The aims of the SpeechDat-Car project are to develop a set of speech databases to support training and testing of multilingual speech recognition applications in the car environment. As a result, a total of ten (10) equivalent and similar resources will be created. The 10 languages are Danish, each language 600 sessions will be recorded (from at least 300 speakers) in seven characteristic envir...

More objective and automated detection of respiratory diseases in pig houses should be possible by on-line sound analysis of cough monitoring. To develop automatic algorithms for pig cough recognition, experiments and well-labeled cough data are needed. The objectives of this article are: (1) to give a short overview of the attained results in cough recognition, and (2) to define a methodology ...

We compare two methods of acquiring ultrasound tongue images. A new system capable of recording directly from the cineloop image buffer at a high frame rate and which is more accurately synchronized with audio is compared with an optimised method of recording images via the NTSC video output of an ultrasound machine. As a focus for this comparison we gathered representative data on English /l f...

In this thesis, I propose a framework for designing 3D-based audio-only games in which all navigation is based on perceiving the 3D-audio, as opposed to relying on other navigational aids or imagining the audio as being spatial, where additional sounds may be added later on in the development process. To test the framework, a game named Sound Hunter was developed in an iterative process togethe...