Annotation of large multilingual corpora remains a challenge to the data-driven approach to speech research, especially for under-resourced languages. This paper presents crosslan...
We derive an efficient learning algorithm for model-based source separation for use on single channel speech mixtures where the precise source characteristics are not known a pri...
Predictive state representation (PSR) models for controlled dynamical systems have recently been proposed as an alternative to traditional models such as partially observable Mark...
Michael R. James, Satinder P. Singh, Michael L. Li...
Abstract. Score functions induced by generative models extract fixeddimensions feature vectors from different-length data observations by subsuming the process of data generation, ...
Alessandro Perina, Marco Cristani, Umberto Castell...
We present two machine learning approaches to information extraction from semi-structured documents that can be used if no annotated training data are available, but there does ex...