Recognition of Depression in Bipolar Disorder: Leveraging Cohort and Person-Specific Knowledge

Khorram, Soheil; Gideon, John; McInnis, Melvin G.; Provost, Emily Mower

doi:10.21437/interspeech.2016-837

Cited by 19 publications

(15 citation statements)

References 27 publications

(59 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The PRIORI Emotion dataset is an affect-annotated subset of the larger PRIORI (Predicting Individual Outcomes for Rapid Intervention) bipolar mood dataset, which includes smartphone calls from 51 patients and 9 healthy controls over the course of six-months to a year [5], [41], [42], [43]. The PRIORI Emotion dataset was obtained by first automatically segmenting the PRIORI dataset using the COMBO-SAD algorithm [44], as described in our prior work [5].…”

Section: Priori Emotion Datasetmentioning

confidence: 99%

See 1 more Smart Citation

Improving Cross-Corpus Speech Emotion Recognition with Adversarial Discriminative Domain Generalization (ADDoG)

Gideon

McInnis

Provost

2021

IEEE Trans. Affective Comput.

Self Cite

View full text Add to dashboard Cite

Automatic speech emotion recognition provides computers with critical context to enable user understanding. While methods trained and tested within the same dataset have been shown successful, they often fail when applied to unseen datasets. To address this, recent work has focused on adversarial methods to find more generalized representations of emotional speech. However, many of these methods have issues converging, and only involve datasets collected in laboratory conditions. In this paper, we introduce Adversarial Discriminative Domain Generalization (ADDoG), which follows an easier to train "meet in the middle" approach. The model iteratively moves representations learned for each dataset closer to one another, improving cross-dataset generalization. We also introduce Multiclass ADDoG, or MADDoG, which is able to extend the proposed method to more than two datasets, simultaneously. Our results show consistent convergence for the introduced methods, with significantly improved results when not using labels from the target dataset. We also show how, in most cases, ADDoG and MADDoG can be used to improve upon baseline state-of-the-art methods when target dataset labels are added and in-the-wild data are considered. Even though our experiments focus on cross-corpus speech emotion, these methods could be used to remove unwanted factors of variation in other settings. , and a co-author of the winner of the Classifier Sub-Challenge event at the Interspeech 2009 emotion challenge. Her research interests are in human-centered speech and video processing, multimodal interfaces design, and speech-based assistive technology. The goals of her research are motivated by the complexities of the perception and expression of human behavior.

show abstract

Section: Priori Emotion Datasetmentioning

confidence: 99%

“…We downsampled this dataset, selecting segments for which all assigned annotators were able to provide a rating, resulting in a dataset with 11,402 utterances over 21.7 hours. See Khorram et al [41] for further information about the PRIORI Emotion dataset and [5], [42], [43] for the PRIORI bipolar mood dataset.…”

Section: Priori Emotion Datasetmentioning

confidence: 99%

Improving Cross-Corpus Speech Emotion Recognition with Adversarial Discriminative Domain Generalization (ADDoG)

Gideon

McInnis

Provost

2021

IEEE Trans. Affective Comput.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Muaremi et al in [11] used statistics of phone calls, such as duration and frequency, to predict mood episodes. Our own work has demonstrated that properties such as speaking rate are also effective for detecting mood [12,13]. However, a recurring theme in these studies is the challenge associated with detecting mood directly from speech, due in part to the highly varying nature of the speech signal.…”

Section: Introductionmentioning

confidence: 99%

The PRIORI Emotion Dataset: Linking Mood to Emotion Detected In-the-Wild

Khorram¹,

Jaiswal²,

Gideon³

et al. 2018

Interspeech 2018

Self Cite

View full text Add to dashboard Cite

Bipolar Disorder is a chronic psychiatric illness characterized by pathological mood swings associated with severe disruptions in emotion regulation. Clinical monitoring of mood is key to the care of these dynamic and incapacitating mood states. Frequent and detailed monitoring improves clinical sensitivity to detect mood state changes, but typically requires costly and limited resources. Speech characteristics change during both depressed and manic states, suggesting automatic methods applied to the speech signal can be effectively used to monitor mood state changes. However, speech is modulated by many factors, which renders mood state prediction challenging. We hypothesize that emotion can be used as an intermediary step to improve mood state prediction. This paper presents critical steps in developing this pipeline, including (1) a new in the wild emotion dataset, the PRIORI Emotion Dataset, collected from everyday smartphone conversational speech recordings, (2) activation/valence emotion recognition baselines on this dataset (PCC of 0.71 and 0.41, respectively), and (3) significant correlation between predicted emotion and mood state for individuals with bipolar disorder. This provides evidence and a working baseline for the use of emotion as a meta-feature for mood state monitoring.

show abstract

“…Several mental health monitoring approaches using mobile devices have been proposed. Most of them [1][2][3][5][6][7][8][9][10][11]13,14] are based on (1) collecting and analyzing smartphone features such as activity, localization, and phone calls, and (2) launching interactive questionnaires such as PHQ-9 3 and BDI 4 . "Active" monitoring approaches (i.e., requiring a patient's intervention) are less used and less effective than "passive" ones (i.e., not requiring a patient's intervention) in practice.…”

Section: Introductionmentioning

confidence: 99%

“…Passive monitoring approaches [3,[5][6][7][8]10,11,13,14] can be divided into two categories. The first category tries to use most of the smartphone's sensors, such as accelerometer and camera, to collect related features [5][6][7]11,14].…”

Section: Introductionmentioning

confidence: 99%

DL4DED: Deep Learning for Depressive Episode Detection on Mobile Devices

Mdhaffar

Cherif²,

Kessentini

et al. 2019

How AI Impacts Urban Living and Public Health

View full text Add to dashboard Cite

This paper presents a deep learning approach for depressive episode detection on mobile devices, called DL4DED. It is based on a convolutional neural network and a long short-term memory network to identify the status of a patient's voice extracted from spontaneous phone calls. To run DL4DED on mobile devices, two neural network model compression techniques are used: quantization and pruning. DL4DED protects data privacy, since it can be executed on a patient's smartphone. Our proposal is validated on the DAIC-WOZ database. The obtained results show that the accuracy of DL4DED with model compression is only slightly lower than the accuracy of DL4DED without model compression. Furthermore, our experiments indicate that the power consumption of DL4DED is reasonably low.

show abstract

Recognition of Depression in Bipolar Disorder: Leveraging Cohort and Person-Specific Knowledge

Cited by 19 publications

References 27 publications

Improving Cross-Corpus Speech Emotion Recognition with Adversarial Discriminative Domain Generalization (ADDoG)

Improving Cross-Corpus Speech Emotion Recognition with Adversarial Discriminative Domain Generalization (ADDoG)

The PRIORI Emotion Dataset: Linking Mood to Emotion Detected In-the-Wild

DL4DED: Deep Learning for Depressive Episode Detection on Mobile Devices

Contact Info

Product

Resources

About