ISCA Archive Interspeech 2015
ISCA Archive Interspeech 2015

NIST language recognition evaluation — plans for 2015

Alvin F. Martin, Craig S. Greenberg, John M. Howard, Désiré Bansé, George R. Doddington, Jaime Hernández-Cordero, Lisa P. Mason

We discuss two NIST coordinated evaluations of automatic language recognition technology planned for calendar year 2015 along with possible additional plans for the future. The first is the Language Recognition i-Vector Machine Learning Challenge, largely modeled on the 2013-2014 Speaker Recognition i-Vector Machine Learning Challenge. This online challenge, emphasizing the language identification task, is particularly intended to attract interest from the machine learning community and others beyond the audio processing community. The second is the next NIST Language Recognition Evaluation, following in the series of NIST evaluations previously held in 1996, 2003, 2005, 2007, 2009, and 2011. This evaluation will emphasize language detection in the context of closely related language pairs and is open to all interested in participating.