AUTHOR=Hajduska-Dér Bálint , Kiss Gábor , Sztahó Dávid , Vicsi Klára , Simon Lajos TITLE=The applicability of the Beck Depression Inventory and Hamilton Depression Scale in the automatic recognition of depression based on speech signal processing JOURNAL=Frontiers in Psychiatry VOLUME=Volume 13 - 2022 YEAR=2022 URL=https://www.frontiersin.org/journals/psychiatry/articles/10.3389/fpsyt.2022.879896 DOI=10.3389/fpsyt.2022.879896 ISSN=1664-0640 ABSTRACT=Depression is a growing problem worldwide, impacting on an increasing number of patients, and also affecting health systems and the global economy. The most common diagnostical rating scales of depression are self-reported or clinician-administered, which differ in the symptoms that they are sampling. Speech is a promising biomarker in the diagnostical assessment of depression, due to non-invasiveness and cost and time efficiency. In our study we used the Hungarian Depressed Speech Database, recorded read speech samples and scores as severity measurement according to the Beck Depression Inventory. Also, Hamilton Depression Scale assessment was available in 20% of our cases. After preprocessing (phoneme-level segmentation and feature extraction) the speech samples, we used Support Vector Regression as machine learning method to assess the speech samples automatically. We found that the estimated values of the acoustic model trained on BDI scores are closer to HAMD assessment than to the BDI scores, and the partial application of HAMD scores instead of BDI scores (20%) in training improves the accuracy of automatic recognition of depression.