converting computer readable text in the speech driven application to said digitized speech audio in said TTS engine; and

,

transporting said digitized speech audio from said TTS engine to said specific audio output device through said output buffer without specifying said device-dependent parameters.

20. A machine readable storage, having stored thereon a computer program for transparently linking a speech driven application to specific audio input and output devices, said computer program having a plurality of code sections executable by a machine for causing the machine to perform the steps of:

configuring an input buffer to receive digitized speech audio from a specific audio input device;

configuring an output buffer to transmit digitized speech audio to a specific audio output device;

providing device-independent methods for accessing said buffers; and

,

transporting digitized speech audio between the speech driven application and said specific audio input and output devices through said buffers via said device-independent methods, the speech driven application not specifying device-dependent parameters necessary to transport said digitized speech audio between said audio input and output sources.

21. The machine readable storage of claim 20, wherein said step of configuring comprises:

selecting in said device-independent methods at least one method in a media framework for configuring said buffers according to device-dependent parameters necessary to transport said digitized speech audio between said specific audio input and output devices.

22. The machine readable storage of claim 20, further comprising:

communicatively linking a speech recognition engine to said input buffer;

transporting said digitized speech audio from said specific audio input device to said speech recognition engine through said input buffer without specifying said device-dependent parameters;

converting said digitized speech audio to text in said speech recognition engine and providing said converted text to the speech driven application.

23. The machine readable storage of claim 20, further comprising:

communicatively linking a text-to-speech (TTS) engine to said output buffer;

converting computer readable text in the speech driven application to said digitized speech audio in said TTS engine; and

,

transporting said digitized speech audio from said TTS engine to said specific audio output device through said output buffer without specifying said device-dependent parameters.