User profiles for Li Deng
Li DengChief AI Officer, Citadel (former) Verified email at ieee.org Cited by 85074 |
Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups
Most current speech recognition systems use hidden Markov models (HMMs) to deal with the
temporal variability of speech and Gaussian mixture models (GMMs) to determine how well …
temporal variability of speech and Gaussian mixture models (GMMs) to determine how well …
Recent advances in deep learning for speech research at Microsoft
Deep learning is becoming a mainstream technology for speech recognition at industrial
scale. In this paper, we provide an overview of the work by Microsoft speech researchers since …
scale. In this paper, we provide an overview of the work by Microsoft speech researchers since …
Machine learning paradigms for speech recognition: An overview
L Deng, X Li - IEEE Transactions on Audio, Speech, and …, 2013 - ieeexplore.ieee.org
Automatic Speech Recognition (ASR) has historically been a driving force behind many
machine learning (ML) techniques, including the ubiquitously used hidden Markov model, …
machine learning (ML) techniques, including the ubiquitously used hidden Markov model, …
The mnist database of handwritten digit images for machine learning research [best of the web]
L Deng - IEEE signal processing magazine, 2012 - ieeexplore.ieee.org
… Li Deng … Li Deng (deng@microso ft.com) is a principal researcher at Microsoft
Research, Redmond, Washington. … Deng and D. Yu, “Deep convex network: A scalable …
Research, Redmond, Washington. … Deng and D. Yu, “Deep convex network: A scalable …
Deep learning: methods and applications
This monograph provides an overview of general deep learning methodology and its
applications to a variety of signal and information processing tasks. The application areas are …
applications to a variety of signal and information processing tasks. The application areas are …
Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition
We propose a novel context-dependent (CD) model for large-vocabulary speech recognition
(LVSR) that leverages recent advances in using deep belief networks for phone recognition…
(LVSR) that leverages recent advances in using deep belief networks for phone recognition…
Embedding entities and relations for learning and inference in knowledge bases
We consider learning representations of entities and relations in KBs using the neural-embedding
approach. We show that most existing models, including NTN (Socher et al., 2013) …
approach. We show that most existing models, including NTN (Socher et al., 2013) …
TAK1 is a ubiquitin-dependent kinase of MKK and IKK
TRAF6 is a signal transducer that activates IκB kinase (IKK) and Jun amino-terminal kinase (JNK)
in response to pro-inflammatory mediators such as interleukin-1 (IL-1) and …
in response to pro-inflammatory mediators such as interleukin-1 (IL-1) and …
Convolutional neural networks for speech recognition
Recently, the hybrid deep neural network (DNN)-hidden Markov model (HMM) has been shown
to significantly improve speech recognition performance over the conventional Gaussian …
to significantly improve speech recognition performance over the conventional Gaussian …
[HTML][HTML] Activation of the IκB kinase complex by TRAF6 requires a dimeric ubiquitin-conjugating enzyme complex and a unique polyubiquitin chain
L Deng, C Wang, E Spencer, L Yang, A Braun, J You… - Cell, 2000 - cell.com
TRAF6 is a signal transducer in the NF-κB pathway that activates IκB kinase (IKK) in response
to proinflammatory cytokines. We have purified a heterodimeric protein complex that links …
to proinflammatory cytokines. We have purified a heterodimeric protein complex that links …