In this paper, we describe a system and architecture for building and remotely accessing shared context between a user and a computer. The system is designed to allow a user to browse web pages on a personal computer and then remotely make queries about information seen on the web pages using a telephone-based voice user interface. Keywords Shared context, voice user interfaces, information access, telephone-based user interfaces, software architecture, VoiceXML. 1.

We describe the design and implementation of the dialogue management module in a voice operated car-driver information system. The literature on designing 'good' user interfaces involving naturM language dialogue in general and speech in particular is abundant with use- ful guidelines for actual development. We have tried to summarize these guidelines in 7 'meta- guidelines', or commandments. Even though state-of-the-art Speech Recognition modules perform well, speech recognition errors cannot be precluded. For'the current application, the fact that the car is an acoustically hostile environment is an extra complication. This means that special attention should be paid to effective methods to compensate for speech recognition errors. Moreover, this should be done in a way which is not disturbing for the driver. In this paper, we show how these con- straints influence the design and subsequent implementation of the Dialogue Manager mod- ule, and how the additional requirements fit in with the 7 commandments.

Abstract. We discover and experiment with categorization-based methods to natural language identification. Two approaches to language identification based on Markov processes are compared, both methods treat the incoming text on the character level. We performed series of experiments with the aim to make certain of high precision in language identification task of selected methods and also with the objective to compare them against themselves. Experimental evaluation was based on largescaled Multilingual Reuters Corpus with various European and Slavic languages. Our research results showed that both methods are comparable in the task of natural language identification achieving recall as high as 99,75%. 1

Acknowledgements I would like to take this opportunity to thank all the people who have helped me with my research and thus made this work possible. First of all, I am very grateful to my advisor, Alexander Rudnicky, for his valuable guidance and support throughout the course of this work and my graduate school career. His vision and understanding in scientific research teach me all the elements I would need to know when conducting high quality research on my own. I am also sincerely grateful to my committee members, William Cohen, Carolyn Penstein Rosé, and Gokhan Tür, for their valuable suggestions and contributions to this research. Carolyn Penstein Rosé in particular gave me a great deal of feedback on the thesis writing. While at CMU, I have been lucky enough to be a part of a friendly and very helpful research community. I would like to thank my fellow research group members and the members of the Dialogs on Dialogs reading group, Dan Bohus, Antoine Raux, Mihai Rotaru, Banerjee Satanjeev, Stefanie Tomko, and many other people that I would not be possible to list all their names here, for numerous intellectual discussions and their

We show a diagnostic evaluation of DIPETT, a broad-coverage parser of English sentences. We consider the TSNLP suite as a diagnostic tool, and propose an alternative broader-coverage test suite of test sentences extracted from Quirk et al. We compare the diagnostic effectiveness of the two suites, and draw a few general conclusions. The evaluation results were used to make significant improvements to DIPETT.

To my wife Wei and my son Billy. iv Generating human motion that appears natural is a long standing problem in character animation. Researchers have explored many different approaches including physics-based simulation, optimization, and data-driven methods such as motion graphs and motion interpolation. One major difficulty in applying most of these approaches is the lack of an implementable definition of what it means for motion to be natural or human-like. In this thesis, we explore two techniques to fill this gap. The first technique creates a naturalness measure for quantifying natural human motion. The second technique involves a statistical analysis of human motion to compute aggregate statistics that are needed to guide animation algorithms for human figures toward natural looking solutions. A naturalness measure should be useful in verifying that a motion editing

Real-time acoustic source localization in noisy environments for human-robot multimodal interaction

Real-time acoustic source localization in noisy environments for human-robot multimodal interaction

Abstract. This paper presents design, development and contents of Lithuanian continuous speech corpus LRN 0.1 (Lithuanian Radio News, prototype-version 0.1). The corpus contains 17 hours 23 minutes of records from radio broadcast news read by 31 speakers. The recorded material is segmented into sentence-length records that are divided into training, development, and evaluation sets. Speech recordings are accompanied by word level transcriptions and automatically generated word-to-phone lexicon. The corpus is designed for the constructing and evaluating speaker-independent continuous speech recognition systems, and may also be used for linguistic research.

Efficient wide-coverage parsing is integral to large-scale NLP applications. Unfortunately, parsers for linguistically motivated formalisms, e.g. HPSG and TAG, are often too inefficient for these applications. This paper describes two modifications to the standard CKY chart parsing algorithm used in the Clark and Curran (2006) Combinatory Categorial Grammar (CCG) parser. The first modification extends the tight integration of the supertagger and parser, so that individual supertags can be added to the chart, which is then repaired rather than rebuilt. The second modification adds constraints to the chart that restrict which constituents can combine. Parsing speed is improved by 30–35% without a significant accuracy penalty and a small increase in coverage when both of these modifications are used. 1