Robust Speech and Natural Language Processing Models for Depression Screening
| Autor: | Piotr Chlebek, Ricardo C. L. F. Oliveira, Y. Lu, Amir Harati, Tomasz Rutowski, Shriberg Elizabeth E |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Conversational speech
business.industry Computer science Deep learning media_common.quotation_subject Speech technology 020206 networking & telecommunications 02 engineering and technology computer.software_genre Depression screening Session (web analytics) 030227 psychiatry Test (assessment) 03 medical and health sciences ComputingMethodologies_PATTERNRECOGNITION 0302 clinical medicine 0202 electrical engineering electronic engineering information engineering Artificial intelligence Transfer of learning Function (engineering) business computer Natural language processing media_common |
| Zdroj: | 2020 IEEE Signal Processing in Medicine and Biology Symposium (SPMB). |
| Popis: | Depression is a global health concern with a critical need for increased patient screening. Speech technology offers advantages for remote screening but must perform robustly across patients. We have described two deep learning models developed for this purpose. One model is based on acoustics; the other is based on natural language processing. Both models employ transfer learning. Data from a depression-labeled corpus in which 11,000 unique users interacted with a human-machine application using conversational speech is used. Results on binary depression classification have shown that both models perform at or above AUC=0.80 on unseen data with no speaker overlap. Performance is further analyzed as a function of test subset characteristics, finding that the models are generally robust over speaker and session variables. We conclude that models based on these approaches offer promise for generalized automated depression screening. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|