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 …

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 …

Automatic Speech Recognition (ASR) has historically been a driving force behind many
machine learning (ML) techniques, including the ubiquitously used hidden Markov model, …

… 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 …

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 …

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…

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) …

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 …

Recently, the hybrid deep neural network (DNN)-hidden Markov model (HMM) has been shown
to significantly improve speech recognition performance over the conventional Gaussian …

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 …