Nonverbal social withdrawal in depression: Evidence from manual and automatic analyses

Girard, Jeffrey M.; Cohn, Jeffrey F.; Mahoor, Mohammad H.; Mavadati, S. Mohammad; Hammal, Zakia; Rosenwald, Dean P.

doi:10.1016/j.imavis.2013.12.007

Cited by 211 publications

(152 citation statements)

References 85 publications

Supporting

Mentioning

141

Contrasting

Order By: Relevance

“…Such tools are open to a range of subjective biases including the skill and experience of a clinician and the reliability of a patient's own insights on their current mental state [2]. With the aim of enhancing current diagnostic techniques, investigations into new approaches for objectively detecting and monitoring depression based on measurable biological, physiological or behavioural signals are a highly active and growing area of research [3][4][5][6].…”

Section: Introductionmentioning

confidence: 99%

Implementing Gender-Dependent Vowel-Level Analysis for Boosting Speech-Based Depression Recognition

et al. 2017

View full text Add to dashboard Cite

Whilst studies on emotion recognition show that genderdependent analysis can improve emotion classification performance, the potential differences in the manifestation of depression between male and female speech have yet to be fully explored. This paper presents a qualitative analysis of phonetically aligned acoustic features to highlight differences in the manifestation of depression. Gender-dependent analysis with phonetically aligned gender-dependent features are used for speech-based depression recognition. The presented experimental study reveals gender differences in the effect of depression on vowel-level features. Considering the experimental study, we also show that a small set of knowledge-driven gender-dependent vowel-level features can outperform state-of-the-art turn-level acoustic features when performing a binary depressed speech recognition task. A combination of these preselected gender-dependent vowel-level features with turn-level standardised openSMILE features results in additional improvement for depression recognition.

show abstract

Section: Introductionmentioning

confidence: 99%

Implementing Gender-Dependent Vowel-Level Analysis for Boosting Speech-Based Depression Recognition

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Facial expressions convey information about an individual's experience of depression in straightforward ways. For example, Girard and colleagues found that participants with elevated depressive symptoms expressed fewer smiles and more signifiers of disgust [21]. Capturing these indicators of mood in a person's facial expressions has become much more efficient and affordable in recent years with the advent of automated facial analysis [22].…”

Section: Justificationmentioning

confidence: 99%

The Effortless Assessment of Risk States (EARS) Tool: An Interpersonal Approach to Mobile Sensing (Preprint)

Lind¹,

Byrne²,

Wicks³

et al. 2018

Preprint

View full text Add to dashboard Cite

Background: To predict and prevent mental health crises, we must develop new approaches that can provide a dramatic advance in the effectiveness, timeliness, and scalability of our interventions. Current methods of predicting mental health crises (e.g., clinical monitoring, screening) usually fail on most, if not all, of these criteria. Lucky for us, 77% of Americans carry with them an unprecedented opportunity to detect risk states and provide precise, life-saving interventions. Smart phones represent an opportunity to empower individuals to leverage the data they generate through their normal phone use to predict and prevent mental health crises. Objective: We believe that with enough high-quality, passive mobile sensing data, we may be able to generate predictive machine learning algorithms to solve previously intractable problems and identify risk states before they become crises. To test this hypothesis, our team built the Effortless Assessment of Risk States (EARS) tool. Methods: The EARS tool captures multiple indices of a person's social and affective behavior via their naturalistic use of a smart phone. These indices include facial expressions, acoustic vocal quality, natural language use, physical activity, music choice, and geographical location, among others. Critically, the EARS tool collects these data passively, with almost no burden on the user. We programmed the EARS tool in Java for the Android mobile platform. In building the EARS tool, we concentrated on two main considerations: (1) privacy and encryption and (2) phone use impact. Results: In a pilot study (N = 24), participants tolerated the EARS tool well, reporting minimal burden. None of the participants who completed the study reported needing to use the provided battery packs. Current testing on a range of phones indicated the tool will consume approximately 15% of the battery over a 16 hour period. Installation of the EARS tool causes minimal change in the UI/UX. Once installation is completed, the only difference the user will notice is the custom keyboard. Conclusions: The EARS tool offers an innovative approach to passive mobile sensing by emphasizing the centrality of a person's social life to their well-being. We built the EARS tool to

show abstract

“…The implicit cues consists of a set of vocal cues (Murray & Arnott 1993) (Girard and Cohn 2014), latency to speak, pauses. These approaches may also be combined in order to have a more natural and error-prone interaction (Lee & Naranyan 2005, Irastorza 2016).…”

Section: Emotion Recognition From Speech Signalsmentioning

confidence: 99%

Engagement with Artificial Intelligence through Natural Interaction Models

Feldman

Yalçın

DiPaola

2017

Electronic Workshops in Computing

View full text Add to dashboard Cite

As Artificial Intelligence (AI) systems become more ubiquitous, what user experience design paradigms will be used by humans to impart their needs and intents to an AI system, in order to engage in a more social interaction? In our work, we look mainly at expression and creativity based systems, where the AI both attempts to model or understand/assist in processes of human expression and creativity. We therefore have designed and implemented a prototype system with more natural interaction modes for engagement with AI as well as other human computer interaction (HCI) where a more open natural communication stream is beneficial. Our proposed conversational agent system makes use of the affective signals from the gestural behaviour of the user and the semantic information from the speech input in order to generate a personalised, human-like conversation that is expressed in the visual and conversational output of the 3D virtual avatar system. We describe our system and two application spaces we are using it in -a care advisor / assistant for the elderly and an interactive creative assistant for uses to produce art forms.Artificial Intelligence. Natural user interfaces. Voice systems. Expression systems. ChatBots.

show abstract

Nonverbal social withdrawal in depression: Evidence from manual and automatic analyses

Cited by 211 publications

References 85 publications

Implementing Gender-Dependent Vowel-Level Analysis for Boosting Speech-Based Depression Recognition

Implementing Gender-Dependent Vowel-Level Analysis for Boosting Speech-Based Depression Recognition

The Effortless Assessment of Risk States (EARS) Tool: An Interpersonal Approach to Mobile Sensing (Preprint)

Engagement with Artificial Intelligence through Natural Interaction Models

Contact Info

Product

Resources

About