REAL-TIME TRANSCRIPTION OF CONFERENCE CALLS

• US 20110112833A1
• Filed: 10/28/2010
• Published: 05/12/2011
• Est. Priority Date: 10/30/2009
• Status: Active Grant

• Current Assignee: ZipDX LLC
• Original Assignee: ZipDX LLC
• Inventors: Frankel, David P., Tarnoff, Noel
• Granted Patent: US 8,370,142 B2
• Time in Patent Office: Days
• US Class Current: 704/235
• CPC Class Codes: G06F 16/685 using automatically derived transcript of audio data, e.g. lyrics speech recognition G10L15/00
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 15/32 Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems

Abstract

Described herein are embodiments of systems, methods and computer program products for real-time transcription of conference calls that employ voice activity detection, audio snippet capture, and multiple transcription instances to deliver practical real-time or near real-time conference call transcription.

Claims

1. A system for transcribing a conference call among a plurality of participants using a plurality of audio connections;

the system comprising;

(a) a plurality of capture mechanisms, each of the plurality of capture mechanisms capturing a portion of audio associated with one of the plurality of audio connections;

(b) a plurality of speech recognition engines for converting audio to text

(c) a dispatcher for forwarding a captured portion of audio from one of the plurality of capture mechanisms to at least one of the plurality of speech recognition engines; and

(c) a combiner for re-assembling the text converted by the plurality of speech recognition engines from captured portions of audio from the plurality of capture mechanisms.

2. The system of claim 1, wherein each of the plurality of capture mechanisms comprises:

(i) a voice activity detector for detecting a voice snippet, wherein the length of the voice snippet is determined by detecting a break in audio of the associated audio connection; and

(ii) a means for capturing the voice snippet.

3. The system of claim 2, wherein the voice activity detector automatically adapts to maintain a target snippet length.

4. The system of claim 1, wherein each of the plurality of capture mechanisms generates an audio connection ID and sequence number associated with the captured portion of audio, and wherein the combiner re-assembles the text based on the audio connection IDs and sequence numbers generated by each of the plurality of capture mechanisms.

5. The system of claim 4, wherein the sequence number associated with each captured portion of audio comprises a sequence in time relative to other captured portions of audio.

6. The system of claim 1, wherein the plurality of speech recognition engines are implemented as multiple instances of a software algorithm.

7. The system of claim 1, wherein at least one of the plurality of speech recognition engines uses an automated speech to text algorithm.

8. The system of claim 1, wherein at least one of the plurality of speech recognition engines uses a human.

9. The system of claim 1, wherein the combiner function is accomplished by storing the converted text and any associated meta-data to a database, and further comprising an output mechanism which retrieves and displays the converted text and meta-data.

10. The system of claim 9, wherein the output mechanism displays the re-assembled text in near real-time.

11. The system of claim 9, wherein the output mechanism allows a user to hear one or more audio snippets associated with selected re-assembled text.

12. The system of claim 9, wherein the output mechanism provides access to the re-assembled text after the conference call has ended.

13. A method for transcribing a conference call among a plurality of participants using a plurality of audio connections;

the method comprising the steps of;

(a) capturing a plurality of portions of audio, each of the plurality of portions of audio being associated with at least one of the plurality of audio connections;

(b) forwarding each of the captured plurality of portions of audio to at least one of a plurality of speech recognition engines, whereby each of the plurality of speech recognition engines converts the audio to text; and

(c) re-assembling the text converted by the plurality of speech recognition engines.

14. The method of claim 13, wherein the capturing step comprises detecting a voice snippet, wherein the length of the voice snippet is determined by detecting a break in audio of the associated audio connection.

15. The method of claim 14, wherein the capturing step automatically adapts to maintain a target snippet length.

16. The method of claim 13, wherein the capturing step generates an audio connection ID and sequence number associated with each of the plurality of portions of audio, and wherein the re-assembling step re-assembles the text based on the audio connection IDs and sequence numbers generated by the capturing step.

17. The method of claim 16, wherein the sequence number associated with each captured portion of audio comprises a sequence in time relative to other captured portions of audio.

18. The method of claim 13, wherein the re-assembling step is accomplished by storing the converted text and any associated meta-data to a database, and further comprising the steps of retrieving and displaying the converted text and meta-data.

19. The method of claim 13, further comprising the step of displaying the re-assembled text in near real-time.

20. The method of claim 13, further comprising allowing a user to hear one or more audio snippets associated with selected re-assembled text.

21. The method of claim 13, further comprising the step of providing access to the re-assembled text after the conference call has ended.

22. A computer-readable medium with a computer program recorded thereon, the computer program comprising computer code instructions for implementing a method for transcribing a conference call among a plurality of participants using a plurality of audio connections;

the computer-readable medium comprising;

(a) a first computer code instruction portion for capturing a plurality of portions of audio, each of the plurality of portions of audio being associated with at least one of the plurality of audio connections;

(b) a second computer code instruction portion for forwarding each of the captured plurality of portions of audio to at least one of a plurality of speech recognition engines, whereby each of the plurality of speech recognition engines converts the audio to text; and

(c) a third computer code instruction portion for re-assembling the text converted by the plurality of speech recognition engines.