{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T02:07:24Z","timestamp":1767319644982,"version":"3.48.0"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032131867","type":"print"},{"value":"9783032131874","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\/978-3-032-13187-4_13","type":"book-chapter","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T02:03:17Z","timestamp":1767319397000},"page":"186-196","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Automatic Speech Disorder Detection (ASDD) System with Self-Supervised Representation of Children's Speech"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4248-1327","authenticated-orcid":false,"given":"Yaoxuan","family":"Luan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5466-5484","authenticated-orcid":false,"given":"Marisha","family":"Speights","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7862-4026","authenticated-orcid":false,"given":"Gerry","family":"Dozier","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheryl","family":"Seals","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"13_CR1","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1007\/s004050000299","volume":"258","author":"PH Dejonckere","year":"2001","unstructured":"Dejonckere, P.H., et al.: A basic protocol for functional assessment of voice pathology, especially for investigating the efficacy of (phonosurgical) treatments and evaluating new assessment techniques. Eur. Arch. Otorhinolaryngol. 258, 77\u201382 (2001)","journal-title":"Eur. Arch. Otorhinolaryngol."},{"key":"13_CR2","first-page":"1","volume":"205","author":"LI Black","year":"2015","unstructured":"Black, L.I., Vahratian, A.M., Hoffman, H.J.: Communication disorders and use of intervention services among children aged 3\u201317 years: United States, 2012. NCHS Data Brief 205, 1\u20138 (2015)","journal-title":"NCHS Data Brief"},{"key":"13_CR3","doi-asserted-by":"publisher","first-page":"2998","DOI":"10.3389\/fpsyg.2019.02998","volume":"10","author":"AK Namasivayam","year":"2020","unstructured":"Namasivayam, A.K., et al.: Speech sound disorders in children: an articulatory phonology perspective. Front. Psychol. 10, 2998 (2020)","journal-title":"Front. Psychol."},{"issue":"3","key":"13_CR4","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1044\/1058-0360.0503.07","volume":"5","author":"RD Kent","year":"1996","unstructured":"Kent, R.D.: Hearing and believing. Am. J. Speech Lang. Pathol. 5(3), 7\u201323 (1996)","journal-title":"Am. J. Speech Lang. Pathol."},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Liu, J., et al.: Speech disorders classification in phonetic exams with MFCC and DTW. In: 2021 IEEE 7th International Conference on Collaboration and Internet Computing (CIC), pp. 35\u201340 (2021)","DOI":"10.1109\/CIC52973.2021.00015"},{"key":"13_CR6","doi-asserted-by":"publisher","unstructured":"Liu, J., et al: Speech disorders classification by CNN in phonetic e-learning system. In: Degen, H., Ntoa, S. (eds.) Artificial Intelligence in HCI, HCII 2022. LNCS(LNAI), vol. 13336, pp. 557\u2013566. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-05643-7_36","DOI":"10.1007\/978-3-031-05643-7_36"},{"issue":"2","key":"13_CR7","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1109\/JSTSP.2019.2959393","volume":"14","author":"M Shahin","year":"2019","unstructured":"Shahin, M., Zafar, U., Ahmed, B.: The automatic detection of speech disorders in children: challenges, opportunities, and preliminary results. IEEE J. Sel. Top. Signal Process. 14(2), 400\u2013412 (2019)","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Gui, J., et al.: A survey on self-supervised learning: algorithms, applications, and future trends. IEEE Trans. Pattern Anal. Mach. Intell. 