SuperLectures.com

LANGUAGE IDENTIFICATION USING A COMBINED ARTICULATORY PROSODY FRAMEWORK

Language Identification

Full Paper at IEEE Xplore

Přednášející: John Hansen, Autoři: Abhijeet Sangwan, Mahnoosh Mehrabani, John Hansen, The University of Texas at Dallas, United States

This study presents new advancements in our articulatory-based language identification (LID) system. Our LID system automatically identifies language-features (LFs) from a phonological features (PFs) based representation of speech. While our baseline system uses a static PF-representation for extracting LFs, the new system is based on a dynamic PF representation for feature extraction. Interestingly, the new LFs outperform our baseline system by 11.8% absolute in a difficult 5-way classification task of South Indian Languages. Additionally, we incorporate pitch and energy based features in our new system to leverage prosody in classification. In particular, we employ a Legendre polynomial based contour-estimation to capture shape parameters which are used in classification. Additionally, the fusion of PF and prosody-based LFs further improves the overall classification result by 16.5% absolute over the baseline system. Finally, the proposed articulatory language ID system is combined with a PPRLM (parallel phone recognition language model) system to obtain an overall classification accuracy of 86.6%.


  Přepis řeči

|

  Slajdy

Zvětšit slajd | Zobrazit všechny slajdy

0:00:16

  1. slajd

0:00:52

  2. slajd

0:01:37

  3. slajd

0:02:33

  4. slajd

0:05:39

  5. slajd

0:06:14

  6. slajd

0:07:12

  7. slajd

0:07:57

  8. slajd

0:08:22

  9. slajd

0:09:09

 10. slajd

0:09:25

 11. slajd

0:09:51

 12. slajd

0:10:29

 13. slajd

0:11:09

 14. slajd

0:11:56

 15. slajd

0:12:35

 16. slajd

0:13:12

 17. slajd

0:14:11

 18. slajd

0:14:57

 19. slajd

  Komentáře

Please sign in to post your comment!

  Informace o přednášce

Nahráno: 2011-05-24 10:55 - 11:15, Panorama
Přidáno: 16. 6. 2011 15:17
Počet zhlédnutí: 38
Rozlišení videa: 1024x576 px, 512x288 px
Délka videa: 0:19:23
Audio stopa: MP3 [6.55 MB], 0:19:23