BlaBla: Linguistic Feature Extraction for Clinical Analysis in Multiple Languages

• DOI: 10.21437/interspeech.2020-2880
• Publication Date: 2020-10-27T09:22:11Z
• Authors: Abhishek Shivkumar; Jack Weston; Raphael Lenain; Emil Fristed
• Keywords: Feature (linguistics)

We introduce BlaBla, an open-source Python library for extracting linguistic features with proven clinical relevance to neurological and psychiatric diseases across many languages.BlaBla is a unifying framework accelerating simplifying research.The built on state-of-theart NLP frameworks supports multithreaded/GPU-enabled feature extraction via both native calls command line interface.We describe BlaBlas architecture validation of its 12 diseases.We further demonstrate the application BlaBla task visualizing classifying language disorders in three languages real data from AphasiaBank dataset.We make codebase freely available researchers hope providing consistent, well-validated foundation next generation research.