Heikki Keränen

Learn More
Mental overload directly affects safety in aviation and needs to be alleviated. Speech recordings are obtained non-invasively and as such are feasible for monitoring cognitive load. We recorded speech of 13 military pilots while they were performing a simulator task. Three types of cognitive load (load on situation awareness, information processing and(More)
Online communities enabled by mobile communication have needs for sharing experiences and common interests in a context sensitive manner. However, due to the current division of creation, delivery and access functionality of multimedia to applications, much user effort is needed to communicate efficiently. This paper presents an approach for a user(More)
When developing adaptive speech-based multilingual interaction systems, we need representative data on the user's behaviour. In this paper we focus on a data collection method pertaining to adaptation in the user's interaction with the system. We describe a multi-session group scenario for Wizard of Oz studies with two novel features: firstly, instead of(More)
In this paper we discuss possibilities for building adaptive spoken dialogue systems and how learning in such systems could be modelled. Especially, we are interested in the dialogue strategies that different users exploit in their interactions with speech applications, and how the systems could learn differences in the strategies so as to allow(More)
This paper presents a scalable and modular client-server architecture for content-based multimedia retrieval. The proposed architecture is designed to facilitate straightfoward addition of new media types and retrieval operations without modifications to existing features. This is achieved by the encapsulation of data, operations and user interface related(More)
Military fighter pilots have to function in environments that unavoidably have an effect on both production and reception of speech. Speech production is affected by for example g-forces, positive pressure breathing (PBG), background noise and workload. This can have an effect on the understandability of speech, which in turn can affect flight safety. This(More)
An experiment is reported exploring whether the general auditorily assessed segmental quality of second language speech can be evaluated with automatic methods, based on a number of prosodic features of the speech data. The results suggest that prosodic features can predict the occurrence of a number of segmental problems in non-native speech.