English

Multimodal Deep Learning for Mental Disorders Prediction from Audio Speech Samples

Machine Learning 2020-04-15 v5 Sound Audio and Speech Processing Machine Learning

Abstract

Key features of mental illnesses are reflected in speech. Our research focuses on designing a multimodal deep learning structure that automatically extracts salient features from recorded speech samples for predicting various mental disorders including depression, bipolar, and schizophrenia. We adopt a variety of pre-trained models to extract embeddings from both audio and text segments. We use several state-of-the-art embedding techniques including BERT, FastText, and Doc2VecC for the text representation learning and WaveNet and VGG-ish models for audio encoding. We also leverage huge auxiliary emotion-labeled text and audio corpora to train emotion-specific embeddings and use transfer learning in order to address the problem of insufficient annotated multimodal data available. All these embeddings are then combined into a joint representation in a multimodal fusion layer and finally a recurrent neural network is used to predict the mental disorder. Our results show that mental disorders can be predicted with acceptable accuracy through multimodal analysis of clinical interviews.

Keywords

Cite

@article{arxiv.1909.01067,
  title  = {Multimodal Deep Learning for Mental Disorders Prediction from Audio Speech Samples},
  author = {Habibeh Naderi and Behrouz Haji Soleimani and Stan Matwin},
  journal= {arXiv preprint arXiv:1909.01067},
  year   = {2020}
}

Comments

arXiv admin note: text overlap with arXiv:1811.09362 by other authors

R2 v1 2026-06-23T11:03:52.532Z