84 citations · 183 across the 32 of their papers we have counts for
Showing 2019Show all
2 papers · 1 filter
eess.AS2019★ 11 cited
Adversarial Attacks on GMM i-vector based Speaker Verification Systems
Xu Li, Jinghua Zhong, Xixin Wu +3
This work investigates the vulnerability of Gaussian Mixture Model (GMM) i-vector based speaker verification systems to adversarial attacks, and the transferability of adversarial…
eess.AS2019★ 13 cited
Maximizing Mutual Information for Tacotron
Peng Liu, Xixin Wu, Shiyin Kang +3
End-to-end speech synthesis methods already achieve close-to-human quality performance. However compared to HMM-based and NN-based frame-to-frame regression methods, they are prone…