Detecting and Analysing Spontaneous Oral Cancer Speech in the Wild

Oral cancer speech is a disease which impacts more than half a million people worldwide every year. Analysis of oral cancer speech has so far focused on read speech. In this paper, we 1) present and 2) analyse a three-hour long spontaneous oral cancer speech dataset collected from YouTube. 3) We set baselines for an oral cancer speech detection task on this dataset. The analysis of these explainable machine learning baselines shows that sibilants and stop consonants are the most important indicators for spontaneous oral cancer speech detection. Cite as: Halpern, B.M., Son, R.V., Brekel, M.V.D., Scharenborg, O. (2020) Detecting and Analysing Spontaneous Oral Cancer Speech in the Wild. Proc. Interspeech 2020, 4826-4830, DOI: 10.21437/Interspeech.2020-1598. BibTex citation @inproceedings{Halpern2020, author={Bence Mark Halpern and Rob van Son and Michiel van den Brekel and Odette Scharenborg}, title={{Detecting and Analysing Spontaneous Oral Cancer Speech in the Wild}}, year=2020, booktitle={Proc. Interspeech 2020}, pages={4826--4830}, doi={10.21437/Interspeech.2020-1598}, url={http://dx.doi.org/10.21437/Interspeech.2020-1598}