Building autonomous sensitive artificial listeners (Extended abstract)

This paper describes a substantial effort to build a real-time interactive multimodal dialogue system with a focus on emotional and non-verbal interaction capabilities. The work is motivated by the aim to provide technology with competences in perceiving and producing the emotional and non-verbal behaviours required to sustain a conversational dialogue. We present the Sensitive Artificial Listener (SAL) scenario as a setting which seems particularly suited for the study of emotional and non-verbal behaviour, since it requires only very limited verbal understanding on the part of the machine. This scenario allows us to concentrate on non-verbal capabilities without having to address at the same time the challenges of spoken language understanding, task modeling etc. We first summarise three prototype versions of the SAL scenario, in which the behaviour of the Sensitive Artificial Listener characters was determined by a human operator. These prototypes served the purpose of verifying the effectiveness of the SAL scenario and allowed us to collect data required for building system components for analysing and synthesising the respective behaviours. We then describe the fully autonomous integrated real-time system we created, which combines incremental analysis of user behaviour, dialogue management, and synthesis of speaker and listener behaviour of a SAL character displayed as a virtual agent. We discuss principles that should underlie the evaluation of SAL-type systems. Since the system is designed for modularity and reuse, and since it is publicly available, the SAL system has potential as a joint research tool in the affective computing research community.

Expecting Too Much: European Union’s Minority Protection Hide-and-Seek

EU’s deference to the Member State approaches in minority protection can intensify the oppression of
the vulnerable groups, its insistence on non-discrimination on the basis of nationality in the minority regions with special rights in place can equally produce injustice. Its inability to protect EU-wide minorities, like the Roma, is equally problematic. Although a ‘value’, minority protection functions incoherently, if at all. It is time to approach the EU as a highly specific minority protection arena not to be confused with its component parts – the Member States. The reform of the Member State-centred thinking should start at the level of approaching the core issues. It should include the assessment of such questions as what is a minority in the EU’s context of a missing majority, what is the appropriate depth of EU’s intervention in the area of minority protection, i.e. how much room for manœuvre should reasonably be left with the Member States without disrupting the effectiveness of EU’s regulation, as well as the approach to defining what a success in minority protection should be, in the
EU context. The latter should be done, in particular, with due regard to the division of competences between the EU and the Member States in this and other relevant fields. This paper briefly explores a series of diverse casestudies – from migrant EU citizens, Baltic Russians, and sexual minorities to, most importantly, Roma rights to make the first attempt to test the proposed synergetic approach.