Speech synthesis systems have gained their position into a range of products and services. In the applications domain, applied research is aiming to alleviate the limitations and shortcomings of today’s speech synthesis systems that hinder their wider adoption and exploitation into mass markets and everyday use. Multimodality and affect seek to augment human-machine and human-robot interaction, fueling truly natural speech interfaces and dialog systems, and speeding up the take-up of speech synthesis into tomorrow's entertainment, learning and gaming platforms and environments.

In this context particular focus has been given by the Group to the application of speech synthesis in areas such as speech-enabling of digital content, natural spoken interaction and accessibility, leading to innovative systems for applications such as:

• speech-enabling web content ([Chalamandaris et al., 2009c; Raptis et al., 2005a]);
• mobile screen reading ([Karabetsos et al., 2009; Chalamandaris et al., 2010] and the MobiTalk project);
• home-based telecare systems ([Raptis et al., 2009] and the HEARTS project); and
• monitoring in the broadcast sector [Demiros et al., 2008].