Method, system, and apparatus for repairing audio recordings

• US 20050207541A1
• Filed: 09/27/2004
• Published: 09/22/2005
• Est. Priority Date: 09/30/2003
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Dictaphone Corporation (Microsoft Corporation)
• Inventors: Cote, William F.
• Granted Patent: US 7,542,909 B2
• Time in Patent Office: Days
• US Class Current: 379/46
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G11B 20/10009 Improvement or modification of read or write signals
• CPC Class Codes: G11B 20/10527 Audio or video recording; Data buffering arrangements G11B20/12 - G11B20/18 take precedence
• CPC Class Codes: H04M 11/10 with dictation recording and playback systems

Abstract

A system and method is disclosed for detecting and repairing audio recordings that contain busy signals and extended periods of silence by searching for clusters of silence by reviewing the amplitude in an audio recording sample and listing each silence and sample time.

Claims

1. A method for repairing an audio recording, the method comprising the steps of:

detecting an anomaly point in the audio recording, comprising the steps of;

detecting at least one silence in the audio recording;

determining the length of the at least one silence;

detecting at least one busy signal in the audio recording;

detecting a final silence;

detecting a hang-up silence;

determining the location of the hang-up silence in the audio recording;

truncating said audio recording at the anomaly point; and

outputting said truncated audio recording.

2. The method according to claim 1, wherein detecting the at least one busy signal comprises the steps of:

determining a location of a first busy signal;

determining a rate of the first busy signal;

determining a location of a second busy signal; and

determining a rate of the second busy signal.

3. The method according to claim 2, further comprising the step of determining a location of a third busy signal.

4. The method according to claim 3, where detecting the location of the hang-up silence in the audio recording comprises the step subtracting the length of the detected busy signal from the location of the third busy signal.

5. The method according to claim 4, further comprising the steps of;

determining whether the first busy signal has a first pre-determined value;

determining whether the second busy signal has a second pre-determined value;

determining whether the hang-up silence has a third pre-determined value;

determining whether the final silence has a fourth pre-determined value;

determining a spacing between the first busy signal and the second busy signal; and

determining a spacing between the first busy signal and the final silence.

6. The method according to claim 5, where the third pre-determined value equals one.

7. The method according to claim 6, where the first pre-determined value equals one.

8. The method according to claim 7, where the second pre-determined value equals one.

9. The method according to claim 8, where the fourth pre-determined value equals one.

10. The method according to claim 6, where the anomaly point is the location of the hang-up silence.

11. The method according to claim 5 where the fourth pre-determined value equals zero.

12. The method according to claim 11, where the first pre-determined value equals zero.

13. The method according to claim 12, where the second pre-determined value equals zero.

14. The method according to claim 13, where the third pre-determined value equals zero.

15. The method according to claim 14, where the anomaly point is the location of the at least one silence.

16. The method according to claim 6, where the first pre-determined value is greater than zero.

17. The method according to claim 15, where the second pre-determined value is greater than zero.

18. The method according to claim 16, where the fourth pre-determined value is greater than zero.

19. The method according to claim 2, where in the third busy signal is an inter-busy signal.

20. The method according to claim 1, where the truncated audio recording is output to a speech recognition engine.