SuperLectures.com

LOCALIZATION OF NON-LINGUISTIC EVENTS IN SPONTANEOUS SPEECH BY NON-NEGATIVE MATRIX FACTORIZATION AND LONG SHORT-TERM MEMORY

Audio/Visual Detection of Non-Linguistic Vocal Outbursts

Full Paper at IEEE Xplore

Presented by: Felix Weninger, Author(s): Felix Weninger, Björn Schuller, Martin Wöllmer, Gerhard Rigoll, Technische Universität München, Germany

Features generated by Non-Negative Matrix Factorization (NMF) have successfully been introduced into robust speech processing, including noise-robust speech recognition and detection of non-linguistic vocalizations. In this study, we introduce a novel tandem approach by integrating likelihood features derived from NMF into Bidirectional Long Short-Term Memory Recurrent Neural Networks (BLSTM-RNNs) in order to dynamically localize non-linguistic events, i.e., laughter, vocal, and non-vocal noise, in highly spontaneous speech. We compare our tandem architecture to a baseline conventional phoneme-HMM-based speech recognizer, and achieve a relative reduction of the frame error rate by 37.5% in the discrimination of speech and different non-speech segments.


  Speech Transcript

|

  Slides

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

0:00:16

  1. slide

0:00:29

  2. slide

0:00:46

  3. slide

0:02:25

  4. slide

0:03:21

  5. slide

0:04:26

  6. slide

0:07:45

  7. slide

0:09:36

  8. slide

0:10:37

  9. slide

0:11:55

 10. slide

0:12:20

 11. slide

0:13:28

 12. slide

0:14:31

 13. slide

0:15:28

 14. slide

0:16:50

 15. slide

  Comments

Please sign in to post your comment!

  Lecture Information

Recorded: 2011-05-25 14:45 - 15:05, Club D
Added: 19. 6. 2011 17:19
Number of views: 24
Video resolution: 1024x576 px, 512x288 px
Video length: 0:19:47
Audio track: MP3 [6.69 MB], 0:19:47