We present MARS (Multilingual Automatic tRanslation System), a research prototype speech-to-speech translation system. MARS is aimed at two-way conversational spoken language trans...
Yuqing Gao, Bowen Zhou, Zijian Diao, Jeffrey S. So...
The Context Recognition Network (CRN) Toolbox permits fast implementation of activity and context recognition systems. It utilizes parameterizable and reusable software components...
Defining suitable features for environmental sounds is an important problem in an automatic acoustic scene recognition system. As with most pattern recognition problems, extracti...
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 addresses the problem of discriminative training of language models that does not require any transcribed acoustic data. We propose to minimize the conditional entropy ...