Correlation of transcribed text with corresponding audio

• US 8,374,864 B2
• Filed: 03/17/2010
• Issued: 02/12/2013
• Est. Priority Date: 03/17/2010
• Status: Active Grant

• Current Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Original Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Inventors: Kerr, Jim
• Primary Examiner(s): GUERRA-ERAZO, EDGAR X
• Application Number:
  US12/661,457
• Publication Number:
  US 20110231184A1
• Time in Patent Office: 1,063 Days
• Field of Search: 704/201, 704/235, 704/251, 704/253, 704/244, 704/231, 704/232, 704/243, 704/270, 704/270.1, 704/275, 704/276, 379/88.01, 379/88.08, 379/88.13
• US Class Current: 704/243
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04M 1/72403 with means for local support of applications that increase the functionality
• CPC Class Codes: H04M 2250/74 with voice recognition means voice activated dialling H04M1/271; voice recognition algorithms G10L15/00

Abstract

In one embodiment, a method includes receiving at a communication device an audio communication and a transcribed text created from the audio communication, and generating a mapping of the transcribed text to the audio communication independent of transcribing the audio. The mapping identifies locations of portions of the text in the audio communication. An apparatus for mapping the text to the audio is also disclosed.

Claims

1. A method comprising:

receiving at a communication device, an audio file comprising an audio communication;

receiving at the communication device, a text file comprising a transcribed text created from the audio communication; and

generating at the communication device, a mapping of the text file comprising the transcribed text to the audio file comprising the audio communication, independent of transcribing the audio communication, said mapping identifying locations of portions of the transcribed text in the audio communication

wherein generating said mapping comprises processing the audio file at a speech recognition engine to match words in the text file to sounds in the audio file.

2. The method of claim 1 wherein the audio communication comprises a voice mail message.

3. The method of claim 1 wherein the transcribed text comprises a human generated transcription.

4. The method of claim 1 wherein the communication device comprises a voice mail system.

5. The method of claim 1 wherein the communication device comprises a user device operable to display the transcribed text and play the audio communication.

6. The method of claim 1 further comprising transmitting the audio communication to a transcription center and wherein receiving the transcribed text comprises receiving the text from the transcription center.

7. The method of claim 1 wherein said portions of the text comprise words or phrases and said locations comprise time offsets from a start of the audio communication.

8. The method of claim 1 further comprising inserting links in the transcribed text to said locations in the audio communication based on said mapping.

9. An apparatus comprising:

memory for storing an audio file comprising an audio communication and a text file comprising a transcribed text created from the audio communication; and

a processor for generating a mapping of the text file comprising the transcribed text to the audio file comprising the audio communication independent of transcribing the audio communication, said mapping identifying locations of portions of the text in the audio communication; and

a speech recognition engine, wherein generating said mapping comprises processing the audio file at the speech recognition engine to match words in the text file to sounds in the audio file.

10. The apparatus of claim 9 wherein the audio communication comprises a voice mail message.

11. The apparatus of claim 9 wherein the transcribed text comprises a human generated transcription.

12. The apparatus of claim 9 wherein the apparatus comprises a voice mail system.

13. The apparatus of claim 9 wherein the apparatus comprises a user device operable to display the transcribed text and play the audio communication.

14. The apparatus of claim 9 wherein the processor is configured to transmit the audio communication to a transcription center and receive the transcribed text from the transcription center.

15. The apparatus of claim 9 wherein said portions of the text comprise words or phrases and said locations comprise time offsets from a start of the audio communication.

16. The apparatus of claim 9 wherein the processor is further operable to insert links in the transcribed text to said locations in the audio communication based on said mapping.

17. Logic encoded in one or more non-transitory media for execution and when executed operable to:

receive an audio file comprising an audio communication;

receive a text file comprising a transcribed text created from the audio communication; and

generate a mapping of the text file comprising the transcribed text to the audio file comprising the audio communication independent of transcribing the audio communication, said mapping identifying locations of portions of the text in the audio communication;

wherein generating said mapping comprises processing the audio file to match words in the text file to sounds in the audio file.

18. The logic of claim 17 wherein the logic is operable to insert links in the transcribed text to said locations in the audio communication based on said mapping.