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...
The modeling of systems mixing discrete and continuous behavior is a challenge for model builders. Sometimes, the continuous part is important, but small near the complex decision...
Marcelo Moretti Fioroni, Luiz Augusto Gago Franzes...
Fluidification constitutes a relaxation technique for studying discrete event systems through fluidified approximated models, thus avoiding the state explosion problem. Moreove...
Recently there has been interest in structured discriminative models for speech recognition. In these models sentence posteriors are directly modelled, given a set of features ext...