Jens Edlund - projects in which I've been involved
Multimodal database of spontaneous speech in dialog (Spontal)
This was a national project started in 2007 and funded by the Swedish Research Council
. The goal is to gather 60 hours of spontaneous dialogues in an audio-visual database.
The MonAMI project, instigated in 2006, was a research project aimed at researching and developing prototype dialogue systems suitable for testing and evaluating human-like dialogue behaviour, such as error handling strategies and responsivity.
Vad gör tal till samtal/What makes conversation special?
This was a three-year national fundamental research project, started in January 2007 and funded by the Swedish Research Council
. The aim was to investigate what makes spoken conversations special in relation to speech in general.
CHIL was an Integrated Project (IP 506909) under the European Commission's Sixth Framework Programme. The project launched on January, 1st 2004. The objective of the project was to design computer services that model humans and the state of their activities and intentions in order to allow computers to provide assistance unobtrusively.
The Higgins project, instigated in 2003, is a research project aimed at researching and developing prototype dialogue systems suitable for testing and evaluating human-like dialogue behaviour, such as error handling strategies and responsivity.
Centlex is the central lexicon resource produced and maintained by the Centre for Speech Technology. It is currently dormant.
Fel och missförstånd i människa-maskindialogsystem/Error and Miscommunication in Human-Computer Dialogue Systems
Den långsiktiga målsättningen för projektet är att öka kunskaperna om mänsklig kommunikation och att utnyttja dessa för att skapa bättre och mer användbara talbaserade dialogsystem.
This is a national project started in 2002 and was funded by the Swedish Research Council
. The aim was increase our knowledge of human communication and to ustilise these to improve spoken dialogue systems.
The AdApt project, which ran in the years 1998 to 2002, had as its goal to be the foundation for the development and evaluation of advanced multimodala spoken dialogue systems. Within the project, a spoken dialogue system where a user could cooperate with an animated talking agent to solve more complex problems than what had previously been achieved in our systems.
GESOM is an XML based mark-up language for describing dialogue system output, and is focused on generality and simplicity, rather than exactness and completeness. It was originally created as part of AdApt
. GESOM can be seen as a layer of separation between the dialogue system's generation of output and the output device's interpretation and realisation (rendering) of the same, which frees the dialogue system designer from the need to know exactly what output device(s) will be used.