Detta är ett uppsatsförslag hämtat från Nationella Exjobb-poolen. Klicka här för att komma tillbaka till samtliga exjobbsförslag.
Can you read tongue movements?
The studies indicate that the information provided by the tongue is much weaker than from the lips, but that it does improve the perception of words and sentences in noise.
Several questions however arise from the studies:
1) The subjects differ greatly in their ability to interpret the animations. We would like to perform a gaze-tracking experiment and analyze the results: Is there any relationship between where the subjects focus their attention (on the face, the lips, the tongue) and the recognition results?
2) How does the performance improve with training? There are indications that some subjects learn the interpretation of the animations during a training phase as templates, while others use already established articulatory knowledge. We would like to perform an experiment on the importance of consistency between training and test vs. the articulatory relevance.
3) It is not clear how the animations are interpreted by the listeners. Is it good to have many details, providing much information, or is a simple display better? Does a three-dimensional, realistic display, or a simplified display with a two-dimensional tongue result in the best recognition results.
We would like the thesis work to focus on the above and/or other questions related to tongue reading in an augmented reality display.
The test set-up and the stimuli is available.
Informationen om uppsatsförslag är hämtad från Nationella Exjobb-poolen.