LOGIN TO YOUR ACCOUNT

Username
Password
Remember Me
Or use your Academic/Social account:

CREATE AN ACCOUNT

Or use your Academic/Social account:

Congratulations!

You have just completed your registration at OpenAire.

Before you can login to the site, you will need to activate your account. An e-mail will be sent to you with the proper instructions.

Important!

Please note that this site is currently undergoing Beta testing.
Any new content you create is not guaranteed to be present to the final version of the site upon release.

Thank you for your patience,
OpenAire Dev Team.

Close This Message

CREATE AN ACCOUNT

Name:
Username:
Password:
Verify Password:
E-mail:
Verify E-mail:
*All Fields Are Required.
Please Verify You Are Human:
fbtwitterlinkedinvimeoflicker grey 14rssslideshare1
Ng, W.; Nicolao, M.; Saz, O.; Hasan, M.; Chettri, B.; Doulaty, M.; Lee, T.; Hain, T. (2016)
Publisher: ISCA
Languages: English
Types: Other
Subjects:
The Speech and Hearing Research Group of the University of\ud Sheffield submitted a fusion language recognition system to\ud NIST LRE 2015. It combines three language classifiers. Two\ud are acoustic-based, which use i–vectors and a tandem DNN language\ud recogniser respectively. The third classifier is a phonotactic\ud language recogniser. Two sets of training data with duration\ud of approximately 170 and 300 hours were composed for\ud LR training. Using the larger set of training data, the primary\ud Sheffield LR system gives 32.44 min DCF on the official LR\ud 2015 eval data. A post-evaluation system enhancement was carried\ud out where i–vectors were extracted from the bottleneck features\ud of an English DNN. The min DCF was reduced to 29.20.
  • No references.
  • No related research data.
  • No similar publications.

Share - Bookmark

Cite this article