Voicemail filtering and transcription

• US 8,107,598 B2
• Filed: 02/21/2007
• Issued: 01/31/2012
• Est. Priority Date: 02/21/2007
• Status: Active Grant

• Current Assignee: Arlington Technologies, LLC (Dominion Harbor Enterprises, LLC)
• Original Assignee: Avaya Incorporated
• Inventors: Skakkebaek, Jens Ulrik, FitzGerald, Cary W.
• Primary Examiner(s): Goins, Davetta W
• Assistant Examiner(s): ISLAM, MOHAMMAD K
• Application Number:
  US11/709,513
• Publication Number:
  US 20080198980A1
• Time in Patent Office: 1,805 Days
• Field of Search: 379/88.13, 455/466, 704/260
• US Class Current: 379/88.13
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: H04M 2201/18 Comparators
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 2201/60 Medium conversion
• CPC Class Codes: H04M 2203/303 Marking
• CPC Class Codes: H04M 2203/4536 Voicemail combined with text-based messaging
• CPC Class Codes: H04M 3/53333 Message receiving aspects
• CPC Class Codes: H04M 3/537 Arrangements for indicating the presence of a recorded message , whereby the presence information might include a preview or summary of the message

Abstract

Systems and methods for voicemail filtering and transcription are described herein. According to various embodiments, an integrated communication system performs filtering and transcription of voicemail messages (“voicemails”) and forwards the voicemails via email to a user'"'"'s email-capable device. Filtering includes generating a priority flag based on a word search of the voicemail. The integrated communication system further performs a rough transcription of the voicemail, either automatically or on demand as specified by the user. According to embodiments, the rough transcription is entered as text in an email that is sent to the user. In an embodiment, a user may request a refined transcription of the voicemail by pressing a button on the user'"'"'s device. In an embodiment, the rough transcription is replaced by the refined transcription in the original email and the original is marked “unread” in the user'"'"'s email inbox on the user'"'"'s device.

Claims

1. A computer-readable medium storing instructions that when executed in a networked communication system, cause the system to perform an integrated messaging method, the method comprising:

receiving audio data via a first network, wherein the audio data comprises a message of a first type sent by a caller to a user;

transforming the audio data to a first format;

filtering the audio data, comprising searching for predetermined words in the audio data;

transforming the audio data to a second format, wherein transforming the data comprises generating a rough transcription based on the predetermined words, wherein the rough transcription facilitates the user determining an appropriate response to the message of the first type;

generating a message of a second type, wherein the message of the second type includes the transformed audio data in the second format, wherein the message of the second type further includes the audio data in the first format;

sending the message of the second type to the user via a second network;

receiving a request from the user to provide the user a refined transcription of the message of the first type;

in response to the request, placing the audio file in the first format on a file server; and

sending a notification to a transcriber, wherein the notification includes the request and directions to the file server.

2. The computer-readable medium of claim 1, the method further comprising:

generating a priority flag based on results of the filtering; and

including the priority flag in the message of the second type.

3. The computer-readable medium of claim 1, wherein receiving comprises determining whether the audio data is to be filtered based on a user preference previously set.

4. The computer-readable medium of claim 1, wherein the predetermined words are comprised in a word list.

5. The computer-readable medium of claim 4, wherein the word list comprises a predetermined set of words and words added by the user.

6. The computer-readable medium of claim 1, wherein filtering further comprises accessing data regarding the user from a plurality of sources within an enterprise, comprising a User List, a Global Address List, Public Folders, and Personal Contact Folders.

7. The computer-readable medium of claim 1, the method further comprising sending the message of the second type to one or more recipients other than the user, based on a user preference previously set.

8. The computer-readable medium of claim 1, wherein the message of the first type is a voicemail message, and wherein the message of the second type is an email message.

9. The computer-readable medium of claim 8, wherein the first format is an electronic audio format, comprising a WAV format.

10. The computer-readable medium of claim 8, wherein the second format is text.

11. The computer-readable medium of claim 1, the method further comprising, in response to the request, sending a message of a third type to a transcriber, wherein the message of the third type includes the request and the audio data in the first format.

