SuperLectures.com

UNSUPERVISED ACOUSTIC SUB-WORD UNIT DETECTION FOR QUERY-BY-EXAMPLE SPOKEN TERM DETECTION

Full Paper at IEEE Xplore

Speaker Diarization

Presented by: Marijn Huijbregts, Author(s): Marijn Huijbregts, Mitchell McLaren, David van Leeuwen, Radboud University Nijmegen, Netherlands

In this paper we present a method for automatically generating acoustic sub-word units that can substitute conventional phone models in a query-by-example spoken term detection system. We generate the sub-word units with a modified version of our speaker diarization system. Given a speech recording, the original diarization system generates a set of speaker models in an unsupervised manner without the need for training or development data. Modifying the diarization system to process the speech of a single speaker and decreasing the minimum segment duration constraint allows us to detect speaker-dependent sub-word units. For the task of query-by-example spoken term detection, we show that the proposed system performs well on both broadcast and non-broadcast recordings, unlike a conventional phone-based system trained solely on broadcast data. A mean average precision of 0.28 and 0.38 was obtained for experiments on broadcast news and on a set of war veteran interviews, respectively.


  Speech Transcript

|

  Slides

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

0:00:22

  1. slide

0:00:40

  2. slide

0:01:55

  3. slide

0:02:46

  4. slide

0:03:35

  5. slide

0:05:06

  6. slide

0:06:29

  7. slide

0:07:08

  8. slide

0:08:24

  9. slide

0:09:16

 10. slide

  Comments

Please sign in to post your comment!

  Lecture Information

Recorded: 2011-05-24 15:25 - 15:45, Panorama
Added: 15. 6. 2011 13:40
Number of views: 17
Video resolution: 1024x576 px, 512x288 px
Video length: 0:11:36
Audio track: MP3 [3.87 MB], 0:11:36