{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T11:03:17Z","timestamp":1781262197356,"version":"3.54.1"},"publisher-location":"Cham","reference-count":16,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032263513","type":"print"},{"value":"9783032263520","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-26352-0_40","type":"book-chapter","created":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T10:51:48Z","timestamp":1781261508000},"page":"484-492","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Audio Spectrogram Transformer for\u00a0Automatic Speech-Based Depression Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8477-7842","authenticated-orcid":false,"given":"Hitesh Arjunbhai","family":"Ramrakhiyani","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Himashri","family":"Deka","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sandeep Kumar","family":"Pandey","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"N. S.","family":"Sreenivasalu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanumant Singh","family":"Shekhawat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ravi","family":"Jasuja","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,2]]},"reference":[{"key":"40_CR1","doi-asserted-by":"crossref","unstructured":"Joormann, J., Gotlib, I.H.: Emotion regulation in depression: relation to cognitive inhibition. Cogn. Emotion 24(2), 281\u2013298 (2010)","DOI":"10.1080\/02699930903407948"},{"key":"40_CR2","doi-asserted-by":"crossref","unstructured":"Christensen, M.C., Ren, H., Fagiolini, A.: Emotional blunting in patients with depression. part i: clinical characteristics. Ann. General Psychiatry 21(1), 10 (2022)","DOI":"10.1186\/s12991-022-00387-1"},{"key":"40_CR3","doi-asserted-by":"crossref","unstructured":"Rutter, L.A., Passell, E., Scheuer, L., Germine, L.: Depression severity is associated with impaired facial emotion processing in a large international sample. J. Affective Disord. 275, 175\u2013179 (2020)","DOI":"10.1016\/j.jad.2020.07.006"},{"key":"40_CR4","doi-asserted-by":"crossref","unstructured":"Akhapkin, R.V., et al.: Recognition of facial emotion expressions in patients with depressive disorders: a prospective, observational study. Neurol. Therapy 10(1), 225\u2013234 (2021)","DOI":"10.1007\/s40120-021-00231-w"},{"key":"40_CR5","doi-asserted-by":"crossref","unstructured":"Kroenke, K., Strine, T.W., Spitzer, R.L., Williams, J.B.W., Berry, J.T., Mokdad, A.H.: The phq-8 as a measure of current depression in the general population. J. Affective Disord. 114(1-3), 163\u2013173 (2009)","DOI":"10.1016\/j.jad.2008.06.026"},{"key":"40_CR6","doi-asserted-by":"crossref","unstructured":"Gratch, J., et\u00a0al.: The distress analysis interview corpus of human and computer interviews. In: LREC, vol.\u00a014, pp. 3123\u20133128. Reykjavik (2014)","DOI":"10.63317\/3o7bccg9xequ"},{"key":"40_CR7","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.specom.2015.09.003","volume":"75","author":"N Cummins","year":"2015","unstructured":"Cummins, N., Sethu, V., Epps, J., Schnieder, S., Krajewski, J.: Analysis of acoustic space variability in speech affected by depression. Speech Commun. 75, 27\u201349 (2015)","journal-title":"Speech Commun."},{"key":"40_CR8","doi-asserted-by":"crossref","unstructured":"Ma, X., Yang, H., Chen, Q., Huang, D., Wang, Y.: Depaudionet: aAn efficient deep model for audio based depression classification. In: Proceedings of the 6th International Workshop on Audio\/Visual Emotion Challenge, AVEC \u201916, pp. 35\u201342. New York, NY, USA (2016). Association for Computing Machinery","DOI":"10.1145\/2988257.2988267"},{"key":"40_CR9","doi-asserted-by":"crossref","unstructured":"Pandey, S.K., Shekhawat, H.S., Prasanna, S.R.M., Bhasin, S., Jasuja, R.: A deep tensor-based approach for automatic depression recognition from speech utterances. Plos One 17(8), e0272659 (2022)","DOI":"10.1371\/journal.pone.0272659"},{"key":"40_CR10","doi-asserted-by":"publisher","first-page":"775","DOI":"10.1109\/TASLP.2023.3235194","volume":"31","author":"W Chen","year":"2023","unstructured":"Chen, W., Xing, X., Xiangmin, X., Pang, J., Lan, D.: Speechformer++: a hierarchical efficient framework for paralinguistic speech processing. IEEE\/ACM Trans. Audio Speech Lang. Process. 31, 775\u2013788 (2023)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"40_CR11","doi-asserted-by":"crossref","unstructured":"Gong, Y., Chung, Y.-A., Glass, J.: Ast: Audio spectrogram transformer. arXiv preprint arXiv:2104.01778 (2021)","DOI":"10.21437\/Interspeech.2021-698"},{"key":"40_CR12","doi-asserted-by":"crossref","unstructured":"Gemmeke, J.F., et al.: Audio set: An ontology and human-labeled dataset for audio events. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 776\u2013780. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"40_CR13","doi-asserted-by":"crossref","unstructured":"McFee, B., et al.: librosa: Audio and music signal analysis in python. In: Proceedings of the 14th Python in Science Conference, vol.\u00a08 (2015)","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"40_CR14","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"674","DOI":"10.1007\/978-981-10-7299-4_56","volume-title":"Computer Vision","author":"J Song","year":"2017","unstructured":"Song, J., Shen, Y., Jing, Y., Song, M.: Towards Deeper Insights into Deep Learning from Imbalanced Data. In: Yang, J., et al. (eds.) CCCV 2017. CCIS, vol. 771, pp. 674\u2013684. Springer, Singapore (2017). https:\/\/doi.org\/10.1007\/978-981-10-7299-4_56"},{"key":"40_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2024.103106","volume":"163","author":"J Wang","year":"2024","unstructured":"Wang, J., Ravi, V., Flint, J., Alwan, A.: Speechformer-ctc: sequential modeling of depression detection with speech temporal classification. Speech Commun. 163, 103106 (2024)","journal-title":"Speech Commun."},{"key":"40_CR16","unstructured":"Dumpala, S.H., Rodriguez, S., Rempel, S., Sajjadian, M., Uher, R., Oore, S.: Detecting depression with a temporal context of speaker embeddings. In: Proceedings of AAAI SAS (2022)"}],"container-title":["Lecture Notes in Computer Science","Intelligent Human Computer Interaction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-26352-0_40","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T10:52:01Z","timestamp":1781261521000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-26352-0_40"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032263513","9783032263520"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-26352-0_40","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IHCI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Human Computer Interaction","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Jaipur","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ihci2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ihciconference.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}