{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T11:10:41Z","timestamp":1790161841112,"version":"4.1.0"},"reference-count":52,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T00:00:00Z","timestamp":1790121600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82460279"],"award-info":[{"award-number":["82460279"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013142","name":"Key Research and Development Project of Hainan Province","doi-asserted-by":"publisher","award":["ZDYF2024SHFZ073"],"award-info":[{"award-number":["ZDYF2024SHFZ073"]}],"id":[{"id":"10.13039\/501100013142","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004761","name":"Natural Science Foundation of Hainan Province","doi-asserted-by":"publisher","award":["624RC528"],"award-info":[{"award-number":["624RC528"]}],"id":[{"id":"10.13039\/501100004761","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007935","name":"Hainan Medical University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007935","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Psychiatry"],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Speech holds promise for depressive symptom screening, but practical applications require clearer guidance on effective segmentation, optimal speech tasks, minimum duration, and feature-model matching.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To enable low-burden screening for depressive symptoms, this study aims to evaluate the effectiveness of short speech samples and systematically investigate how to identify the optimal practical combination of different speech tasks, time-window lengths, and the matching between features and models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Using the HMU-DDAC-24 dataset of 143 participants aged 18\u201322 years, we evaluated 10 segmentation lengths (0.1\u201315 s), 5 models (Random Forest, Extreme Gradient Boosting (XGBoost), Long Short-Term Memory (LSTM), Transformer, Extended Long Short-Term Memory (xLSTM)), and 3 feature types (frame-level, statistical, fused). We also assessed 19 window lengths (1\u201335 s) across four speech tasks and their combinations. In addition, supplementary cross-dataset validation analysis was performed using the external Emotional Audio-Textual Depression (EATD) dataset.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Frame-level features performed best with sequence models and short windows (0.1\u20132 s; Transformer accuracy: 0.731 at 2 s). Statistical features paired best with tree models and short windows (Random Forest accuracy: 0.698 at 1 s). Fused features improved tree models (Random Forest accuracy: 0.703 at 4 s) but introduced noise into sequence models. Task 4 (positive recall) achieved the best overall performance (Area Under the Receiver Operating Characteristic Curve (AUC) = 0.860), outperforming all single and combined tasks, showing no multi-task synergy. A 1-s segment performed comparably to full-length speech (3.14% relative performance loss). Kullback-Leibler divergence analysis showed short segments closely approximated the full recording\u2019s distribution (Task 4 KL\u00a0=\u00a09.56 at 1 s).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>When combined with appropriate speech tasks and feature-model matching, short speech samples can facilitate low-burden screening for depressive symptoms. Supplementary analysis on the EATD dataset supported these trends, though absolute performance depended on feature representation. We recommend positive recall with 2-s truncation, frame-level features, and Transformer for accuracy-oriented settings; and 1-s truncation, statistical features, and Random Forest for resource-limited settings. These findings may inform rapid, remote speech-based screening for depressive symptoms, especially in resource-limited primary-care settings.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpsyt.2026.1888425","type":"journal-article","created":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T10:23:12Z","timestamp":1790158992000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Low-burden speech-based screening of depressive symptoms using ultra-short speech samples"],"prefix":"10.3389","volume":"17","author":[{"given":"Zhiguo","family":"Zheng","sequence":"first","affiliation":[{"name":"School of Information and Communication Engineering, Hainan University","place":["Haikou, China"]},{"name":"School of Information Engineering, Hainan Vocational University of Science and Technology","place":["Haikou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lijuan","family":"Liang","sequence":"additional","affiliation":[{"name":"Department of Psychology, The First Affiliated Hospital of Hainan Medical University","place":["Haikou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Intelligent Medicine and Technology (Big Data Research Center), Hainan Medical University","place":["Haikou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Qi","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Hainan Vocational University of Science and Technology","place":["Haikou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanjun","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronic Science and Technology, Hainan University","place":["Haikou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenyang","family":"Xue","sequence":"additional","affiliation":[{"name":"School of Electronic Science and Technology, Hainan University","place":["Haikou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,23]]},"reference":[{"key":"B1","volume-title":"World Mental Health Report: Transforming Mental Health for All","year":"2022"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.2217\/bmm-2016-0076","article-title":"Seeking an objective diagnosis of depression","volume":"10","author":"Bilello","year":"2016","journal-title":"biomark Med"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.comppsych.2012.06.006","article-title":"The diagnosis of depression: current and emerging methods","volume":"54","author":"Smith","year":"2013","journal-title":"Compr