Deep CNN based feature extractor for text-prompted speaker recognition

no code implementations • 13 Mar 2018 • Sergey Novoselov, Oleg Kudashev, Vadim Schemelinin, Ivan Kremnev, Galina Lavrentyeva

By using multitask learning scheme to train the high-level feature extractor we were able to surpass the classic baseline systems in terms of quality and achieved impressive results for such a novice approach, getting 2. 85% EER on the RSR2015 evaluation set.

Speaker Recognition Speaker Verification