In this paper the research have tried to show the pattern variations of sound units in Amharic language for multiple pronunciation model. This are variation of sound units at lexical level due to dialects. After that an attempt to build a pronunciation dictionary for Automatic Speech Recognition (ASR).At last comments and recommendations are included. Amharic is an official language of Ethiopia...

IDA (Intelligent Document Analysis) is a modular software system, which assists to automate paper document entry. IDA consists of the following components: layout analysis, preclassification, OCR interface, fuzzy string matching, text categorization, lexical, syntactical and semantic analysis. The system has been applied to a variety of tasks: Presorting of forms, reports and letters, index ext...

Almost forty years ago, Connes, Feldman and Weiss proved that for measurable equivalence relations the notions of amenability hyperfiniteness coincide. In this paper we define uniform version graphed bounded vertex degrees prove these two coincide as well. Roughly speaking, a measured graph $\mathcal {G}$ is uniformly hyperfinite if any ${\varepsilon }>0$ there exists $K\geq 1$ such not only {G...

It is well-known that a Kleinian group is amenable if and only if it is elementary. We establish an analogous property for equivalence relations and foliations with Gromov hyperbolic leaves: they are amenable if and only if they are elementary in the sense that one can assign (in a measurable way) to any leaf a finite subset of its hyperbolic boundary (as in the group case, such subsets cannot ...

LogicWeb has traditionally lacked devices for dealing with intractable queries. We address this limitation by adopting length-bounded inference, a form of approximate reasoning. A length-bounded inference is of the form pv(P, G, n) which is a success if a query G can be proved from the web page P within n proof steps. It thus makes LogicWeb decidable and more tractable. During the process, we p...

We study learning in Bayesian games (or games with differential information) with an arbitrary number of bounded rational players, i.e., players who choose approximate best response strategies [approximate Bayesian Nash Equilibrium (BNE) strategies] and who also are allowed to be completely irrational in some states of the world. We show that bounded rational players by repetition can reach a l...

Bounded Max-Sum is a message-passing algorithm for solving Distributed Constraint Optimization Problems able to compute solutions with a guaranteed approximation ratio. Although its approximate solutions were empirically proved to be within a small percentage of the optimal solution on low and moderately dense problems, in this paper we show that its theoretical approximation ratio is overestim...