DEPAC: a Corpus for Depression and Anxiety Detection from Speech

Abstract

Mental distress like depression and anxiety contribute to the largest proportion of the global burden of diseases. Automated diagnosis system of such disorders, empowered by recent innovations in Artificial Intelligence, can pave the way to reduce the sufferings of the affected individuals. Development of such systems requires information-rich and balanced corpora. In this work, we introduce a novel mental distress analysis audio dataset DEPAC, labelled based on established thresholds on depression and anxiety standard screening tools. This large dataset comprises multiple speech tasks per individual, as well as relevant demographic information. Alongside, we present a feature set consisting of hand-curated acoustic and linguistic features, which were found effective in identifying signs of mental illnesses in human speech. Finally, we justify the quality and effectiveness of our proposed audio corpus and feature set in predicting depression severity by comparing the performance of baseline machine learning models built on this dataset with baseline models trained on other well-known depression corpora.

Automated speech analysis for risk detection of depression, anxiety, insomnia, and fatigue: Algorithm Development and Validation Study

“…Our study builds upon existing mental health research on speech analysis and extends the insights for deployment into clinical practice. For risk and anxiety depression in the general population, we found similar strong performances such as [25,26,62,63]. Our recruitment and involvement of participants was in person.…”

“…Our recruitment and involvement of participants was in person. For medium-sized datasets, below 1000 participants, such as ours, it can be observed that web-based crowd-sourced recruitment of participants needs more training data to yield the same level of model accuracy [62, 64], as models trained on speech with face-to-face recruitment. This was also observed in a large study, with over 6000 participants, with online data recruitment for risk detection in the general population in American English [63].…”

A Comprehensive Review on Synergy of Multi-Modal Data and AI Technologies in Medical Diagnosis

“…Yin et al [121] presented a deep learning model that harnesses the strengths of parallel Convolutional Neural Networks (CNNs) and Transformers, balancing effective information extraction with computational tractability for depression detection. Adding to this body of work, Tasnim et al [122] examined the predictive utility of two acoustic feature sets-conventional handcrafted features and those derived from deep representations-in assessing depression severity through speech analysis. He et al [123] proposed a hybrid approach combining handcrafted elements with deep learning features to precisely gauge depression severity from speech.…”

Ensemble learning with speaker embeddings in multiple speech task stimuli for depression detection

“…The collection of spontaneous and read speech from 30 depressed and 30 control subjects was used to extract acoustic features ( Alghowinem et al, 2013 ). DEPression and Anxiety Crowdsourced corpus (DEPAC) ( Tasnim et al, 2022 ), which has a diversity of speech tasks (Phoneme fluency, Phonemic fluency, Picture description, Semantic fluency, and Prompted narrative), has been published recently as a depression and anxiety detection corpus. Furthermore, the classification results in Long et al (2017) based on the corpus of three speech types (reading, picture description, and interview), each of which corresponds to three emotional valences (negative, neutral, and positive), showed that speaking style and mood had a significant influence on depression recognition.…”