12. The computer-readable medium of claim 11, wherein the message of the third type is an instant message, and wherein the transcriber can listen to the audio data in the first format and type the refined transcription into the instant message.

13. The computer-readable medium of claim 12, the method further comprising:

receiving the instant message with the refined transcription from the transcriber; and

editing the message of the second type to include the refined transcription in place of the rough transcription.

14. The computer-readable medium of claim 13, the method further comprising:

resetting a status of the message of the second type to be “

unread”

.

15. The computer-readable medium of claim 1, the method further comprising presenting a web page to the transcriber, wherein the web page includes a user interface that enables the transcriber to listen to the audio data and type the refined transcription onto the web page.

16. The computer-readable medium of claim 15, wherein the user interface further enables the transcriber to send the refined transcription to the file server.

17. The computer-readable medium of claim 16, the method further comprising:

retrieving the transcription from the file server;

editing the message of the second type to include the refined transcription in place of the rough transcription.

18. The computer-readable medium of claim 17, the method further comprising:

resetting a status of the message of the second type to be “

unread”

.

19. The computer-readable medium of claim 18, the method further comprising sending a predetermined notification to the user with the message of the second type, wherein the predetermined notification notifies the user that the message of the second type now includes the refined transcription.

20. The computer-readable medium of claim 19, wherein the notification comprises one or more of a priority flag, and an audible alert.

21. A method for integrating messages, the method comprising:

receiving audio data via a first network, wherein the audio data comprises a message of a first type sent by a caller to a user;

transforming the audio data to a first format;

filtering the audio data, comprising searching for predetermined words in the audio data;

transforming the audio data to a second format, wherein transforming the data comprises generating a rough transcription based on the predetermined words, wherein the rough transcription facilitates the user determining an appropriate response to the message of the first type;

generating a message of a second type, wherein the message of the second type includes the transformed audio data in the second format, wherein the message of the second type further includes the audio data in the first format;

sending the message of the second type to the user via a second network;

receiving a request from the user to provide the user a refined transcription of the message of the first type;

in response to the request, sending a message of a third type to a transcriber, wherein the message of the third type includes the request and the audio data in the first format, wherein the message of the third type is an instant message, and wherein the transcriber can listen to the audio data in the first format and type the refined transcription into the instant message;

receiving the instant message with the refined transcription from the transcriber;

editing the message of the second type to include the refined transcription in place of the rough transcription;

resetting a status of the message of the second type to be “

unread”

; and

sending a predetermined notification to the user with the message of the second type, wherein the predetermined notification notifies the user that the message of the second type now includes the refined transcription.

22. The method of claim 21, wherein the notification comprises one or more of a priority flag, and an audible alert.

23. A computer-readable storing instructions that when executed in a networked communication system, cause the system to perform an integrated messaging method, the method comprising:

receiving audio data via a first network, wherein the audio data comprises a message of a first type sent by a caller to a user;

transforming the audio data to a first format;

filtering the audio data, comprising searching for predetermined words in the audio data;

transforming the audio data to a second format, wherein transforming the data comprises generating a rough transcription based on the predetermined words, wherein the rough transcription facilitates the user determining an appropriate response to the message of the first type;

generating a message of a second type, wherein the message of the second type includes the transformed audio data in the second format, wherein the message of the second type further includes the audio data in the first format;

sending the message of the second type to the user via a second network;

receiving a request from the user to provide the user a refined transcription of the message of the first type;

in response to the request, placing the audio file in the first format on a file server;

sending a notification to a transcriber, wherein the notification includes the request and directions to the file server;

in response to the request, sending a message of a third type to a transcriber, wherein the message of the third type includes the request and the audio data in the first format, wherein the message of the third type is an instant message, and wherein the transcriber can listen to the audio data in the first format and type the refined transcription into the instant message;

receiving the instant message with the refined transcription from the transcriber;

editing the message of the second type to include the refined transcription in place of the rough transcription;

resetting a status of the message of the second type to be “

unread”

; and

sending a predetermined notification to the user with the message of the second type, wherein the predetermined notification notifies the user that the message of the second type now includes the refined transcription.