29 citations · 39 across the 2 of their papers we have counts for
2 papers
cs.LG2019★ 10 cited
Signal Combination for Language Identification
Shengye Wang, Li Wan, Yang Yu +1
Google's multilingual speech recognition system combines low-level acoustic signals with language-specific recognizer signals to better predict the language of an utterance. This p…
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…