{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T18:25:04Z","timestamp":1761157504808,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":21,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T00:00:00Z","timestamp":1668038400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"General Program of Tianjin, China","award":["19JCYBJC29200"],"award-info":[{"award-number":["19JCYBJC29200"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["81925020, 81801786"],"award-info":[{"award-number":["81925020, 81801786"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,11,10]]},"DOI":"10.1145\/3574198.3574219","type":"proceedings-article","created":{"date-parts":[[2023,3,15]],"date-time":"2023-03-15T09:24:43Z","timestamp":1678872283000},"page":"133-139","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["An Automatic Depression Recognition Method from Spontaneous Pronunciation Using Machine Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1894-6032","authenticated-orcid":false,"given":"Minghao","family":"Du","sequence":"first","affiliation":[{"name":"Academy of Medical Engineering and Translational Medicine, Tianjin University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7757-3056","authenticated-orcid":false,"given":"Wenquan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Academy of Medical Engineering and Translational Medicine, Tianjin University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3038-0097","authenticated-orcid":false,"given":"Tao","family":"Wang","sequence":"additional","affiliation":[{"name":"Academy of Medical Engineering and Translational Medicine, Tianjin University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4372-8443","authenticated-orcid":false,"given":"Shuang","family":"Liu","sequence":"additional","affiliation":[{"name":"Academy of Medical Engineering and Translational Medicine, Tianjin University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8192-2538","authenticated-orcid":false,"given":"Dong","family":"Ming","sequence":"additional","affiliation":[{"name":"Academy of Medical Engineering and Translational Medicine, Tianjin University, China"}]}],"member":"320","published-online":{"date-parts":[[2023,3,15]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Cognitive function and neurocognitive deficits in depression. The Neuroscience of Depression. (March","author":"Semkovska Maria","year":"2021","unstructured":"Maria Semkovska . 2021. Cognitive function and neurocognitive deficits in depression. The Neuroscience of Depression. (March 2021 ). 361-371. https:\/\/doi.org\/10.1016\/B978-0-12-817935-2.00021-0 10.1016\/B978-0-12-817935-2.00021-0 Maria Semkovska. 2021. Cognitive function and neurocognitive deficits in depression. The Neuroscience of Depression. (March 2021). 361-371. https:\/\/doi.org\/10.1016\/B978-0-12-817935-2.00021-0"},{"key":"e_1_3_2_1_2_1","volume-title":"Institute of Health Metrics and Evaluation. Retrieved","author":"Data Global Health","year":"2021","unstructured":"Global Health Data Exchange (GHDx). Institute of Health Metrics and Evaluation. Retrieved May 1, 2021 from http:\/\/ghdx.healthdata.org\/gbd-results-tool?params=gbd-api-2019-permalink\/d780dffbe8a381b25e1416884959e88b Global Health Data Exchange (GHDx). Institute of Health Metrics and Evaluation. Retrieved May 1, 2021 from http:\/\/ghdx.healthdata.org\/gbd-results-tool?params=gbd-api-2019-permalink\/d780dffbe8a381b25e1416884959e88b"},{"key":"e_1_3_2_1_3_1","volume-title":"2020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA). IEEE","author":"Madhavi Ishara","year":"2020","unstructured":"Ishara Madhavi , Sadil Chamishka , Rashmika Nawaratne , Vishaka Nanayakkara , Damminda Alahakoon , and Daswin De Silva . 