SuperLectures.com

SPEAKER VERIFICATION BY INEXPERIENCED AND EXPERIENCED LISTENERS VS. SPEAKER VERIFICATION SYSTEM

Human Assisted Speaker Recognition

Full Paper at IEEE Xplore

Přednášející: Juliette Kahn, Autoři: Juliette Kahn, University of Avignon, France; Nicolas Audibert, Laboratoire de Phonétique et Phonologie, France; Solange Rossato, University of Grenoble, France; Jean-François Bonastre, University of Avignon, France

This paper describes the participation of the LIA in the Human Assisted Speaker Recognition (HASR) task of the NIST-SRE 2010 evaluation campaign and its extension to a larger number of listeners.The human performance in such unfavorable conditions is analyzed in relation to the decision of a speaker recognition automatic system. Results of the perception test showed an important inter-trial variability (from 3% to 90% of correct answers for non-target trials) whereas there was no significant difference between the experienced and inexperienced listeners. Some complementarity between speaker verification system and human decisions was also found.


  Přepis řeči

|

  Slajdy

Zvětšit slajd | Zobrazit všechny slajdy

0:00:16

  1. slajd

0:00:45

  2. slajd

0:01:14

  3. slajd

0:02:04

  4. slajd

0:03:16

  5. slajd

0:03:48

  6. slajd

0:04:56

  7. slajd

0:06:46

     7. slajd

0:06:58

  8. slajd

0:07:16

  9. slajd

0:08:53

 10. slajd

0:10:35

 11. slajd

0:11:06

 12. slajd

0:11:50

 13. slajd

0:13:05

 14. slajd

0:13:47

 15. slajd

0:14:06

 16. slajd

0:15:04

 17. slajd

  Komentáře

Please sign in to post your comment!

  Informace o přednášce

Nahráno: 2011-05-26 15:05 - 15:25, Club D
Přidáno: 19. 6. 2011 00:31
Počet zhlédnutí: 24
Rozlišení videa: 1024x576 px, 512x288 px
Délka videa: 0:17:22
Audio stopa: MP3 [5.85 MB], 0:17:22