Inferring Depression and Affect from Application Dependent Meta Knowledge

Kächele, Markus; Schels, Martin; Schwenker, Friedhelm

doi:10.1145/2661806.2661813

Cited by 36 publications

(17 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It was also compared with all the stateof-the-art methods in the AVEC2014 affect recognition subchallenge with fairly good performance. NLPR [4], SAIL [9], BU-CMPE [11] and our method achieve better performance than baseline method, while Ulm [10] achieves best performance. However, it utilized extra information on subjects and annotation process that is not comparable with other methods.…”

Section: Conclusion and Discussionmentioning

confidence: 86%

“…The single modality regressors are then combined using particle filtering, by treating these independent regression outputs as measurements of the affective states in a Bayesian filtering framework, where previous observations provide prediction about the current state by means of learned affect dynamics. At AVEC2014 affect recognition sub-challenge, the temporal relations in naturalistic expressions was used to boost the performance in decision level filtering [10] [9]. Kachele et al [10] proposed an approach based on abstract meta information about individual subjects and also prototypical task and label dependent templates to infer the respective emotional states and achieved the best performance.…”

Section: Related Workmentioning

confidence: 99%

“…At AVEC2014 affect recognition sub-challenge, the temporal relations in naturalistic expressions was used to boost the performance in decision level filtering [10] [9]. Kachele et al [10] proposed an approach based on abstract meta information about individual subjects and also prototypical task and label dependent templates to infer the respective emotional states and achieved the best performance. Gupta et al [9] proposed a 4-stage system including individual training, prediction processing, system fusion and temporal regression.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Automatic affective dimension recognition from naturalistic facial expressions based on wavelet filtering and PLS regression

Gaus

Meng

Jan

et al. 2015

2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)

View full text Add to dashboard Cite

Abstract-Automatic affective dimension recognition from facial expression continuously in naturalistic contexts is a very challenging research topic but very important in humancomputer interaction. In this paper, an automatic recognition system was proposed to predict the affective dimensions such as Arousal, Valence and Dominance continuously in naturalistic facial expression videos. Firstly, visual and vocal features are extracted from image frames and audio segments in facial expression videos. Secondly, a wavelet transform based digital filtering method is applied to remove the irrelevant noise information in the feature space. Thirdly, Partial Least Squares regression is used to predict the affective dimensions from both video and audio modalities. Finally, two modalities are combined to boost overall performance in the decision fusion process. The proposed method is tested in the fourth international Audio/Visual Emotion Recognition Challenge (AVEC2014) dataset and compared to other state-of-the-art methods in the affect recognition sub-challenge with a good performance.

show abstract

Section: Conclusion and Discussionmentioning

confidence: 86%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Automatic affective dimension recognition from naturalistic facial expressions based on wavelet filtering and PLS regression

Gaus

Meng

Jan

et al. 2015

2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)

View full text Add to dashboard Cite

show abstract

“…One could argue that this is not necessary as the different subjects are arriving in a, in a sense, "neutral" affective state at the experiment which is subsequently altered in the course of the recording. There is, however, little evidence for this assumption and also the costs that come with this approach are notable: it tends to result in very characteristic label traces that exhibit a transient phase (Glodek et al, 2012;Kächele et al, 2014). An example for such traces can be seen in Figure 5 where the continuous average labels of the AVEC 2012 and 2014 data sets are denoted together with the frame-wise variances over all sequences.…”

Section: Time-dependent Effectsmentioning

confidence: 99%

“…These variances are present in all channels but most prominently in physiological data and they diminish the classification performance especially when conducting leave-one-subject-out experiments . Performing subject-dependent classification experiments, on the other hand, however, yields comparably high accuracies, often fueled by multiple of the shortcomings in the recording (Walter et al, 2013a;Williamson et al, 2013;Kächele et al, 2014). For example, for subject-dependent classification using physiological signals in an experimental setting with blocked stimuli, classification can work exceptionally well because artifacts from the different blocks might dominate the outcome.…”

