Methods and apparatus for buffering data for use in accordance with a speech recognition system

• US 20070043563A1
• Filed: 08/22/2005
• Published: 02/22/2007
• Est. Priority Date: 08/22/2005
• Status: Active Grant

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Viswanathan, Mahesh, Rachevksy, Leonid, Frank, David, Comerford, Liam, Lewis, Burn
• Granted Patent: US 7,962,340 B2
• Time in Patent Office: Days
• US Class Current: 704/243
• CPC Class Codes: G10L 15/28 Constructional details of speech recognition systems

Abstract

Techniques are disclosed for overcoming errors in speech recognition systems. For example, a technique for processing acoustic data in accordance with a speech recognition system comprises the following steps/operations. Acoustic data is obtained in association with the speech recognition system. The acoustic data is recorded using a combination of a first buffer area and a second buffer area, such that the recording of the acoustic data using the combination of the two buffer areas at least substantially minimizes one or more truncation errors associated with operation of the speech recognition system.

Claims

1. A method for processing acoustic data in accordance with a speech recognition system, comprising the steps of:

obtaining acoustic data in association with the speech recognition system; and

recording the acoustic data using a combination of a first buffer area and a second buffer area, such that the recording of the acoustic data using the combination of the two buffer areas at least substantially minimizes one or more truncation errors associated with operation of the speech recognition system.

2. The method of claim 1, wherein the recording step further comprises:

recording acoustic data obtained by the speech recognition system in the first buffer area;

stopping recording of acoustic data in the first buffer area and starting recording of acoustic data obtained by the speech recognition system in the second buffer area, when an indication that the speech recognition system is being addressed is detected; and

prepending, to the beginning of the acoustic data stored in the second buffer area, acoustic data in the first buffer area.

3. The method of claim 2, wherein, after the prepending step, a composite buffer area comprises the prepended acoustic data and the acoustic data from the second buffer area.

4. The method of claim 3, wherein the composite buffer area contains, at the start of the acoustic data prepended to the second buffer area, the oldest acoustic data in the first buffer area, and further wherein the acoustic data recorded immediately before the indication that the speech recognition system is being addressed ends the prepended acoustic data and is contiguous in memory with the acoustic data which immediately followed the indication that the speech recognition system is being addressed that is stored in the second buffer area.

5. The method of claim 4, further comprising the step of processing the acoustic data in the composite buffer area to detect one or more features indicating silence.

6. The method of claim 5, wherein the location of the silence closest to the end of the prepended acoustic data is used as the location in the composite buffer area at which speech intended for the speech recognition system to process begins.

7. The method of claim 6, wherein the silence is in the prepended acoustic data if the indication that the speech recognition system is being addressed was given after speech started, and further wherein the silence follows the end of the prepended acoustic data if speech began after the indication.

8. The method of claim 3, further comprising the step of decoding acoustic data in the composite buffer area into text.

9. The method of claim 2, wherein the recording of acoustic data in the second buffer area continues until an indication that the speech recognition system is no longer being addressed is detected and a silence indication is detected in the acoustic data recorded in the second buffer area.

10. The method of claim 2, further comprising stopping recording of acoustic data in the second buffer area and restarting recording of acoustic data in the first buffer area, when an indication that the speech recognition system is no longer being addressed is detected and a silence indication is detected in the acoustic data recorded in the second buffer area.

11. The method of claim 10, wherein the indication that the speech recognition system is being addressed comprises a microphone on event, and the indication that the speech recognition system is no longer being addressed comprises a microphone off event.

12. The method of claim 2, wherein the first buffer area comprises a circular buffer, and the second buffer area comprises a linear buffer.

13. The method of claim 1, wherein the first buffer area and the second buffer area are at least part of a single storage data structure.

14. The method of claim 1, wherein the first buffer area and the second buffer area are at least part of separate storage data structures.

15. The method of claim 1, wherein the recording step further comprises:

recording acoustic data obtained by the speech recognition system in the first buffer area;

appending acoustic data recorded in the first buffer area to the second buffer area, when the first buffer area is full;

identifying the existence of a speech region and a silence region in the acoustic data appended to the second buffer area;

detecting when an indication that the speech recognition system is being addressed occurs; and

filling a recognition buffer area at least with the acoustic data appended to the second buffer area, when a speech region is identified and when the indication that the speech recognition system is being addressed is detected, or filling the recognition buffer area at least with incoming acoustic data for the speech recognition system, when a silence region is identified and when the indication that the speech recognition system is being addressed is detected.

16. The method of claim 15, further comprising the step of decoding the acoustic data in the recognition buffer area.

17. Apparatus for processing acoustic data in accordance with a speech recognition system, comprising:

a memory comprising a first buffer area and a second buffer area; and

a processor coupled to the memory and operative to;

(i) obtain acoustic data in association with the speech recognition system; and

(ii) record the acoustic data using a combination of the first buffer area and the second buffer area, such that the recording of the acoustic data using the combination of the two buffer areas at least substantially minimizes one or more truncation errors associated with operation of the speech recognition system.

18. The apparatus of claim 17, wherein the recording operation further comprises:

recording acoustic data obtained by the speech recognition system in the first buffer area;

stopping recording of acoustic data in the first buffer area and starting recording of acoustic data obtained by the speech recognition system in the second buffer area, when an indication that the speech recognition system is being addressed is detected; and

prepending, to the beginning of the acoustic data stored in the second buffer area, acoustic data in the first buffer area.

19. The apparatus of claim 17, wherein the recording operation further comprises:

recording acoustic data obtained by the speech recognition system in the first buffer area;

appending acoustic data recorded in the first buffer area to the second buffer area, when the first buffer area is full;

identifying the existence of a speech region and a silence region in the acoustic data appended to the second buffer area;

detecting when an indication that the speech recognition system is being addressed occurs; and

filling a recognition buffer area at least with the acoustic data appended to the second buffer area, when a speech region is identified and when the indication that the speech recognition system is being addressed is detected, or filling the recognition buffer area at least with incoming acoustic data for the speech recognition system, when a silence region is identified and when the indication that the speech recognition system is being addressed is detected.

20. An article of manufacture for use in processing acoustic data in accordance with a speech recognition system, comprising a machine readable medium containing one or more programs which when executed implement the steps of:

obtaining acoustic data in association with the speech recognition system; and

recording the acoustic data using a combination of a first buffer area and a second buffer area, such that the recording of the acoustic data using the combination of the two buffer areas at least substantially minimizes one or more truncation errors associated with operation of the speech recognition system.