{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T23:21:52Z","timestamp":1781306512403,"version":"3.54.1"},"reference-count":51,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2022,8,11]],"date-time":"2022-08-11T00:00:00Z","timestamp":1660176000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/publicdomain\/zero\/1.0\/"}],"funder":[{"name":"Ministry of Science and ICT (MSIT) Korea"},{"name":"Department of Biotechnology,India","award":["DBT\/IC-12031(22)-ICD-DBT"],"award-info":[{"award-number":["DBT\/IC-12031(22)-ICD-DBT"]}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation (NRF) Korea","doi-asserted-by":"crossref","award":["2020K1A3A1A68093469"],"award-info":[{"award-number":["2020K1A3A1A68093469"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>Depression is one of the significant mental health issues affecting all age groups globally. While it has been widely recognized to be one of the major disease burdens in populations, complexities in definitive diagnosis present a major challenge. Usually, trained psychologists utilize conventional methods including individualized interview assessment and manually administered PHQ-8 scoring. However, heterogeneity in symptomatic presentations, which span somatic to affective complaints, impart substantial subjectivity in its diagnosis. Diagnostic accuracy is further compounded by the cross-sectional nature of sporadic assessment methods during physician-office visits, especially since depressive symptoms\/severity may evolve over time. With widespread acceptance of smart wearable devices and smartphones, passive monitoring of depression traits using behavioral signals such as speech presents a unique opportunity as companion diagnostics to assist the trained clinicians in objective assessment over time. Therefore, we propose a framework for automated depression classification leveraging alterations in speech patterns in the well documented and extensively studied DAIC-WOZ depression dataset. This novel tensor-based approach requires a substantially simpler implementation architecture and extracts discriminative features for depression recognition with high f1 score and accuracy. We posit that such algorithms, which use significantly less compute load would allow effective onboard deployment in wearables for improve diagnostics accuracy and real-time monitoring of depressive disorders.<\/jats:p>","DOI":"10.1371\/journal.pone.0272659","type":"journal-article","created":{"date-parts":[[2022,8,11]],"date-time":"2022-08-11T17:29:10Z","timestamp":1660238950000},"page":"e0272659","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":6,"title":["A deep tensor-based approach for automatic depression recognition from speech utterances"],"prefix":"10.1371","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1995-6515","authenticated-orcid":true,"given":"Sandeep Kumar","family":"Pandey","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanumant Singh","family":"Shekhawat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"S. R. M.","family":"Prasanna","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shalendar","family":"Bhasin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ravi","family":"Jasuja","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2022,8,11]]},"reference":[{"key":"pone.0272659.ref001","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1016\/j.specom.2015.03.004","article-title":"A review of depression and suicide risk assessment using speech analysis","volume":"71","author":"Nicholas Cummins","year":"2015","journal-title":"Speech Communication"},{"issue":"11","key":"pone.0272659.ref002","doi-asserted-by":"crossref","first-page":"e442","DOI":"10.1371\/journal.pmed.0030442","article-title":"Projections of global mortality and burden of disease from 2002 to 2030","volume":"3","author":"Colin D Mathers","year":"2006","journal-title":"PLoS medicine"},{"issue":"1-3","key":"pone.0272659.ref003","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/j.jad.2013.01.004","article-title":"Risk factors for suicide in individuals with depression: a systematic review","volume":"147","author":"Keith Hawton","year":"2013","journal-title":"Journal of affective disorders"},{"issue":"3","key":"pone.0272659.ref004","doi-asserted-by":"crossref","first-page":"207","DOI":"10.30773\/pi.2019.0171","article-title":"Understanding the complex of suicide in depression: from research to clinics","volume":"17","author":"Laura Orsolini","year":"2020","journal-title":"Psychiatry investigation"},{"issue":"1","key":"pone.0272659.ref005","first-page":"1","article-title":"Critical appraisal of major depression with suicidal ideation","volume":"18","author":"Maurizio Pompili","year":"2019","journal-title":"Annals of general psychiatry"},{"key":"pone.0272659.ref006","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1007\/978-3-642-70486-4_14","volume-title":"Assessment of depression","author":"Max Hamilton","year":"1986"},{"key":"pone.0272659.ref007","doi-asserted-by":"crossref","unstructured":"Kurt Kroenke and Robert L Spitzer. The PHQ-9: a new depression diagnostic and severity measure. 