This report develops and studies a new family of NSE-regularizations, Tikhonov Leray Regularization with Time Relaxation Models. This new family of turbulence models is based on a...
It is generally known that a well-designed excitation produces high quality signals in hidden Markov model (HMM)-based speech synthesis systems. This paper proposes a novel techni...
June Sig Sung, Doo Hwa Hong, Kyung Hwan Oh, Nam So...
Neural networks are a useful alternative to Gaussian mixture models for acoustic modeling; however, training multilayer networks involves a difficult, nonconvex optimization that...
We present an unsupervised model for joint phrase alignment and extraction using nonparametric Bayesian methods and inversion transduction grammars (ITGs). The key contribution is...
Graham Neubig, Taro Watanabe, Eiichiro Sumita, Shi...
We introduce a generative probabilistic document model based on latent Dirichlet allocation (LDA), to deal with textual errors in the document collection. Our model is inspired by...