METHOD AND SYSTEM FOR PROVIDING AN AUTOMATED WEB TRANSCRIPTION SERVICE

• US 20080059173A1
• Filed: 08/31/2006
• Published: 03/06/2008
• Est. Priority Date: 08/31/2006
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: AT&T Corporation (AT&T, Inc.)
• Inventors: Gilbert, Mazin, Kanthak, Stephan
• Granted Patent: US 8,521,510 B2
• Time in Patent Office: Days
• US Class Current: 704/235
• CPC Class Codes: G06F 16/972 Access to data in other repository systems, e.g. legacy data or dynamic Web page generation
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

A system, method and computer readable medium that provides an automated web transcription service is disclosed. The method may include receiving input speech from a user using a communications network, recognizing the received input speech, understanding the recognized speech, transcribing the understood speech to text, storing the transcribed text in a database, receiving a request via a web page to display the transcribed text, retrieving transcribed text from the database, and displaying the transcribed text to the requester using the web page.

Claims

1. A method of providing an automated web transcription service, comprising:

receiving input speech from a user using a communications network;

recognizing the received input speech;

understanding the recognized speech;

transcribing the understood speech to text;

storing the transcribed text in a database;

receiving a request via a web page to display the transcribed text;

retrieving transcribed text from the database; and

displaying the transcribed text to the requester using the web page.

2. The method of claim 1, wherein the communications network is one of a computer network, an Internet, and a telephone network.

3. The method of claim 1, further comprising:

recognizing and understanding system commands spoken by the user, wherein the system commands facilitate the user'"'"'s navigation through the transcribed text and correction of the transcribed text.

4. The method of claim 1, further comprising:

prompting the requester to correct the displayed transcription;

receiving correction inputs for the displayed transcription from the requester; and

correcting the transcription according to the received correction inputs.

5. The method of claim 4, further comprising:

calculating an accuracy of the transcription based on the correction inputs.

6. The method of claim 1, further comprising:

prompting the requester to select one of printing the displayed transcript, sending the transcript to another party, and saving the displayed transcript to a memory.

7. The method of claim 1, wherein the transcribing step transcribes the text into a predefined document template.

8. The method of claim 1, wherein the transcribing step highlights transcribed text based on recognition confidence levels.

9. The method of claim 1, further comprising:

learning from correction data and new data; and

adapting the automated web transcription service based on the learned correction data and new data.

10. A computer-readable medium storing instructions for controlling a computing device to provide automated web transcription services, the instructions comprising:

receiving input speech from a user using a communications network;

recognizing the received input speech;

understanding the recognized speech;

transcribing the understood speech to text;

storing the transcribed text in a database;

receiving a request via a web page to display the transcribed text;

retrieving transcribed text from the database; and

displaying the transcribed text to the requester using the web page.

11. The computer-readable medium of claim 10, wherein the communications network is one of a computer network, an Internet, and a telephone network.

12. The computer-readable medium of claim 10, further comprising:

recognizing and understanding system commands spoken by the user, wherein the system commands facilitate the user'"'"'s navigation through the transcribed text and correction of the transcribed text.

13. The computer-readable medium of claim 10, further comprising:

prompting the requester to correct the displayed transcription;

receiving correction inputs for the displayed transcription from the requester; and

correcting the transcription according to the received correction inputs.

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

calculating an accuracy of the transcription based on the correction inputs.

15. The computer-readable medium of claim 10, further comprising:

prompting the requester to select one of printing the displayed transcript, sending the transcript to another party, and saving the displayed transcript to a memory.

16. The computer-readable medium of claim 10, wherein the transcribing instruction transcribes the text into a predefined document template.

17. A system that provides automated web transcription services, comprising:

a database;

an automated web transcription service unit that further comprises;

an automatic speech recognizer that receives input speech from a user using a communications network and recognizes the received input speech;

a spoken language understanding unit that understands the recognized speech; and

a transcription generator that transcribes the understood speech to text and stores the transcribed text in the database,

wherein the automated web transcription service unit receives a request via a web page to display the transcribed text, retrieves transcribed text from the database, and displays the transcribed text to the requester using the web page.

18. The system of claim 17, wherein the communications network is one of a computer network, an Internet, and a telephone network.

19. The system of claim 17, wherein the automatic speech recognizer recognizes and the spoken language understanding unit understands system commands spoken by the user, wherein the system commands facilitate the user'"'"'s navigation through the transcribed text and correction of the transcribed text.

20. The system of claim 17, wherein the automated web transcription service unit prompts the requester to correct the displayed transcription, receives correction inputs for the displayed transcription from the requester, and corrects the transcription according to the received correction inputs.

21. The system of claim 17, wherein automated web transcription service unit prompts the requester to select one of printing the displayed transcript, sending the transcript to another party, and saving the displayed transcript to a memory.

22. The system of claim 17, wherein the transcription generator transcribes the text into a predefined document template.