50 citations · 95 across the 7 of their papers we have counts for
Showing 2017 · eess.ASShow all
2 papers · 2 filters
eess.AS2017★ 50 cited
Attention-Based Models for Text-Dependent Speaker Verification
F A Rezaur Rahman Chowdhury, Quan Wang, Ignacio Lopez Moreno +1
Attention-based models have recently shown great performance on a range of tasks, such as speech recognition, machine translation, and image captioning due to their ability to summ…
eess.AS2017★ 29 cited
Generalized End-to-End Loss for Speaker Verification
Li Wan, Quan Wang, Alan Papir +1
In this paper, we propose a new loss function called generalized end-to-end (GE2E) loss, which makes the training of speaker verification models more efficient than our previous tu…