Automatic administration of semantic verbal fluency tests for Portuguese
DOI:
https://doi.org/10.36505/ExLing-2019/10/0015/000377Keywords:
verbal fluency tests, natural language processing, automatic speech recognitionAbstract
Verbal fluency tests are quick and flexible tests used in the area of Neuropsychology to evaluate executive and language functions of subjects. An automatic modular pipeline for the analysis of verbal fluency tests for the semantic category of animals is proposed in this document. The system was developed for European Portuguese using test audio recordings as input. Google Cloud Speech-to-Text is used to perform automatic speech recognition. fastText word embeddings and phonemic transcriptions are applied to automatically evaluate temporal, phonemic, and semantic clusters produced. The proposed architecture was evaluated using 164 animal category tests, performed by Portuguese elderly subjects. Correlations were found between manual and automatic extracted features, such as the number of correct words produced ($\rho = 0.58$). Feature extraction efficacy was found to be dependent on background noise levels during recording.
References
Amorim, P., Susano, M. J. 2017. Clinical Trial: Pre-operative Neurocognitive Disorder and Low Near-infrared Spectrometry is Associated with Postoperative Delirium. https://clinicaltrials.gov/ct2/show/NCT03171766?id=NCT03171766
Google Cloud. 2019. Cloud Speech-to-Text - Speech Recognition | Cloud Speech-toText API. https://cloud.google.com/speech-to-text/
Grave, E. et al. 2018. Learning Word Vectors for 157 Languages.
König, A. et al. 2018. Fully automatic speech-based analysis of the semantic verbal fluency task. Dementia and Geriatric Cognitive Disorders, 45(3-4):198–209.
Porto Editora. 2019. Infopédia - Dicionários Porto Editora. https://www.infopedia.pt/
Troyer, A.K. et al. 1997. Clustering and switching as two components of verbal fluency: Evidence from younger and older healthy adults. Neuropsychology, 11(1), 138–146.
Xiaowei Xu et al. 2002. A distribution-based clustering algorithm for mining in large spatial databases. Proceedings 14th International Conference on Data Engineering, 324–331.
Downloads
Published
Issue
Section
License
Articles are published under the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are properly credited.