Section: Subject Dependencies and Evaluation Of Classification Experimentioning

confidence: 99%

The Influence of Annotation, Corpus Design, and Evaluation on the Outcome of Automatic Classification of Human Emotions

2016

Self Cite

View full text Add to dashboard Cite

The integration of emotions into human-computer interaction applications promises a more natural dialog between the user and the technical system operators. In order to construct such machinery, continuous measuring of the affective state of the user becomes essential. While basic research that is aimed to capture and classify affective signals has progressed, many issues are still prevailing that hinder easy integration of affective signals into human-computer interaction. In this paper, we identify and investigate pitfalls in three steps of the work-flow of affective classification studies. It starts with the process of collecting affective data for the purpose of training suitable classifiers. Emotional data have to be created in which the target emotions are present. Therefore, human participants have to be stimulated suitably. We discuss the nature of these stimuli, their relevance to human-computer interaction, and the repeatability of the data recording setting. Second, aspects of annotation procedures are investigated, which include the variances of individual raters, annotation delay, the impact of the used annotation tool, and how individual ratings are combined to a unified label. Finally, the evaluation protocol is examined, which includes, among others, the impact of the performance measure on the accuracy of a classification model. We hereby focus especially on the evaluation of classifier outputs against continuously annotated dimensions. Together with the discussed problems and pitfalls and the ways how they affect the outcome, we provide solutions and alternatives to overcome these issues. As the final part of the paper, we sketch a recording scenario and a set of supporting technologies that can contribute to solve many of the issues mentioned above.

show abstract

Automated assessment of psychiatric disorders using speech: A systematic review

Low

Bentley

Ghosh

2020

Laryngoscope Investig Oto

289

268

View full text Add to dashboard Cite

Objective There are many barriers to accessing mental health assessments including cost and stigma. Even when individuals receive professional care, assessments are intermittent and may be limited partly due to the episodic nature of psychiatric symptoms. Therefore, machine‐learning technology using speech samples obtained in the clinic or remotely could one day be a biomarker to improve diagnosis and treatment. To date, reviews have only focused on using acoustic features from speech to detect depression and schizophrenia. Here, we present the first systematic review of studies using speech for automated assessments across a broader range of psychiatric disorders. Methods We followed the Preferred Reporting Items for Systematic Reviews and Meta‐Analysis (PRISMA) guidelines. We included studies from the last 10 years using speech to identify the presence or severity of disorders within the Diagnostic and Statistical Manual of Mental Disorders (DSM‐5). For each study, we describe sample size, clinical evaluation method, speech‐eliciting tasks, machine learning methodology, performance, and other relevant findings. Results 1395 studies were screened of which 127 studies met the inclusion criteria. The majority of studies were on depression, schizophrenia, and bipolar disorder, and the remaining on post‐traumatic stress disorder, anxiety disorders, and eating disorders. 63% of studies built machine learning predictive models, and the remaining 37% performed null‐hypothesis testing only. We provide an online database with our search results and synthesize how acoustic features appear in each disorder. Conclusion Speech processing technology could aid mental health assessments, but there are many obstacles to overcome, especially the need for comprehensive transdiagnostic and longitudinal studies. Given the diverse types of data sets, feature extraction, computational methodologies, and evaluation criteria, we provide guidelines for both acquiring data and building machine learning models with a focus on testing hypotheses, open science, reproducibility, and generalizability. Level of Evidence 3a

show abstract

Inferring Depression and Affect from Application Dependent Meta Knowledge

Cited by 36 publications

References 54 publications

Automatic affective dimension recognition from naturalistic facial expressions based on wavelet filtering and PLS regression

Automatic affective dimension recognition from naturalistic facial expressions based on wavelet filtering and PLS regression

The Influence of Annotation, Corpus Design, and Evaluation on the Outcome of Automatic Classification of Human Emotions

Automated assessment of psychiatric disorders using speech: A systematic review

Contact Info

Product

Resources

About