
TOEFL iBT® Test Security: Voice Biometrics
TOEFL iBT® Test Security: Voice Biometrics Every fingerprint is different, just like every voice is. This is why ETS makes use of voice recordings from the TOEFL iBT® test’s speaking section to help make sure that the takers of the test are not misrepresenging themselves.
These voice recordings are then compared by making use of voice biometrics, a technology which uses techniques for statistical pattern-making, as well as advanced voice classification methods and inputs from a number of systems to compare samples of speech from those who take the test.
There are 3 ways in which voice biometrics is used to identify potential misconduct in testing.
- For Repeat Test Takers – So that voice prints can be compared with speech samples from the same test taker using a number of test administrations. If the voiceprints are different, then that is the time to investigate.
- For those who can potentially impersonate within a Test Center – So that voiceprints can be compared with speech samples for all test takers at a specific test center. If there are any voiceprints that would match, then that is the time to investigate.
- For those who are known to impersonate within a Group – So that voiceprints can be compared with speech samples from known imposters for all test takers within a suspect group. If there are any voiceprints that would match, then that is the time to investigate.
It was in 2012 when voice biometrics was introduced for the TOEFL® test security investigations. It is now being used on all test takers all over the world before the release of scores.
Please visit https://www.ets.org/toefl/institutions/about/security/ for more information regarding the TOEFL test security.