D
Dong Yu
Researcher at Tencent
Publications - 389
Citations - 45733
Dong Yu is an academic researcher from Tencent. The author has contributed to research in topics: Artificial neural network & Word error rate. The author has an hindex of 72, co-authored 339 publications receiving 39098 citations. Previous affiliations of Dong Yu include Peking University & Microsoft.
Papers
More filters
Journal ArticleDOI
Using continuous features in the maximum entropy model
Dong Yu,Li Deng,Alex Acero +2 more
TL;DR: A spline-based solution to the MaxEnt model with non-linear continuous weighting functions is proposed and it is illustrated that the optimization problem can be converted into a standard log-linear model at a higher-dimensional space.
Deep Learning for Signal and Information Processing
TL;DR: Deep learning has been extensively studied in the literature up to March, 2013 as discussed by the authors, covering practical aspects in the fast development of deep learning research during the interim year, including the use of multiple layers of nonlinear transformations to derive features from the sensory signals.
Posted Content
Multi-talker Speech Separation with Utterance-level Permutation Invariant Training of Deep Recurrent Neural Networks
TL;DR: In this article, the utterance-level permutation invariant training (uPIT) is proposed to separate multi-talker mixed speech without any prior knowledge of signal duration, number of speakers, speaker identity or gender.
Proceedings ArticleDOI
Audio-Visual Recognition of Overlapped Speech for the LRS2 Dataset
Jianwei Yu,Shi-Xiong Zhang,Jian Wu,Shahram Ghorbani,Bo Wu,Shiyin Kang,Shansong Liu,Xunying Liu,Helen Meng,Dong Yu +9 more
TL;DR: Experiments suggest the proposed AVSR system outperformed the audio only baseline LF-MMI DNN system by up to 29.98% absolute in word error rate (WER) reduction, and produced recognition performance comparable to a more complex pipelined system.
Journal ArticleDOI
Audio-Visual Speech Separation and Dereverberation With a Two-Stage Multimodal Network
TL;DR: This study addresses joint speech separation and dereverberation, which aims to separate target speech from background noise, interfering speech and room reverberation, and proposes a novel multimodal network that exploits both audio and visual signals.