In the last few years we have been experimenting with an automatic phonetic segmentation and labeling system based on a modified HMM phonetic recognizer followed by a local phonetic boundary refinement system. During this period we have used different approaches for the local refinement, including fuzzy rules and neural networks. In this paper we present a unified framework for the local refine...

The main goal of this paper is to compare the performance which can be achieved by five different approaches analyzing their applications’ potentiality on real world paradigms. We compare the performance obtained with (1) Multi-network RBF/LVQ structure (2) Discrete Hidden Markov Models (HMM) (3) Hybrid HMM/MLP system using a Multi LayerPerceptron (MLP) to estimate the HMM emission probabilitie...

In this note, we define the concepts of admissible relation and admissible partition for an arbitrary BL-general fuzzy automaton.In particular, a connection between the admissible partition and the quotient BL-general fuzzy automaton is presented.It is shown that if we use the maximal admissible partition, then we obtain a quotient BL-general fuzzy automaton and this quotient is minimal. Finall...

the objective of this paper is to deal with the fuzzy conic program- ming problems. the aim here is to derive weak and strong duality theorems for a general fuzzy conic programming. toward this end, the convexity-like concept of fuzzy mappings is introduced and then a speci c ordering cone is established based on the parameterized representation of fuzzy numbers. un- der this setting, duality t...

The present paper is an attempt to study the minimal BL-general fuzzy automata which realizes the given fuzzy behavior. Of two methods applied for construction of such automaton presented here, one has been based on Myhill-Nerode's theory while the other has been based on derivatives of the given fuzzy behavior. Meanwhile, the categories of BL-general fuzzy automata and fuzzy behavior, along wi...

Humans comprehend the meanings and relations of discourses heavily relying on their semantic memory that encodes general knowledge about concepts and facts. Inspired by this, we propose a neural recognizer for implicit discourse relation analysis, which builds upon a semantic memory that stores knowledge in a distributed fashion. We refer to this recognizer as SeMDER. Starting from word embeddi...