2002.","DOI":"10.3928\/0048-5713-20020901-06"},{"issue":"2","key":"pone.0272659.ref008","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1002\/wps.20229","article-title":"What has serotonin to do with depression?","volume":"14","author":"Philip J Cowen","year":"2015","journal-title":"World Psychiatry"},{"issue":"3","key":"pone.0272659.ref009","doi-asserted-by":"crossref","first-page":"818","DOI":"10.1016\/j.neubiorev.2010.10.002","article-title":"Evidence for GABAergic inhibitory deficits in major depressive disorder","volume":"35","author":"Paul E Croarkin","year":"2011","journal-title":"Neuroscience & Biobehavioral Reviews"},{"key":"pone.0272659.ref010","doi-asserted-by":"crossref","unstructured":"Sharifa Alghowinem et al. \u201cEye movement analysis for depression detection\u201d. In: 2013 IEEE International Conference on Image Processing. IEEE. 2013, pp. 4220-4224.","DOI":"10.1109\/ICIP.2013.6738869"},{"key":"pone.0272659.ref011","unstructured":"Jeffrey F Cohn et al. \u201cDetecting depression from facial actions and vocal prosody\u201d. In: 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops. IEEE. 2009, pp. 1-7."},{"issue":"3","key":"pone.0272659.ref012","doi-asserted-by":"crossref","first-page":"227","DOI":"10.2174\/157340012800792966","article-title":"Verbal and nonverbal correlates for depression: a review","volume":"8","author":"Martin JH Balsters","year":"2012","journal-title":"Current Psychiatry Reviews"},{"issue":"3","key":"pone.0272659.ref013","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1016\/S0272-7358(98)00104-4","article-title":"Social skills deficits associated with depression","volume":"20","author":"Chris Segrin","year":"2000","journal-title":"Clinical psychology review"},{"key":"pone.0272659.ref014","doi-asserted-by":"crossref","unstructured":"Sharifa Alghowinem et al. \u201cCharacterising depressed speech for classification\u201d. In: (2013).","DOI":"10.21437\/Interspeech.2013-571"},{"key":"pone.0272659.ref015","unstructured":"Sharifa Alghowinem et al. \u201cFrom Joyous to Clinically Depressed: Mood Detection Using Spontaneous Speech.\u201d In: FLAIRS Conference. Vol. 19. Citeseer. 2012."},{"key":"pone.0272659.ref016","doi-asserted-by":"crossref","unstructured":"Hailiang Long et al. \u201cDetecting depression in speech: Comparison and combination between different speech types\u201d. In: 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). IEEE. 2017, pp. 1052-1058.","DOI":"10.1109\/BIBM.2017.8217802"},{"key":"pone.0272659.ref017","doi-asserted-by":"crossref","unstructured":"Soheil Khorram et al. \u201cThe priori emotion dataset: Linking mood to emotion detected in-the-wild\u201d. In: arXiv preprint arXiv:1806.10658 (2018).","DOI":"10.21437\/Interspeech.2018-2355"},{"key":"pone.0272659.ref018","doi-asserted-by":"crossref","unstructured":"Nicholas Cummins et al. \u201cAn investigation of depressed speech detection: Features and normalization\u201d. In: Twelfth Annual Conference of the International Speech Communication Association. 2011.","DOI":"10.21437\/Interspeech.2011-750"},{"issue":"4","key":"pone.0272659.ref019","doi-asserted-by":"crossref","first-page":"478","DOI":"10.1109\/TAFFC.2016.2634527","article-title":"Multimodal Depression Detection: Fusion Analysis of Paralinguistic, Head Pose and Eye Gaze Behaviors","volume":"9","author":"S. Alghowinem","year":"2018","journal-title":"IEEE Transactions on Affective Computing"},{"key":"pone.0272659.ref020","doi-asserted-by":"crossref","unstructured":"Le Yang et al. \u201cDCNN and DNN based multi-modal depression recognition\u201d. In: 2017 Seventh International Conference on Affective Computing and Intelligent Interaction (ACII). IEEE. 2017, pp. 484-489.","DOI":"10.1109\/ACII.2017.8273643"},{"key":"pone.0272659.ref021","first-page":"1","article-title":"Integrating Deep and Shallow Models for Multi-Modal Depression Analysis\u2014Hybrid Architectures","author":"L. Yang","year":"2018","journal-title":"IEEE Transactions on Affective Computing"},{"key":"pone.0272659.ref022","doi-asserted-by":"crossref","unstructured":"Md Nasir et al. \u201cMultimodal and multiresolution depression detection from speech and facial landmark features\u201d. In: Proceedings of the 6th international workshop on audio\/visual emotion challenge. 