SuperLectures.com

CROVER: IMPROVING ROVER USING AUTOMATIC ERROR DETECTION

Full Paper at IEEE Xplore

Industrial Technology for Speech Processing Applications

Presented by: Kacem Abida, Author(s): Kacem Abida, Fakhri Karray, University of Waterloo, Canada; Wafa Abida, Vestec, Canada

Recognizer Output Voting Error Reduction (ROVER), is a well-known procedure for decoders’ combination aiming at reducing the Word Error Rate (WER) in transcription applications. However, it appears that this technique has reached a plateau in terms of performance. This paper presents a novel approach, cROVER, to boosting the current ROVER performance, by relying on a contextual analysis to trim erroneous words. Experiments have proven that it is possible to outperform ROVER, despite the high false positive rate of the error detection technique.

  Speech Transcript

  Slides

Enlarge the slide | Show all slides in a pop-up window

0:00:16

  1. slide

0:01:02

  2. slide

0:01:48

  3. slide

0:02:28

  4. slide

0:02:54

  5. slide

0:03:37

  6. slide

0:04:05

  7. slide

0:04:11

  8. slide

0:05:12

  9. slide

0:06:05

 10. slide

0:06:48

 11. slide

0:07:35

 12. slide

0:08:16

 13. slide

0:08:35

 14. slide

0:09:17

 15. slide

0:09:49

 16. slide

0:10:35

 17. slide

0:10:53

 18. slide

0:11:57

 19. slide

0:12:36

 20. slide

0:14:13

 21. slide

  Comments

Please sign in to post your comment!

  Lecture Information