For many practical applications of speech recognition systems, it is desirable to have an estimate of con dence for each hypothesized word, i.e. to have an estimate of which words of the output of the speech recognizer are likely to be correct and which are not reliable. We describe the development of the measure of con dence tagger JANKA, which is able to provide con dence information for the ...

In this paper, a two-stage texture segmentation approach is proposed where an initial segmentation map is obtained through unsupervised clustering of MRSAR features and is followed by self-supervised or bootstrapped classi cation of wavelet features. The selfsupervised stage is based on a segmentation con dence map, where the regions of \high con dence" and \low con dence" are identi ed on the ...

Distributed Shared Memory(DSM) has gained popular acceptance by combining the scalability and low cost of distributed system with the ease of use of single address space. Many new hardware DSM and software DSM systems were proposed in recent years. In general, benchmarking is widely used to demonstrate the performance advantages of new systems. However, the common method used to summarize the m...

Con tent: The suc cess ful in tro duc tion of ev i dence-based prac tice into psy chi a try re quires the ac qui si tion of new skills by cli ni cians. It is also im por tant that pol icy state ments that aim to be ev i dence-based, such as clin i cal prac tice guide lines, use rig or ous meth ods to syn the size the pri mary ev i dence and do not over look its lim i ta tions. One re sult of th...

In this paper we consider the problem of making inference on a structural parameter in instrumental variables regression when the instruments are only weakly correlated with the endogenous explanatory variables. Adopting a local-to-zero assumption as in Staiger and Stock (1994) on the coe cients of the instruments in the rst stage equation, the asymptotic distributions of various test statistic...

We give a novel method for performing statistically signi cant detection of speci ed object features which operates directly on X-ray (Gaussian) or radio-isotope (Poisson) tomographic projection data. The method is based on constructing an exact (1 )100% con dence region on the object derived by backprojecting a projection-domain con dence region into object space. The projection-domain con den...

In this paper, I devise a new way to construct con…dence sets for a parameter of interest in models comprised of a …nite number of moment inequalities. Many models of this form have appeared in the literature to date, particularly in the recent literature on partial identi…cation, but performing statistical inference in these settings is an area of ongoing research. Toward this end, I establish...

We construct bootstrap conndence intervals for smoothing spline and smoothing spline ANOVA estimates based on Gaussian data, and penalized likelihood smoothing spline estimates based on data from exponential families. Several variations of bootstrap conndence intervals are considered and compared. We nd that the commonly used bootstrap percentile intervals are inferior to the T intervals and to...

be independent multivariate observations , where the x i 's are known vectors, B; and are unknown, being a positive deenite matrix. The calibration problem deals with statistical inference concerning and the problem that we have addressed is the construction of conndence regions. When the same set of y i 's are used to construct conndence regions for a sequence of possibly diierent parameter ve...