Psychiatry"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.2174\/1871527320666211213125847","article-title":"Speech as a biomarker for depression","volume":"22","author":"Koops","year":"2023","journal-title":"CNS Neurol Disord Drug Targets"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2023.1141621","article-title":"Ensemble learning with speaker embeddings in multiple speech task stimuli for depression detection","volume":"17","author":"Liu","year":"2023","journal-title":"Front Neurosci"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128209","article-title":"Attention-based acoustic feature fusion network for depression detection","volume":"601","author":"Xu","year":"2024","journal-title":"Neurocomputing"},{"key":"B7","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-311","article-title":"Vocal-source biomarkers for depression: a link to psychomotor activity","author":"Quatieri","year":"2012"},{"key":"B8","first-page":"65","article-title":"Vocal and facial biomarkers of depression based on motor incoordination and timing","author":"Williamson","year":"2014"},{"key":"B9","doi-asserted-by":"publisher","first-page":"794","DOI":"10.1186\/s12888-024-06253-6","article-title":"The voice of depression: speech features as biomarkers for major depressive disorder","volume":"24","author":"Menne","year":"2024","journal-title":"BMC Psychiatry"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.2478\/ecce-2014-0009","article-title":"Improving speech recognition rate through analysis parameters","volume":"5","author":"Eringis","year":"2014","journal-title":"Electr Control Commun Eng"},{"key":"B11","doi-asserted-by":"crossref","DOI":"10.1109\/DASA54658.2022.9765043","article-title":"An overview of automatic speech recognition preprocessing techniques","author":"Labied","year":"2022"},{"key":"B12","doi-asserted-by":"publisher","first-page":"992","DOI":"10.1109\/TAFFC.2020.2983669","article-title":"Multi-task semi-supervised adversarial autoencoding for speech emotion recognition","volume":"13","author":"Latif","year":"2022","journal-title":"IEEE Trans Affect Comput"},{"key":"B13","first-page":"1","article-title":"Depac: a corpus for depression and anxiety detection from speech","author":"Tasnim","year":"2022"},{"key":"B14","first-page":"1","article-title":"Speech-based clinical depression detection: an empirical study","author":"Chen","year":"2025"},{"key":"B15","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP40776.2020.9053207","article-title":"Hierarchical attention transfer networks for depression assessment from speech","author":"Zhao","year":"2020"},{"key":"B16","doi-asserted-by":"publisher","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":"Cummins","year":"2015","journal-title":"Speech Commun"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2021.103107","article-title":"MFCC-based recurrent neural network for automatic clinical depression recognition and assessment from speech","volume":"71","author":"Rejaibi","year":"2022","journal-title":"BioMed Signal Process Control"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1007\/s11036-022-02086-3","article-title":"Deep learning for depression recognition from speech","volume":"29","author":"Tian","year":"2024","journal-title":"Mobile Netw Appl"},{"key":"B19","first-page":"27","article-title":"Depression assessment by fusing high and low level features from audio, video, and text","author":"Pampouchidou","year":"2016"},{"key":"B20","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP43922.2022.9746569","article-title":"Automatic depression detection: an emotional audio-textual corpus and a GRU\/BiLSTM-based model","author":"Shen","year":"2022"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1155\/da\/4839334","article-title":"Method matters: enhancing voice-based depression detection with a new data collection framework","volume":"2025","author":"Vilenchik","year":"2025","journal-title":"Depress Anxiety"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1046\/j.1525-1497.2001.016009606.x","article-title":"The PHQ-9: validity of a brief depression severity measure","volume":"16","author":"Kroenke","year":"2001","journal-title":"J Gen Intern Med"},{"key":"B23","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2020-2888","article-title":"Spotting the traces of depression in read speech: an approach based on computational paralinguistics and social signal processing","author":"Tao","year":"2020"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0203574","article-title":"Depression history and memory bias for specific daily emotions","volume":"13","author":"Urban","year":"2018","journal-title":"PloS One"},{"key":"B25","doi-asserted-by":"publisher","first-page":"830","DOI":"10.1186\/s12888-022-04475-0","article-title":"Detecting subtle signs of depression with automated speech analysis in a non-clinical sample","volume":"22","author":"K\u00f6nig","year":"2022","journal-title":"BMC Psychiatry"},{"key":"B26","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1016\/j.brat.2017.02.005","article-title":"Engaging in an experiential processing mode increases positive emotional response during recall of pleasant autobiographical memories","volume":"92","author":"Gadeikis","year":"2017","journal-title":"Behav Res Ther"},{"key":"B27","first-page":"35","article-title":"Depaudionet: an efficient deep model for audio based depression classification","author":"Ma","year":"2016"},{"key":"B28","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1109\/TAFFC.2015.2457417","article-title":"The Geneva minimalistic acoustic parameter set (GeMAPS) for voice research and affective computing","volume":"7","author":"Eyben","year":"2016","journal-title":"IEEE Trans Affect Comput"},{"key":"B29","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP.2013.6639130","article-title":"Detecting depression: a comparison between spontaneous and read speech","author":"Alghowinem","year":"2013"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.2196\/34474","article-title":"Automatic depression detection using smartphone-based text-dependent speech signals: deep convolutional neural network