Learn More
We present evaluation results of a multimodal route navigation system that allows interaction using speech and tactile/visual modes. Various functional aspects of the system were studied, related especially to the IO-modalities and their use as means of communication. We compared the users’ expectations before the evaluation with their actual experience of(More)
We present a design of a rich multimodal interface for mobile route guidance. The application provides public transport information in Finland, including support for pedestrian guidance when the user is changing between the means of transportation. The range of input and output modalities include speech synthesis, speech recognition, a fisheye GUI, haptics,(More)
Mobile devices, such as smartphones and personal digital assistants, can be used to implement efficient speech-based and multimodal interfaces. In this paper we present three approaches for mobile public transport information services, such as bus timetables and route guidance. These applications offer varying functionality depending on the devices and(More)
One of the biggest obstacles in building versatile natural human-computer interaction systems is that the recognition of natural speech is still not sufficiently robust, especially in mobile situations where it's almost impossible to cancel out all irrelevant auditory information. In multimodal systems the possibility to disambiguate between several input(More)
In this paper we present the MUMS Multimodal Route Navigation System which combines speech, pen, and graphics into a PDA-based multimodal system. We focus especially on the three-level modality fusion component which we believe provides an accurate and more flexible input fusion than the usual twolevel approaches. The modular architecture of the system(More)
In this paper, we present our approach to dialogue management in the spoken dialogue system that is being developed within the project Interact. Compared to traditional approaches, our dialogue manager will support the system’s adaptivity and flexibility with the help of two design decisions: an agent-based architecture and the use of neural network models.(More)
  • 1