2016, pp. 43-50.","DOI":"10.1145\/2988257.2988261"},{"key":"pone.0272659.ref023","doi-asserted-by":"crossref","unstructured":"Tuka Al Hanai, Mohammad M Ghassemi, and James R Glass. \u201cDetecting Depression with Audio\/Text Sequence Modeling of Interviews.\u201d In: Interspeech. 2018, pp. 1716-1720.","DOI":"10.21437\/Interspeech.2018-2522"},{"key":"pone.0272659.ref024","unstructured":"M Sharifa et al. \u201cFrom joyous to clinically depressed: Mood detection using spontaneous speech\u201d. In: Twenty-Fifth International FLAIRS Conference. 2012."},{"key":"pone.0272659.ref025","doi-asserted-by":"crossref","first-page":"1258","DOI":"10.1016\/j.procs.2020.03.442","article-title":"Predicting anxiety, depression and stress in modern life using machine learning algorithms","volume":"167","author":"Anu Priya","year":"2020","journal-title":"Procedia Computer Science"},{"key":"pone.0272659.ref026","doi-asserted-by":"crossref","unstructured":"Sandeep Kumar Pandey et al. \u201cAlzheimer\u2019s Dementia Recognition Using Multimodal Fusion of Speech and Text Embeddings\u201d. In: International Conference on Intelligent Human Computer Interaction. Springer. 2021, pp. 718-728.","DOI":"10.1007\/978-3-030-98404-5_64"},{"key":"pone.0272659.ref027","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1016\/j.inffus.2021.10.012","article-title":"Deep learning for depression recognition with audiovisual cues: A review","volume":"80","author":"Lang He","year":"2022","journal-title":"Information Fusion"},{"key":"pone.0272659.ref028","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.procs.2020.04.003","article-title":"An End-to-End Model for Detection and Assessment of Depression Levels using Speech","volume":"171","author":"NS Srimadhur","year":"2020","journal-title":"Procedia Computer Science"},{"key":"pone.0272659.ref029","unstructured":"Xingchen Ma et al. \u201cDepaudionet: An efficient deep model for audio based depression classification\u201d. In: Proceedings of the 6th international workshop on audio\/visual emotion challenge. 2016, pp. 35-42."},{"issue":"6","key":"pone.0272659.ref030","doi-asserted-by":"crossref","first-page":"688","DOI":"10.3390\/e22060688","article-title":"Automatic Detection of Depression in Speech Using Ensemble Convolutional Neural Networks","volume":"22","author":"Adri\u00e1n Vazquez-Romero","year":"2020","journal-title":"Entropy"},{"key":"pone.0272659.ref031","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1016\/j.nicl.2015.11.003","article-title":"Studying depression using imaging and machine learning methods","author":"Meenal J Patel","year":"2016","journal-title":"NeuroImage: Clinical"},{"key":"pone.0272659.ref032","unstructured":"Akkapon Wongkoblap, Miguel A Vadillo, and Vasa Curcin. \u201cModeling depression symptoms from social network data through multiple instance learning\u201d. In: AMIA Summits on Translational Science Proceedings 2019 (2019), p. 44."},{"issue":"2","key":"pone.0272659.ref033","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3214284","article-title":"A weakly supervised learning framework for detecting social anxiety and depression","volume":"2","author":"Asif Salekin","year":"2018","journal-title":"Proceedings of the ACM on interactive, mobile, wearable and ubiquitous technologies"},{"issue":"3","key":"pone.0272659.ref034","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1137\/07070111X","article-title":"Tensor decompositions and applications","volume":"51","author":"Tamara G Kolda","year":"2009","journal-title":"SIAM review"},{"issue":"2","key":"pone.0272659.ref035","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1109\/MSP.2013.2297439","article-title":"Tensor decompositions for signal processing applications: From two-way to multiway component analysis","volume":"32","author":"Andrzej Cichocki","year":"2015","journal-title":"IEEE Signal Processing Magazine"},{"issue":"7","key":"pone.0272659.ref036","doi-asserted-by":"crossref","first-page":"1540","DOI":"10.1016\/j.patcog.2011.01.004","article-title":"A survey of multilinear subspace learning for tensor data","volume":"44","author":"Haiping Lu","year":"2011","journal-title":"Pattern Recognition"},{"issue":"13","key":"pone.0272659.ref037","doi-asserted-by":"crossref","first-page":"3551","DOI":"10.1109\/TSP.2017.2690524","article-title":"Tensor decomposition for signal processing and machine learning","volume":"65","author":"Nicholas D Sidiropoulos","year":"2017","journal-title":"IEEE Transactions on Signal Processing"},{"key":"pone.0272659.ref038","volume-title":"Multilinear subspace learning: dimensionality reduction of multidimensional data","author":"Haiping Lu","year":"2013"},{"key":"pone.0272659.ref039","unstructured":"Jonathan Gratch et al. \u201cThe distress analysis interview corpus of human and computer interviews\u201d. In: Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC\u201914). 