In this paper we present SIMDIAL, a paradigm to assess Spoken Language Dialogue Systems (SLDSs) using deterministic user simulation. The paradigm allows automatic or semiautomatic evaluation on different tasks and uses natural langage to interact with evaluated SLDSs. MOTS-CLÉS : Paradigme d’évaluation, systèmes de dialogue homme-machine, simulation déterministe d’utilisateurs, évaluation autom...

Studies in modality comprise a complex canon of functional, formal, sociological and diachronic analyses language. The current understanding how English language speakers use is unclear; while some research argues that core modal auxiliaries are decline, they reported as increasing elsewhere. A lack contemporary representative spoken data has rendered it difficult to reconcile such differing pe...

Cost-e ective development and widespread deployment of spoken language systems is only possible if their development process is substantially supported by intelligent design tools. In this paper, we present PIA a new approach for fast prototyping of complex spoken dialog systems. Dialog structures are speci ed in a specialised fully declarative design language. Dialog design in PIA is considere...

We treat the spoken dialogue interaction between a command and control system* and the user commanding that system through a conversational interface as an instance of real-time voice-tovoice machine translation (MT) similar to that seen in the Interpreting Telephone (IT) application domain. Voice-to-voice MT and spoken dialogue user interface systems share these important similarities from the...

We describe a method for annotating spoken dialog corpora using both automatic and manual annotation. Our semi-automated method for corpus development results in a corpus combining rich semantics, discourse information and reference annotation, and allows us to explore issues relating these.

Intelligent environments are ubiquitous computing systems that react to and interact with their inhabitants. They adapt to their necessities, assisting them in their every day life. We present a real intelligent environment that supports spoken interaction with its users. The spoken dialogue interface is automatically created according to the environment and the interpretation and generation va...

We present our work in building a spoken language interface for a tutorial dialogue system. Our goal is to allow natural, unrestricted student interaction with the computer tutor, which has been shown to improve the student’s learning gain, but presents challenges for speech recognition and spoken language understanding. Here we describe the system design, focusing on the components used for sp...

As a priority-setting exercise, we examined interactions between users and a simple spoken dialog system in comparison to interactions with a human operator. Based on analysis of the observed usability differences and their root causes we propose seven priority issues for spoken dialog systems research. keywords: evaluation, human-computer interaction, human-human dialog, usability events, huma...

No matter how well hidden our systems are and how well they do their magic un-noticed in the background, there are times when direct interaction between system and human is a necessity. As long as the interaction can take place unobtrusively and without techno-clutter, this is desirable. It is hard to picture a means of interaction less obtrusive and techno-cluttered than spoken communication o...

We present the spoken dialogue system designed and implemented for Virtual Advisers in the FOCAL environment. Its architecture is based on: Dialogue Agents using propositional attitudes, a Natural Language Understanding component using typed unification grammar, and a commercial speaker-independent speech recognition system. The current application aims to facilitate the multimedia presentation...