2020 . A Deep Learning Approach for Work Related Stress Detection from Audio Streams in Cyber Physical Environments . In 2020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA). IEEE , Vienna, Austria, 929\u2013936. https:\/\/doi.org\/10.1109\/ETFA46521. 2020.9212098 10.1109\/ETFA46521.2020.9212098 Ishara Madhavi, Sadil Chamishka, Rashmika Nawaratne, Vishaka Nanayakkara, Damminda Alahakoon, and Daswin De Silva. 2020. A Deep Learning Approach for Work Related Stress Detection from Audio Streams in Cyber Physical Environments. In 2020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA). IEEE, Vienna, Austria, 929\u2013936. https:\/\/doi.org\/10.1109\/ETFA46521.2020.9212098"},{"key":"e_1_3_2_1_4_1","volume-title":"Cognitive function and metabolic syndrome in unipolar and bipolar depression: A pilot study. European Psychiatry. 64. S1(April","author":"Jannini T.","year":"2021","unstructured":"T. Jannini , L. Longo , F. Marasco , M. Di Civita , C. Niolu , A. Siracusano , and G. Di Lorenzo . 2021. Cognitive function and metabolic syndrome in unipolar and bipolar depression: A pilot study. European Psychiatry. 64. S1(April 2021 ). S82\u2013S82. https:\/\/doi.org\/10.1192\/j.eurpsy.2021.246 10.1192\/j.eurpsy.2021.246 T. Jannini, L. Longo, F. Marasco, M. Di Civita, C. Niolu, A. Siracusano, and G. Di Lorenzo. 2021. Cognitive function and metabolic syndrome in unipolar and bipolar depression: A pilot study. European Psychiatry. 64. S1(April 2021). S82\u2013S82. https:\/\/doi.org\/10.1192\/j.eurpsy.2021.246"},{"key":"e_1_3_2_1_5_1","volume-title":"Quatieri","author":"Cummins Nicholas","year":"2015","unstructured":"Nicholas Cummins , Stefan Scherer , Jarek Krajewski , Sebastian Schnieder , Julien Epps , and Thomas F . Quatieri . 2015 . A review of depression and suicide risk assessment using speech analysis. Speech communication. 71, C(July 2015). 10\u201349. https:\/\/doi.org\/10.1016\/j.specom.2015.03.004 10.1016\/j.specom.2015.03.004 Nicholas Cummins, Stefan Scherer, Jarek Krajewski, Sebastian Schnieder, Julien Epps, and Thomas F. Quatieri. 2015. A review of depression and suicide risk assessment using speech analysis. Speech communication. 71, C(July 2015). 10\u201349. https:\/\/doi.org\/10.1016\/j.specom.2015.03.004"},{"key":"#cr-split#-e_1_3_2_1_6_1.1","doi-asserted-by":"crossref","unstructured":"Bethany Little Ossama Alshabrawy Daniel Stow I. Nicol Ferrier Roisin McNaney Daniel G. Jackson Karim Ladha Cassim Ladha Thomas Ploetz and Jaume Bacardit. 2021. Deep learning-based automated speech detection as a marker of social functioning in late-life depression. Psychological medicine. 51 9(July 2021): 1441-1450. https:\/\/doi.org\/10.1017\/S0033291719003994 10.1017\/S0033291719003994","DOI":"10.1017\/S0033291719003994"},{"key":"#cr-split#-e_1_3_2_1_6_1.2","doi-asserted-by":"crossref","unstructured":"Bethany Little Ossama Alshabrawy Daniel Stow I. Nicol Ferrier Roisin McNaney Daniel G. Jackson Karim Ladha Cassim Ladha Thomas Ploetz and Jaume Bacardit. 2021. Deep learning-based automated speech detection as a marker of social functioning in late-life depression. Psychological medicine. 51 9(July 2021): 1441-1450. https:\/\/doi.org\/10.1017\/S0033291719003994","DOI":"10.1017\/S0033291719003994"},{"key":"e_1_3_2_1_7_1","volume-title":"Automatic depression classification based on affective read sentences: Opportunities for text-dependent analysis. Speech Communication. 115, (December","author":"Stasak Brian","year":"2019","unstructured":"Brian Stasak , Julien Epps , and Roland Goecke . 2019. Automatic depression classification based on affective read sentences: Opportunities for text-dependent analysis. Speech Communication. 115, (December 2019 ). 