The ability to have a social conversation is an indication of the stage of dementia. One of the goals of the Smart Teddy project is to determine whether senior citizens with dementia are able to continue to live independently. One of the indicators for this is the degree to which the patient maintains social contacts. The aim of this project is to measure this using the sensors that are present in the Smart Teddy and the base station (see more information on the Smart Teddy project page).
The Smart Teddy and the base station contain a microphone whose sound can be analyzed. One possible direction to measure social contact is to try to determine from the sound whether a person is talking and then whether it is possible to determine that several people are talking. A next step can be to take into account background noise, such as radio and television. It may be possible to detect the distortion of a speaker to determine the difference. A final step could be to see whether two speaking people are also having a substantive conversation or whether they are two separate monologues.
No data is yet available on elderly people with dementia, but it is possible to use material from audiobooks, youtube films, television recordings, etc.From data with subtitles for the deaf and hard of hearing, it can sometimes be concluded that consecutive sentences are spoken by different people. A first step can be to compile a dataset of two sentences spoken by one and the same person or by two different persons. For example, the dataset can be enriched by adding different types of background noise.
- Interest in doing research
- Good English reading and writing skills
- Background in programming or mathematics
If you are interested then please contact one of the leading researchers
Further information: Please visit the page for the Smart Teddy