2014, pp. 3123-3128."},{"key":"pone.0272659.ref040","doi-asserted-by":"crossref","unstructured":"Michel Valstar et al. \u201cAvec 2016: Depression, mood, and emotion recognition workshop and challenge\u201d. In: Proceedings of the 6th international workshop on audio\/visual emotion challenge. 2016, pp. 3-10.","DOI":"10.1145\/2988257.2988258"},{"issue":"12","key":"pone.0272659.ref041","article-title":"pyAudioAnalysis: An Open-Source Python Library for Audio Signal Analysis","volume":"10","author":"Theodoros Giannakopoulos","year":"2015","journal-title":"PloS one"},{"issue":"5","key":"pone.0272659.ref042","doi-asserted-by":"crossref","first-page":"1998","DOI":"10.1109\/TNNLS.2017.2690379","article-title":"Tensor-factorized neural networks","volume":"29","author":"Jen-Tzung Chien","year":"2017","journal-title":"IEEE transactions on neural networks and learning systems"},{"key":"pone.0272659.ref043","doi-asserted-by":"crossref","unstructured":"David Snyder et al. \u201cX-vectors: Robust dnn embeddings for speaker recognition\u201d. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE. 2018, pp. 5329-5333.","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"pone.0272659.ref044","doi-asserted-by":"crossref","unstructured":"Shuiyang Mao, PC Ching, and Tan Lee. \u201cDeep Learning of Segment-Level Feature Representation with Multiple Instance Learning for Utterance-Level Speech Emotion Recognition.\u201d In: Interspeech. 2019, pp. 1686-1690.","DOI":"10.21437\/Interspeech.2019-1968"},{"key":"pone.0272659.ref045","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1016\/j.patcog.2017.10.009","article-title":"Multiple instance learning: A survey of problem characteristics and applications","volume":"77","author":"Marc-Andre Carbonneau","year":"2018","journal-title":"Pattern Recognition"},{"key":"pone.0272659.ref046","doi-asserted-by":"crossref","first-page":"103173","DOI":"10.1016\/j.bspc.2021.103173","article-title":"Attention gated tensor neural network architectures for speech emotion recognition","volume":"71","author":"Sandeep Kumar Pandey","year":"2022","journal-title":"Biomedical Signal Processing and Control"},{"issue":"10","key":"pone.0272659.ref047","doi-asserted-by":"crossref","first-page":"1440","DOI":"10.1109\/LSP.2018.2860246","article-title":"3-D convolutional recurrent neural networks with attention model for speech emotion recognition","volume":"25","author":"Mingyi Chen","year":"2018","journal-title":"IEEE Signal Processing Letters"},{"key":"pone.0272659.ref048","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4612-6333-3","volume-title":"A practical guide to splines","author":"Carl De Boor","year":"1978"},{"key":"pone.0272659.ref049","first-page":"106433","volume-title":"Computer Methods and Programs in Biomedicine","author":"Muhammad Muzammel","year":"2021"},{"key":"pone.0272659.ref050","doi-asserted-by":"crossref","unstructured":"Sandeep Kumar Pandey, Hanumant Singh Shekhawat, and SR Mahadeva Prasanna. \u201cDeep learning techniques for speech emotion recognition: A review\u201d. In: 2019 29th International Conference Radioelektronika (RADIOELEKTRONIKA). IEEE. 2019, pp. 1-6.","DOI":"10.1109\/RADIOELEK.2019.8733432"},{"key":"pone.0272659.ref051","article-title":"Cough recognition based on mel-spectrogram and convolutional neural network","volume":"8","author":"Quan Zhou","year":"2021","journal-title":"Frontiers in Robotics and AI"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0272659","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T07:07:17Z","timestamp":1727766437000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0272659"}},"subtitle":[],"editor":[{"given":"Dhananjay","family":"Singh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2022,8,11]]},"references-count":51,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2022,8,11]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0272659","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,11]]}}}