{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T10:11:03Z","timestamp":1743156663671,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":22,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819611508"},{"type":"electronic","value":"9789819611515"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-1151-5_18","type":"book-chapter","created":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T16:00:17Z","timestamp":1738857617000},"page":"177-186","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Transformer-Based Depression Detection Network Leveraging Speech Emotional Expression Cues"],"prefix":"10.1007","author":[{"given":"Changqing","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyi","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rongfeng","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nan","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,2,7]]},"reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Al\u00a0Hanai, T., Ghassemi, M.M., Glass, J.R.: Detecting depression with audio\/text sequence modeling of interviews. In: Interspeech, pp. 1716\u20131720 (2018)","DOI":"10.21437\/Interspeech.2018-2522"},{"issue":"9\/10","key":"18_CR2","first-page":"341","volume":"5","author":"P Boersma","year":"2001","unstructured":"Boersma, P., Van Heuven, V.: Speak and unspeak with praat. Glot Int. 5(9\/10), 341\u2013347 (2001)","journal-title":"Glot Int."},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Bredin, H., et al.: Pyannote. audio: neural building blocks for speaker diarization. In: ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7124\u20137128. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9052974"},{"key":"18_CR4","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/j.specom.2015.03.004","volume":"71","author":"N Cummins","year":"2015","unstructured":"Cummins, N., Scherer, S., Krajewski, J., Schnieder, S., Epps, J., Quatieri, T.F.: A review of depression and suicide risk assessment using speech analysis. Speech Commun. 71, 10\u201349 (2015)","journal-title":"Speech Commun."},{"issue":"1","key":"18_CR5","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1136\/jnnp.23.1.56","volume":"23","author":"M Hamilton","year":"1960","unstructured":"Hamilton, M.: A rating scale for depression. J. Neurol. Neurosurg. Psychiatry 23(1), 56 (1960)","journal-title":"J. Neurol. Neurosurg. Psychiatry"},{"key":"18_CR6","doi-asserted-by":"publisher","first-page":"3451","DOI":"10.1109\/TASLP.2021.3122291","volume":"29","author":"WN Hsu","year":"2021","unstructured":"Hsu, W.N., Bolte, B., Tsai, Y.H.H., Lakhotia, K., Salakhutdinov, R., Mohamed, A.: Hubert: Self-supervised speech representation learning by masked prediction of hidden units. IEEE\/ACM Trans. Audio Speech Lang. Process. 29, 3451\u20133460 (2021)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"issue":"9","key":"18_CR7","doi-asserted-by":"publisher","first-page":"606","DOI":"10.1046\/j.1525-1497.2001.016009606.x","volume":"16","author":"K Kroenke","year":"2001","unstructured":"Kroenke, K., Spitzer, R.L., Williams, J.B.: The phq-9: validity of a brief depression severity measure. J. Gen. Intern. Med. 16(9), 606\u2013613 (2001)","journal-title":"J. Gen. Intern. Med."},{"issue":"1","key":"18_CR8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1057\/s41599-020-0492-6","volume":"7","author":"A Lausen","year":"2020","unstructured":"Lausen, A., Hammerschmidt, K.: Emotion recognition and confidence ratings predicted by vocal stimulus type and prosodic parameters. Human. Soc. Sci. Commun. 7(1), 1\u201317 (2020)","journal-title":"Human. Soc. Sci. Commun."},{"key":"18_CR9","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Lu, J., Liu, B., Lian, Z., Cai, C., Tao, J., Zhao, Z.: Prediction of depression severity based on transformer encoder and cnn model. In: 2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP), pp. 339\u2013343. IEEE (2022)","DOI":"10.1109\/ISCSLP57327.2022.10038064"},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Ma, X., Yang, H., Chen, Q., Huang, D., Wang, Y.: Depaudionet: an efficient deep model for audio based depression classification. In: Proceedings of the 6th International Workshop on Audio\/Visual Emotion Challenge, pp. 35\u201342 (2016)","DOI":"10.1145\/2988257.2988267"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Ma, Z., et al.: emotion2vec: self-supervised pre-training for speech emotion representation. arXiv preprint arXiv:2312.15185 (2023)","DOI":"10.18653\/v1\/2024.findings-acl.931"},{"key":"18_CR13","unstructured":"Organization, W.H.: World mental health report: Transforming mental health for all. World Health Organization (2022)"},{"key":"18_CR14","unstructured":"Paszke, A., et\u00a0al.: Pytorch: an imperative style, high-performance deep learning library. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Rodrigues\u00a0Makiuchi, M., Warnita, T., Uto, K., Shinoda, K.: Multimodal fusion of bert-cnn and gated cnn representations for depression detection. In: Proceedings of the 9th International on Audio\/Visual Emotion Challenge and Workshop, pp. 55\u201363 (2019)","DOI":"10.1145\/3347320.3357694"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Rohanian, M., Hough, J., Purver, M., et\u00a0al.: Detecting depression with word-level multimodal fusion. In: Interspeech, pp. 1443\u20131447 (2019)","DOI":"10.21437\/Interspeech.2019-2283"},{"key":"18_CR17","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"18_CR18","unstructured":"Wu, X., Xu, C., Li, N., Su, R., Lan, W., Nan, Y.: Depression enhances internal inconsistency between spoken and semantic. In: Interspeech (2024)"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Yao, Z., et al.: Wenet: production oriented streaming and non-streaming end-to-end speech recognition toolkit. arXiv preprint arXiv:2102.01547 (2021)","DOI":"10.21437\/Interspeech.2021-1983"},{"issue":"2","key":"18_CR20","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1109\/JSTSP.2019.2955012","volume":"14","author":"Z Zhao","year":"2019","unstructured":"Zhao, Z., et al.: Automatic assessment of depression from speech via a hierarchical attention transfer network and attention autoencoders. IEEE J. Sel. Topics Signal Process. 14(2), 423\u2013434 (2019)","journal-title":"IEEE J. Sel. Topics Signal Process."},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Zung, W.W.: A rating instrument for anxiety disorders. Psychosomatics: J. Consult. Liaison Psychiatry (1971)","DOI":"10.1016\/S0033-3182(71)71479-0"},{"issue":"1","key":"18_CR22","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1001\/archpsyc.1965.01720310065008","volume":"12","author":"WW Zung","year":"1965","unstructured":"Zung, W.W.: A self-rating depression scale. Arch. Gen. Psychiatry 12(1), 63\u201370 (1965)","journal-title":"Arch. Gen. Psychiatry"}],"container-title":["Lecture Notes in Computer Science","Social Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-1151-5_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T16:00:24Z","timestamp":1738857624000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-1151-5_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819611508","9789819611515"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-1151-5_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"7 February 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICSR + InnoBiz","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Social Robotics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shenzhen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"socrob2024b","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.asianlp.sg\/conferences\/icsr2024\/web\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}