This paper argues that the problems of dialogue management (DM) and Natural Language Generation (NLG) in dialogue systems are closely related and can be fruitfully treated statistically, in a joint optimisation framework such as that provided by Reinforcement Learning (RL). We first review recent results and methods in automatic learning of dialogue management strategies for spoken and multimod...

In this paper, the requirements on semantic representations in spoken dialogue systems are discussed. It is argued that spoken dialogue needs a special treatment when it comes to natural language processing, since the phenomena that occur in spoken language are not the same as those that occur in written language. These special properties of spoken language are outlined and the different aspect...

Spoken language is an important and natural way for people to communicate with computers. Nonetheless, habitable, reliable, and efficient human-machine dialogue remains difficult to achieve. This paper describes a multi-threaded semisynchronous architecture for spoken dialogue systems. The focus here is on its utterance interpretation module. Unlike most architectures for spoken dialogue system...

Speech and hand gestures offer the most natural modalities for everyday human-to-human interaction. The availability of diverse spoken dialogue applications and the proliferation of accelerometers on consumer electronics allow the introduction of new interaction paradigms based on speech and gestures. Little attention has been paid however to the manipulation of spoken dialogue systems through ...

We describe a series of experiments in which memorybased machine learning techniques are used for the interpretation of spoken user input in human-machine interactions. In these experiments, the task is to determine the dialogue act of the user input and the type of information slots the user fills, on the basis of a variety of features representing the spoken input (speech measurements and wor...

We present Witchcraft, an open-source framework for the evaluation of prediction models for spoken dialogue systems based on interaction logs and audio recordings. The use of Witchcraft is two fold: first, it provides an adaptable user interface to easily manage and browse thousands of logged dialogues (e.g. calls). Second, with help of the underlying models and the connected machine learning f...

Due to recent progresses in the field of speech and natural language processing, spoken dialogue systems are becoming more and more common. Nevertheless, the design of complete dialogue systems remains uneasy. On the one hand, developing such a system involves defining a dialogue strategy. Though automatic learning of dialogue strategies has been introduced in several researches, it stays hard ...

This paper introduces a network-based spoken dialog system development tool kit: WFSTDM Builder developed by NICT. WFSTDM Builder provides functions to share and edit SLU and scenario so that developers can create a wfst-based spoken dialogue system instantly with this tool. One can test the scenario by accessing to the servers connected such as ASR, TTS and WFSTDM server via not only the tool’...

This paper focuses on the analysis and prediction of so-called aware sites, defined as turns where a user of a spoken dialogue system first becomes aware that the system has made a speech recognition error. We describe statistical comparisons of features of these aware sites in a train timetable spoken dialogue corpus, which reveal significant prosodic differences between such turns, compared w...

Motivated by prior spoken dialogue system research in user modeling, we analyze interactions between performance and user class in a dataset previously collected with two wizarded spoken dialogue tutoring systems that adapt to user uncertainty. We focus on user classes defined by expertise level and gender, and on both objective (learning) and subjective (user satisfaction) performance metrics....