1\u201314. https:\/\/doi.org\/10.1016\/j.specom.2019.10.003 10.1016\/j.specom.2019.10.003 Brian Stasak, Julien Epps, and Roland Goecke. 2019. Automatic depression classification based on affective read sentences: Opportunities for text-dependent analysis. Speech Communication. 115, (December 2019). 1\u201314. https:\/\/doi.org\/10.1016\/j.specom.2019.10.003"},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC\u201914)","author":"Gratch Jonathan","year":"2014","unstructured":"Jonathan Gratch , Ron Artstein , Gale Lucas , Giota Stratou , Stefan Scherer , Angela Nazarian , Rachel Wood , Jill Boberg , David DeVault , and Stacy Marsella . 2014 . The distress analysis interview corpus of human and computer interviews . In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC\u201914) . Reykjavik, Iceland, 3123\u20133128. Jonathan Gratch, Ron Artstein, Gale Lucas, Giota Stratou, Stefan Scherer, Angela Nazarian, Rachel Wood, Jill Boberg, David DeVault, and Stacy Marsella. 2014. The distress analysis interview corpus of human and computer interviews. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC\u201914). Reykjavik, Iceland, 3123\u20133128."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2512530.2512533"},{"key":"e_1_3_2_1_10_1","article-title":"Major depressive disorder discrimination using vocal acoustic features","author":"Taguchi Takaya","year":"2018","unstructured":"Takaya Taguchi , Hirokazu Tachikawa , Kiyotaka Nemoto , Masayuki Suzuki , Toru Nagano , Ryuki Tachibana , Masafumi Nishimura , and Tetsuaki Arai . 2018 . Major depressive disorder discrimination using vocal acoustic features . Journal of Affective Disorders. 225. ( January 2018). 214\u2013220. https:\/\/doi.org\/10.1016\/j.jad.2017.08.038 10.1016\/j.jad.2017.08.038 Takaya Taguchi, Hirokazu Tachikawa, Kiyotaka Nemoto, Masayuki Suzuki, Toru Nagano, Ryuki Tachibana, Masafumi Nishimura, and Tetsuaki Arai. 2018. Major depressive disorder discrimination using vocal acoustic features. Journal of Affective Disorders. 225. (January 2018). 214\u2013220. https:\/\/doi.org\/10.1016\/j.jad.2017.08.038","journal-title":"Journal of Affective Disorders. 225."},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the 6th international workshop on audio\/visual emotion challenge. Association for Computing Machinery","author":"Valstar Michel","year":"2016","unstructured":"Michel Valstar , Jonathan Gratch , Bj\u00f6rn Schuller , Fabien Ringeval , Denis Lalanne , Mercedes Torres Torres , Stefan Scherer , Giota Stratou , Roddy Cowie , and Maja Pantic . 2016 . Avec 2016: Depression, mood, and emotion recognition workshop and challenge . In Proceedings of the 6th international workshop on audio\/visual emotion challenge. Association for Computing Machinery , New York, USA, 3\u201310. https:\/\/doi.org\/10.1145\/2988257.2988258 10.1145\/2988257.2988258 Michel Valstar, Jonathan Gratch, Bj\u00f6rn Schuller, Fabien Ringeval, Denis Lalanne, Mercedes Torres Torres, Stefan Scherer, Giota Stratou, Roddy Cowie, and Maja Pantic. 2016. Avec 2016: Depression, mood, and emotion recognition workshop and challenge. In Proceedings of the 6th international workshop on audio\/visual emotion challenge. Association for Computing Machinery, New York, USA, 3\u201310. https:\/\/doi.org\/10.1145\/2988257.2988258"},{"key":"e_1_3_2_1_12_1","volume-title":"2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), IEEE","author":"Deshpande Gauri","year":"2019","unstructured":"Gauri Deshpande , Venkata Subramanian Viraraghavan , Mayuri Duggirala , and Sachin Patel . 2019 . Detecting emotional valence using time-domain analysis of speech signals . In 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), IEEE , Berlin, Germany, 3605\u20133608. https:\/\/doi.org\/10.1109\/EMBC. 2019.8857691 10.1109\/EMBC.2019.8857691 Gauri Deshpande, Venkata Subramanian Viraraghavan, Mayuri Duggirala, and Sachin Patel. 