WordNet is extensively used as a major lexical resource in NLP. However, its quality is far from perfect, and this alters the results of applications using it. We propose here to complement previous efforts for “cleaning up” the top-level of its taxonomy with semi-automatic methods based on the detection of errors at the lower levels. The methods we propose test the coherence of two sources of ...

Accent classification technologies directly influence the performance of the state-of-the-art speech recognition system. In this paper, we propose a novel scheme for accent classification, which uses decision-templates (DT) ensemble algorithm to combine base classifiers built on acoustic feature subsets. Different feature subsets can provide sufficient diversity among base classifiers, which is...

Ensemble methods are state of the art for many NLP tasks. Recent work by Banko and Brill (2001) suggests that this would not necessarily be true if very large training corpora were available. However, their results are limited by the simplicity of their evaluation task and individual classifiers. Our work explores ensemble efficacy for the more complex task of automatic thesaurus extraction on ...

We have proposed an automatic speech summarization approach that extracts words from transcription results obtained by automatic speech recognition (ASR) systems. To numerically evaluate this approach, the automatic summarization results are compared with manual summarization generated by human subjects through word extraction. We have proposed three metrics, weighted word precision, word strin...

Building a voice model means to capture the characteristics of a speaker’s voice in a data structure. This data structure is then used by a computer for further processing, such as comparison with other voices. Voice modeling is a vital step in the process of automatic speaker recognition that itself is the foundation of several applied technologies: (a) biometric authentication, (b) speech rec...

Computational Methods for Automatic Image Registration by Marco Zuliani Image registration is the process of establishing correspondences between two or more images taken at different times, from different viewpoints, under different lighting conditions, and/or by different sensors, and aligning them with respect to a coordinate system that is coherent with the three dimensional structure of th...

The SHUNYATA program constructs proof methods by analyzing proofs of simple theorems in mathematical theories such as group theory and uses these methods to form prooh of new theorems in the same or in other theories. Such methods are capable of generating proo& of theorems whose complexity represents the state of the art in automated theorem proving. They are composed of elementary functions s...

This thesis presents work in the area of automatic speech recognition (ASR). The thesis focuses on methods for increasing the efficiency of speech recognition systems and on techniques for efficient representation of different types of knowledge in the decoding process. In this work, several decoding algorithms and recognition systems have been developed, aimed at various recognition tasks. The...

The problem presented in this thesis is to specify and implement a solution which could be used to automatically classify previously completed calls to a call routing service, and furthermore, to specify and implement a solution which could be used to automatically predict the outcome of calls to this service “on-line”, i.e. as they happen. The specific service on which to investigate this prob...

The process of creating working software from source code and other components (like libraries, database files, etc.) is called “software build”. Apart from linking and compiling, it can include other steps like automated testing, static code analysis, documentation generation, deployment and other. All that steps can be automated using a build description of some sort (e.g. script). This artic...