This paper describes the dynamic, multi-lingual lexicon that was developed in the SmartKom project. SmartKom is a multimodal dialogue system that is supposed to assist the user in many applications which are characterised by their highly dynamic contents. Because of this dynamic nature various modules of the dialogue ranging from speech recognition over analysis to synthesis need to have one common knowledge source that takes care of the dynamic vocabularies that need to be processed. This central knowledge source is the lexicon. It is able to dynamically add and remove new words and generate the pronunciations for these words. We also describe the classbased language model (LM) that is used in SmartKom and that is closely coupled with the lexicon. Also evaluation results for this LM are given. Furthermore we describe our approach to dynamically generate pronunciations and give experimental results for the different classifiers we trained for this task.

This paper describes the SmartKom-Home system realized within the SmartKom project. It assists the user by means of a multi-modal dialogue system in the home environment. This involves the control of various devices and the access to services. SmartKom-Home is supposed to serve as a uniform interface to all these devices and services so the user is freed from the necessity to understand which of the devices to consult how and when to fulfill complex wishes. We describe the setting of this scenario together with the hardware used. We furthermore discuss the specific requirements that evolve in a home environment, and how they are handled in the project.

Systems for spoken-language understanding can use prosodic information on the speech recognition side as well as the linguistic processing side. In the former case, prosody improves recognition accuracy and speed. In the latter case, it contributes to the computation of meaning. Interfacing prosodic processing to language analysis has so far been mainly concerned with speeding up the parsing process. The actual integration of prosodic information into the semantic part of a language understanding system, or into the transfer part of a translation system, has mostly been left aside. We describe how prosody has been used in the syntactic-semantic and transfer modules of the Verbmobil spoken dialogue translation system. On the syntactic-semantic side, prosody is currently used for the solution of three different problems: insertion of clause boundaries, selection of sentence mood (declarative, question, etc), and assignment of semantic focus. On the transfer side, the prosodic information...

This paper presents a unification procedure which eliminates the redundant copying of structures by using a lazy incremental copying approach to achieve structure sharing. Copying of structures accounts for a considerable amount of the total processing time. Several methods have been proposed to minimize the amount of necessary copying. Lazy Incremental Copying (LIC) is presented as a new solution to the copying problem. It synthesizes ideas of lazy copying with the notion of chronological dereferencing for achieving a high amount of structure sharing.