2019. Detecting emotional valence using time-domain analysis of speech signals. In 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), IEEE, Berlin, Germany, 3605\u20133608. https:\/\/doi.org\/10.1109\/EMBC.2019.8857691"},{"key":"e_1_3_2_1_13_1","volume-title":"Depression recognition based on speech analysis. Chinese Science Bulletin. 63. 20(July","author":"Wei Pan","year":"2018","unstructured":"Pan Wei , Wang Jingying , Liu Tianli , Liu Xiaoqian , Liu Mingming , Hu Bin , and Zhu Tingshao . 2018. Depression recognition based on speech analysis. Chinese Science Bulletin. 63. 20(July 2018 ). 2081\u20132092. https:\/\/doi.org\/10.1360\/N972017-01250 10.1360\/N972017-01250 Pan Wei, Wang Jingying, Liu Tianli, Liu Xiaoqian, Liu Mingming, Hu Bin, and Zhu Tingshao. 2018. Depression recognition based on speech analysis. Chinese Science Bulletin. 63. 20(July 2018). 2081\u20132092. https:\/\/doi.org\/10.1360\/N972017-01250"},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the 6th International Workshop on Audio\/Visual Emotion Challenge. Association for Computing Machinery","author":"Ma Xingchen","year":"2016","unstructured":"Xingchen Ma , Hongyu Yang , Qiang Chen , Di Huang , and Yunhong Wang . 2016 . DepAudioNet: An Efficient Deep Model for Audio based Depression Classification . In Proceedings of the 6th International Workshop on Audio\/Visual Emotion Challenge. Association for Computing Machinery , New York, USA, 35\u201342. https:\/\/doi.org\/10.1145\/2988257.2988267 10.1145\/2988257.2988267 Xingchen Ma, Hongyu Yang, Qiang Chen, Di Huang, and Yunhong Wang. 2016. DepAudioNet: An Efficient Deep Model for Audio based Depression Classification. In Proceedings of the 6th International Workshop on Audio\/Visual Emotion Challenge. Association for Computing Machinery, New York, USA, 35\u201342. https:\/\/doi.org\/10.1145\/2988257.2988267"},{"key":"e_1_3_2_1_15_1","volume-title":"MODMA dataset: a Multi-modal Open Dataset for Mental-disorder Analysis. Scientific Data. 9. 1(April","author":"Cai Hanshu","year":"2022","unstructured":"Hanshu Cai , Yiwen Gao , Shuting Sun , Na Li , Fuze Tian , Han Xiao , Jianxiu Li , Zhengwu Yang , Xiaowei Li , and Qinglin Zhao . 2022. MODMA dataset: a Multi-modal Open Dataset for Mental-disorder Analysis. Scientific Data. 9. 1(April 2022 ). 1-10. https:\/\/doi.org\/10.1038\/s41597-022-01211-x 10.1038\/s41597-022-01211-x Hanshu Cai, Yiwen Gao, Shuting Sun, Na Li, Fuze Tian, Han Xiao, Jianxiu Li, Zhengwu Yang, Xiaowei Li, and Qinglin Zhao. 2022. MODMA dataset: a Multi-modal Open Dataset for Mental-disorder Analysis. Scientific Data. 9. 1(April 2022). 1-10. https:\/\/doi.org\/10.1038\/s41597-022-01211-x"},{"key":"e_1_3_2_1_16_1","volume-title":"An End-to-End Depression Recognition Method Based on EEGNet. Front Psychiatry. 13. 864393 (March","author":"Liu Bo","year":"2022","unstructured":"Bo Liu , Hongli Chang , Kang Peng , and Xuenan Wang . 2022. An End-to-End Depression Recognition Method Based on EEGNet. Front Psychiatry. 13. 864393 (March 2022 ). https:\/\/doi.org\/10.3389\/fpsyt.2022.864393 10.3389\/fpsyt.2022.864393 Bo Liu, Hongli Chang, Kang Peng, and Xuenan Wang. 2022. An End-to-End Depression Recognition Method Based on EEGNet. Front Psychiatry. 13. 864393 (March 2022). https:\/\/doi.org\/10.3389\/fpsyt.2022.864393"},{"key":"e_1_3_2_1_17_1","volume-title":"Sommer","author":"Koops Sanne","year":"2022","unstructured":"Sanne Koops , Sanne G. Brederoo , Janna N. de Boer , Femke G. Nadema , Alban E. Voppel , and Iris E . Sommer . 