This paper presents a way to perform speaker adaptation for automatic speech recognition using the stream weights in a multi-stream setup, which included acoustic models for “Articulatory Features” such as ROUNDED or VOICED. We present supervised speaker adaptation experiments on a spontaneous speech task and compare the above stream-based approach to conventional approaches, in which the model...

In this paper we show that C-k(X), the set of continuous, realvalued functions on X topologized by the pointwise convergence topology, can have arbitrarily high Borel or projective complexity in Rx even when X is a countable regular space with a unique limit point. In addition we show how to construct countable regular spaces X for which C-n(X) lies nowhere in the projective hierarchy of the co...

According to ‘Excluders’, descriptive uncertainty – but not normative matters what we ought do. Recently, several authors have argued that those wishing treat differently from face a dependence problem because one's can depend on uncertainty. The aim of this paper is determine whether the phenomenon poses decisive for Excluders. I argue existing arguments fail show this, and that, while stronge...

This paper summarizes the results of a descriptive meta-analysis on existing academic research in IS offshoring from 1996 to 2006. It identifies relevant research, categorizes it, and suggests future research directions. The results show that IS offshoring represents a new research area with most research being published during 2003 to 2006. Non-theory based, descriptive research designs domina...

State complexity is a descriptive complexity measure for regular languages. We investigate the problems related to the state complexity of regular languages and their operations. In particular, we compare the state complexity results on regular languages with those on nite languages.

In this paper we present logical characterizations of two preorders, within the framework of Hennessy-Milner Logics. The two preorders (loosely termed bisimulation-based efficiency preorders) are on processes represented as labelled transition systems. The characterizations are particularly interesting as they explore preorders lying between strong and weak bisimilarity, guided by a principle o...

A new distance function dist (A,B) for fuzzy sets A and B is introduced. It is based on the descriptive complexity, i.e., the number of bits (on average) that are needed to describe an element in the symmetric difference of the two sets. The distance gives the amount of additional information needed to describe any one of the two sets given the other. We prove its mathematical properties and pe...

Syntactic constraints in Koskenniemi's Finite-State Intersection Grammar (FSIG) are logically less complex than their formalism (Koskenniemi et al., 1992) would suggest: It turns out that although the constraints in Voutilainen's (1994) FSIG description of English make use of several extensions to regular expressions, the description as a whole reduces to a finite combination of union, compleme...