Abstract--As a replacement for the fast-fading GloballySynchronous model, we have defined a flexible design style called GRLS, for Globally-Ratiochronous, Locally-Synchronous, whic...
This paper proposes a technique for improving tone correctness in Thai speech synthesis based on an average voice model trained with nonprofessional speech corpus. The proposed te...
With an explosion in the proliferation of user-generated content in communities, information overload is increasing and quality of readily available online content is deterioratin...
In this paper, we propose a new variant of Accepting Networks of Evolutionary Processors, in which the operations can be applied only arbitrarily to the words, while the filters ...
Abstract. The prediction of diagnosis codes is typically based on freetext entries in clinical documents. Previous attempts to tackle this problem range from strictly rule-based sy...