2022 . Speech as a Biomarker for Depression. CNS & Neurological Disorders Drug Targets . (February 2022). https:\/\/doi.org\/10.2174\/1871527320666211213125847 10.2174\/1871527320666211213125847 Sanne Koops, Sanne G. Brederoo, Janna N. de Boer, Femke G. Nadema, Alban E. Voppel, and Iris E. Sommer. 2022. Speech as a Biomarker for Depression. CNS & Neurological Disorders Drug Targets. (February 2022). https:\/\/doi.org\/10.2174\/1871527320666211213125847"},{"key":"e_1_3_2_1_18_1","volume-title":"A machine learning approach for classifying and quantifying acoustic diversity. Methods in Ecology and Evolution. 12. 7 (July","author":"Keen Sara C.","year":"2021","unstructured":"Sara C. Keen , Karan J. Odom , Michael S. Webster , Gregory M. Kohn , Timothy F. Wright , and Marcelo Araya-Salas . 2021. A machine learning approach for classifying and quantifying acoustic diversity. Methods in Ecology and Evolution. 12. 7 (July 2021 ). 1213\u20131225. https:\/\/doi.org\/10.1111\/2041-210X.13599 10.1111\/2041-210X.13599 Sara C. Keen, Karan J. Odom, Michael S. Webster, Gregory M. Kohn, Timothy F. Wright, and Marcelo Araya-Salas. 2021. A machine learning approach for classifying and quantifying acoustic diversity. Methods in Ecology and Evolution. 12. 7 (July 2021). 1213\u20131225. https:\/\/doi.org\/10.1111\/2041-210X.13599"},{"key":"e_1_3_2_1_19_1","volume-title":"A Review on Automatic Speech Emotion Recognition with an Experiment Using Multilayer Perceptron Classifier. Soft Computing Techniques and Applications. 1248. (November","author":"Mamun Sardar Abdullah Al","year":"2020","unstructured":"Abdullah Al Mamun Sardar , Sanzidul Islam , and Touhid Bhuiyan . 2021. A Review on Automatic Speech Emotion Recognition with an Experiment Using Multilayer Perceptron Classifier. Soft Computing Techniques and Applications. 1248. (November 2020 ). 381\u2013388. https:\/\/doi.org\/10.1007\/978-981-15-7394-1_36 10.1007\/978-981-15-7394-1_36 Abdullah Al Mamun Sardar, Sanzidul Islam, and Touhid Bhuiyan. 2021. A Review on Automatic Speech Emotion Recognition with an Experiment Using Multilayer Perceptron Classifier. Soft Computing Techniques and Applications. 1248. (November 2020). 381\u2013388. https:\/\/doi.org\/10.1007\/978-981-15-7394-1_36"},{"key":"e_1_3_2_1_20_1","volume-title":"Combination of Time-domain, Frequency-domain, and Cepstral-domain Acoustic Features for Speech Commands Classification. (June","author":"Wang Yikang","year":"2022","unstructured":"Yikang Wang and Hiromitsu Nishizaki . 2022. Combination of Time-domain, Frequency-domain, and Cepstral-domain Acoustic Features for Speech Commands Classification. (June 2022 ). https:\/\/doi.org\/10.48550\/arXiv.2203.16085 10.48550\/arXiv.2203.16085 Yikang Wang and Hiromitsu Nishizaki. 2022. Combination of Time-domain, Frequency-domain, and Cepstral-domain Acoustic Features for Speech Commands Classification. (June 2022). https:\/\/doi.org\/10.48550\/arXiv.2203.16085"}],"event":{"name":"ICBBE 2022: 2022 9th International Conference on Biomedical and Bioinformatics Engineering","acronym":"ICBBE 2022","location":"Kyoto Japan"},"container-title":["Proceedings of the 2022 9th International Conference on Biomedical and Bioinformatics Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3574198.3574219","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3574198.3574219","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:08:25Z","timestamp":1750183705000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3574198.3574219"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,10]]},"references-count":21,"alternative-id":["10.1145\/3574198.3574219","10.1145\/3574198"],"URL":"https:\/\/doi.org\/10.1145\/3574198.3574219","relation":{},"subject":[],"published":{"date-parts":[[2022,11,10]]},"assertion":[{"value":"2023-03-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}