CTS Speaker Recognition Challenge


Contact Us

Please send questions to: sre_poc@nist.gov

For the CTS Challenge discussion please visit our Google Group. https://groups.google.com/a/list.nist.gov/forum/#!forum/cts-challenge


Summary

Following the success of the 2019 Conversational Telephone Speech (CTS) Speaker Recognition Challenge, which received 1347 submissions from 67 academic and industrial organizations, NIST is organizing a 2020 CTS Challenge, the next iteration of an ongoing series of speaker recognition evaluations conducted by NIST since 1996.

The basic task in the CTS Challenge is speaker detection, i.e., determining whether a specified target speaker is speaking during a given segment of speech. Similar to the 2019 CTS Challenge, the 2020 evaluation will feature a leaderboard-style challenge offering an open/unconstrained training condition, but using CTS recordings extracted from multiple data sources containing multilingual speech. In addition, unlike the 2019 CTS Challenge, no development set will be initially released.

For more information about the challenge please visit the announcement page or send questions to sre_poc@nist.gov.

August 7, 2020: Evaluation Plan Published

August 17, 2020 (tentative): CTS Challenge Registration Begins

August 17, 2020 (tentative): Data Available

Aug 2020-Jun 2021: System Output Due to NIST

June 2021: Workshop

Test set results will be released periodically


Leaderboard will be available soon.