approach","volume":"25","author":"Kim","year":"2023","journal-title":"J Med Internet Res"},{"key":"B31","doi-asserted-by":"crossref","DOI":"10.1109\/ISCAIT64916.2025.11010283","article-title":"Speech feature-based depression detection and interpretability analysis","author":"Zheng","year":"2025"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2957988","article-title":"Analysis and detection of pathological voice using glottal source features","volume":"14","author":"Kadiri","year":"2019","journal-title":"IEEE J Sel Top Signal Process"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-012-9166-0","article-title":"Speaker recognition utilizing distributed DCT-II based Mel frequency cepstral coefficients and fuzzy vector quantization","volume":"16","author":"Hossan","year":"2013","journal-title":"Int J Speech Technol"},{"key":"B34","doi-asserted-by":"crossref","DOI":"10.1109\/IALP54817.2021.9675271","article-title":"Research on depression recognition using machine learning from speech","author":"Shi","year":"2021"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1002\/dad2.70055","article-title":"Acoustic speech features are associated with late\u2010life depression and apathy symptoms: preliminary findings","volume":"17","author":"Harlev","year":"2025","journal-title":"Alzheimers Dement (Amst)"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1186\/s40708-022-00180-6","article-title":"Single classifier vs. ensemble machine learning approaches for mental health prediction","volume":"10","author":"Chung","year":"2023","journal-title":"Brain Inform"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3154332","article-title":"Prediction of depression severity based on the prosodic and semantic features with bidirectional LSTM and time distributed CNN","volume":"14","author":"Mao","year":"2023","journal-title":"IEEE Trans Affect Comput"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2025.3594166","article-title":"MFE-former: disentangling emotion-identity dynamics via self-supervised learning for enhancing speech-driven depression detection","volume":"30","author":"Wang","year":"2026","journal-title":"IEEE J BioMed Health Inform"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3417","article-title":"xlstm: extended long short-term memory","volume":"37","author":"Beck","year":"2024","journal-title":"Adv Neural Inf Process Syst"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2509.18691","article-title":"An overview of neural architectures for self-supervised audio representation learning from masked spectrograms","author":"Yadav","year":"2025","journal-title":"Arxiv"},{"key":"B41","doi-asserted-by":"crossref","DOI":"10.1109\/ICCCNT56998.2023.10306745","article-title":"Kullback\u2013Leibler divergence based method for depression diagnosis using video data","author":"Bhasin","year":"2023"},{"key":"B42","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1186\/s12864-020-6490-7","article-title":"Identifying critical state of complex diseases by single-sample Kullback\u2013Leibler divergence","volume":"21","author":"Zhong","year":"2020","journal-title":"BMC Genomics"},{"key":"B43","doi-asserted-by":"publisher","first-page":"73","DOI":"10.5944\/rppc.28235","article-title":"Antidepressants and psychological treatment: hard reasons for synergy","volume":"26","author":"Campagne","year":"2021","journal-title":"Rev Psicol Psicol Clin"},{"key":"B44","first-page":"79","article-title":"Detecting depression in less than 10 seconds: impact of speaking time on depression detection sensitivity","author":"Aloshban","year":"2020"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-020-09808-3","article-title":"What you say or how you say it? depression detection through joint modeling of linguistic and acoustic aspects of speech","volume":"14","author":"Aloshban","year":"2022","journal-title":"Cognit Comput"},{"key":"B46","doi-asserted-by":"crossref","DOI":"10.1109\/SMC.2018.00326","article-title":"Comparing thin-slicing of speech for clinical depression detection","author":"Liu","year":"2018"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.1037\/0033-2909.111.2.256","article-title":"Thin slices of expressive behavior as predictors of interpersonal consequences: a meta-analysis","volume":"111","author":"Ambady","year":"1992","journal-title":"Psychol Bull"},{"key":"B48","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1002\/lio2.354","article-title":"Automated assessment of psychiatric disorders using speech: a systematic review","volume":"5","author":"Low","year":"2020","journal-title":"Laryngoscope Investig Otolaryngol"},{"key":"B49","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1706.05098","article-title":"An overview of multi-task learning in deep neural networks","author":"Ruder","year":"2017","journal-title":"Arxiv"},{"key":"B50","article-title":"Which tasks should be learned together in multi-task learning","author":"Standley","year":"2020"},{"key":"B51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263585","article-title":"Dawn of the transformer era in speech emotion recognition: closing the valence gap","volume":"45","author":"Wagner","year":"2023","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"B52","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.specom.2019.12.001","article-title":"Speech emotion recognition: emotional models, databases, features, preprocessing methods, supporting modalities, and classifiers","volume":"116","author":"Ak\u00e7ay","year":"2020","journal-title":"Speech Commun"}],"container-title":["Frontiers in Psychiatry"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpsyt.2026.1888425\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T10:23:16Z","timestamp":1790158996000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpsyt.2026.1888425\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,23]]},"references-count":52,"alternative-id":["10.3389\/fpsyt.2026.1888425"],"URL":"https:\/\/doi.org\/10.3389\/fpsyt.2026.1888425","relation":{},"ISSN":["1664-0640"],"issn-type":[{"value":"1664-0640","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,23]]},"article-number":"1888425"}}