Classifying depression symptom severity: Assessment of speech representations in personalized and generalized machine learning models.

Campbell, Edward L.; Dineley, Judith; Conde, Pauline; Matcham, Faith; White, Katie M.; Oetzmann, Carolin; Simblett, Sara; Bruce, Stuart; Folarin, Amos A.; Wykes, Til; Vairavan, Srinivasan; Dobson, Richard J. B.; Docio-Fernandez, Laura; Garcia-Mateo, Carmen; Narayan, Vaibhav A.; Hotopf, Matthew; Cummins, Nicholas

doi:10.21437/Interspeech.2023-1721

Classifying depression symptom severity: Assessment of speech representations in personalized and generalized machine learning models.

Edward L. Campbell, Judith Dineley, Pauline Conde, Faith Matcham, Katie M. White, Carolin Oetzmann, Sara Simblett, Stuart Bruce, Amos A. Folarin, Til Wykes, Srinivasan Vairavan, Richard J. B. Dobson, Laura Docio-Fernandez, Carmen Garcia-Mateo, Vaibhav A. Narayan, Matthew Hotopf, Nicholas Cummins

There is an urgent need for new methods that improve the management and treatment of Major Depressive Disorder (MDD). Speech has long been regarded as a promising digital marker in this regard, with many works highlighting that speech changes associated with MDD can be captured through machine learning models. Typically, findings are based on cross-sectional data, with little work exploring the advantages of personalization in building more robust and reliable models. This work assesses the strengths of different combinations of speech representations and machine learning models, in personalized and generalized settings in a two-class depression severity classification paradigm. Key results on a longitudinal dataset highlight the benefits of personalization. Our strongest performing model set-up utilized self-supervised learning features and convolutional neural network (CNN) and long short-term memory (LSTM) back-end.