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
Recent progresses in deep learning based acoustic models
TL;DR: In this paper, the authors summarize recent progress made in deep learning based acoustic models and the motivation and insights behind the surveyed techniques, and further illustrate robustness issues in speech recognition systems, and discuss acoustic model adaptation, speech enhancement and separation.
Journal ArticleDOI
Tensor Deep Stacking Networks
Brian Hutchinson,Li Deng,Dong Yu +2 more
TL;DR: A sufficient depth of the T-DSN, a symmetry in the two hidden layers structure in each T- DSN block, the model parameter learning algorithm, and a softmax layer on top of T-DsN are shown to have all contributed to the low error rates observed in the experiments for all three tasks.
Journal ArticleDOI
Modeling Spectral Envelopes Using Restricted Boltzmann Machines and Deep Belief Networks for Statistical Parametric Speech Synthesis
Zhen-Hua Ling,Li Deng,Dong Yu +2 more
TL;DR: The proposed spectral modeling method can significantly alleviate the over-smoothing effect and improve the naturalness of the conventional HMM-based speech synthesis system using mel-cepstra.
Proceedings ArticleDOI
Improving wideband speech recognition using mixed-bandwidth training data in CD-DNN-HMM
TL;DR: This paper presents the strategy of using mixed-bandwidth training data to improve wideband speech recognition accuracy in the CD-DNN-HMM framework, and shows that DNNs provide the flexibility of using arbitrary features.
Proceedings ArticleDOI
Recurrent conditional random field for language understanding
TL;DR: This paper shows that the performance of an RNN tagger can be significantly improved by incorporating elements of the CRF model; specifically, the explicit modeling of output-label dependencies with transition features, its global sequence-level objective function, and offline decoding.