Robust and adaptive architecture for multilingual spoken dialogue systems

The Benefits of (Automated) Dialogue

“…Research on dialogue content has explored the role of empathy (Liu and Picard, 2005), the use of 'small talk' (Bickmore and Picard 2004), trust (Bickmore and Cassell 2001), emotions, personalisation and narration (Stock, 1996), information exchange and 'like-mindedness' (Svennevig, 1999). Turunen et al (2004) examined the role of user experience, tailoring system output to differentiate between novices and experts, whilst Bernsen and Dybkjaer (1996) compared co-operation between humans with that between humans and computers, highlighting that, in the latter, a clear communication The Benefits of (automated) dialogue…”

Contributions to the contextualization of human-machine spoken interaction systems

“…Hybrid user modeling (from the point of view of the explicitness of the information) has been used in several application domains, especially in recommendation systems, for retrieving personalized news (Kamba et al, 1997;Sakagami and Kamba, 1997), TV programmes (Buckzak et al, 2002;Smyth and Cotter, 1999), or tourist information (Ardissono et al, 2003;Kuflik et al, 2005). As regards spoken language applications, we could mention Pargellis et al (2004), that proposes a dialogue system that presents its users with personalized online information, or Jokinen et al (2004); Turunen et al (2004), that presents a personalized system to manage an e-mail account using speech.…”

“…For instance, to model the behaviour of the caller of a Call Centre system to decide whether it is necessary to route the call to a human operator (Cena and Torre, 2006), or to interact with a robotic assistant in hospitals (Spiliotopoulos et al, 2001). But maybe the most widespread field in which user-adapted SDS are considered is the Information Retrieval one, from e-mail management, as in (Turunen et al, 2004), to travel ticket reservation (Eckert et al, 1997;Litman and Pan, 2002), and also for the recommendation of tourist information or the restaurants preferred by the users (Komatani et al, 2005;Whittaker and Walker, 2005).…”

“…Several strategies have been proposed in the literature to adapt the behaviour of the system to the main features of the users, such as their degree of expertise when interacting with the system (Jokinen et al, 2004;Turunen et al, 2004) or the actions they prefer to carry out during their interactions (Lucas-Cuesta et al, 2009b). The behaviour of the system could be modified, for instance, by deciding at each turn which of the participants of the dialogue takes the initiative.…”