Randomised techniques allow very big language models to be represented succinctly. However, being batch-based they are unsuitable for modelling an unbounded stream of language whi...
Recent studies have shown the potential benefits of leveraging resources for resource-rich languages to build tools for similar, but resource-poor languages. We examine what const...
While subjectivity related research in other languages has increased, most of the work focuses on single languages. This paper explores the integration of features originating fro...
This paper presents a new approach to language model construction, learning a language model not from text, but directly from continuous speech. A phoneme lattice is created using...
Graham Neubig, Masato Mimura, Shinsuke Mori, Tatsu...
Traditional n-gram language models are widely used in state-of-the-art large vocabulary speech recognition systems. This simple model suffers from some limitations, such as overfi...