S
Shuai Nie
Researcher at Chinese Academy of Sciences
Publications - 32
Citations - 482
Shuai Nie is an academic researcher from Chinese Academy of Sciences. The author has contributed to research in topics: Speech enhancement & Computer science. The author has an hindex of 8, co-authored 26 publications receiving 244 citations.
Papers
More filters
Proceedings ArticleDOI
Sequence-To-Sequence Domain Adaptation Network for Robust Text Image Recognition
TL;DR: Extensive text recognition experiments show the SSDAN could efficiently transfer sequence knowledge and validate the promising power of the proposed model towards real world applications in various recognition scenarios, including the natural scene text, handwritten text and even mathematical expression recognition.
Proceedings ArticleDOI
ADD 2022: the first Audio Deep Synthesis Detection Challenge
Jiangyan Yi,Ruibo Fu,Jianhua Tao,Shuai Nie,Haoxin Ma,Chenglong Wang,Zhengkun Tian,Ye Bai,Cunhang Fan,Shangwu Liang,Shiming Wang,Shuai Zhang,Xin Yan,Le Xu,Zhengqi Wen,Haizhou Li +15 more
TL;DR: The datasets, evaluation metrics, and protocols of the first Audio Deep synthesis Detection challenge (ADD) 2022 are described and major findings that reflect the recent advances in audio deepfake detection tasks are reported.
Journal ArticleDOI
Deep Learning Based Speech Separation via NMF-Style Reconstructions
TL;DR: DNN directly optimizes an actual separation objective in the authors' system, so that the accumulated errors could be alleviated and the proposed models are competitive with the previous methods.
Journal ArticleDOI
A pairwise algorithm using the deep stacking network for speech separation and pitch estimation
TL;DR: A supervised learning architecture based on the deep stacking network for stacking simple processing modules to build deep architectures that results in both a high quality estimated binary mask and accurate pitch estimation and outperforms recent systems in its generalization ability.
Proceedings ArticleDOI
Jointly Adversarial Enhancement Training for Robust End-to-End Speech Recognition.
TL;DR: This paper proposes a jointly adversarial enhancement training to boost robustness of end-to-end systems and achieves the relative error rate reduction of 4.6% over the multi-condition training.