This paper introduces a new form of observation distributions for hidden Markov models (HMMs), combining subvector quantization and mixtures of discrete distrib utions. Despite w...
Vassilios Digalakis, S. Tsakalidis, Costas Harizak...
Conversational speech exhibits considerable pronunciation variability, which has been shown to have a detrimental effect on the accuracy of automatic speech recognition. There hav...
Murat Saraclar, Harriet J. Nock, Sanjeev Khudanpur
We report work on the first component of a two stage speech recognition architecture based on phonological features rather than phones. The paper reports experiments on three phon...
This paper outlines ProSynth, an approach to speech synthesis which takes a rich linguistic structure as central to the generation of natural-sounding speech. We start from the as...
Richard Ogden, Sarah Hawkins, Jill House, Mark Huc...
Abstract. We investigate the possibility of giving a computational interpretation of an involutive negation in classical natural deduction. We first show why this cannot be simply ...
We introduce basic concepts from object-oriented programming into dependent type theory based on the idea of modelling objects as interactive programs. We consider methods, interf...
In the ambient logic of classical second order propositional calculus, we solve the specification problem for a family of excluded middle like tautologies. These are shown to be r...