—We present TanGeoMS, a tangible geospatial modeling visualization system that couples a laser scanner, projector, and a flexible physical three-dimensional model with a standar...
In this paper we investigate random forest based language model adaptation. Large amounts of out-of-domain data are used to grow the decision trees while very small amounts of in-...
Speech recognition of inflectional and morphologically rich languages like Czech is currently quite a challenging task, because simple n-gram techniques are unable to capture impo...
This paper presents the use of online Variational Bayes method for online Voice Activity Detection (VAD) in an unsupervised context. In conventional VAD, the final step often rel...
David Cournapeau, Shinji Watanabe, Atsushi Nakamur...
We propose to improve speech recognition performance on speaker-independent, mixed language speech by asymmetric acoustic modeling. Mixed language is either inter-sentential code ...