46(12), 9052\u20139071 (2024)","DOI":"10.1109\/TPAMI.2024.3415112"},{"issue":"6","key":"13_CR9","doi-asserted-by":"publisher","first-page":"1179","DOI":"10.1109\/JSTSP.2022.3207050","volume":"16","author":"A Mohamed","year":"2022","unstructured":"Mohamed, A., et al.: Self-supervised speech representation learning: a review. IEEE J. Sel. Top. Signal Process. 16(6), 1179\u20131210 (2022)","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"13_CR10","unstructured":"Yang, S.-w., et al.: Superb: speech processing universal performance benchmark. arXiv preprint arXiv:2105.01051 (2021)"},{"key":"13_CR11","doi-asserted-by":"publisher","first-page":"49667","DOI":"10.1109\/ACCESS.2024.3371713","volume":"12","author":"I Sindhu","year":"2024","unstructured":"Sindhu, I., Sainin, M.S.: Automatic speech and voice disorder detection using deep learning\u2014a systematic literature review. IEEE Access 12, 49667\u201349681 (2024)","journal-title":"IEEE Access"},{"issue":"2","key":"13_CR12","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1109\/TAFFC.2015.2457417","volume":"7","author":"F Eyben","year":"2015","unstructured":"Eyben, F., et al.: The Geneva minimalistic acoustic parameter set (GeMAPS) for voice research and affective computing. IEEE Trans. Affect. Comput. 7(2), 190\u2013202 (2015)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"13_CR13","doi-asserted-by":"crossref","unstructured":"Ng, S.-I., et al.: Automatic detection of speech sound disorder in child speech using posterior-based speaker representations. arXiv preprint arXiv:2203.15405 (2022)","DOI":"10.21437\/Interspeech.2022-935"},{"key":"13_CR14","unstructured":"Tirronen, S., Kadiri, S.R., Alku, P.: The effect of the MFCC frame length in automatic voice pathology detection. J. Voice (2022)"},{"issue":"1","key":"13_CR15","doi-asserted-by":"publisher","first-page":"7264","DOI":"10.1038\/s41598-023-34461-9","volume":"13","author":"X Peng","year":"2023","unstructured":"Peng, X., et al.: Voice disorder classification using convolutional neural network based on deep transfer learning. Sci. Rep. 13(1), 7264 (2023)","journal-title":"Sci. Rep."},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Gumelar, A.B., et al.: Enhancing detection of pathological voice disorder based on deep VGG-16 CNN. In: 2020 3rd International Conference on Biomedical Engineering (IBIOMED). IEEE (2020)","DOI":"10.1109\/IBIOMED50285.2020.9487589"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Koudounas, A., et al.: Voice disorder analysis: a transformer-based approach. arXiv preprint arXiv:2406.14693 (2024)","DOI":"10.21437\/Interspeech.2024-1122"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Tami, M., et al.: Transformer-based approach to pathology diagnosis using audio spectrogram. Information 15(5), 253 (2024)","DOI":"10.3390\/info15050253"},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Farhad, J., Sudarsana Reddy, K., Paavo, A.: Pre-trained models for detection and severity level classification of dysarthria from speech. Speech Commun. 158, 103047 (2024)","DOI":"10.1016\/j.specom.2024.103047"},{"key":"13_CR20","doi-asserted-by":"crossref","unstructured":"Tirronen, S., et al.: Utilizing wav2vec in database-independent voice disorder detection. In: ICASSP 2023\u20132023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10094798"},{"key":"13_CR21","doi-asserted-by":"crossref","unstructured":"Speights Atkins, M., Bailey, D.J., Boyce, S.: Speech exemplar and evaluation database (SEED) for clinical training in articulatory phonetics and speech science. Clin. Linguist. Phon. 34, 878\u2013886 (2020)","DOI":"10.1080\/02699206.2020.1743761"},{"key":"13_CR22","unstructured":"Bill Martin, E.C.: Brown bear, brown bear (1984)"},{"key":"13_CR23","unstructured":"Secord, W., Donohue, J.S.: CAAP-2: Clinical assessment of articulation and phonology-2. Super Duper Publications (2014)"},{"key":"13_CR24","unstructured":"Wiig, E.H., Secord, W.A., Semel, E.: CELF-Preschool-2: Clinical evaluation of language fundamentals, preschool. Harcourt Assessment (2004)"},{"key":"13_CR25","unstructured":"Baevski, A., et al.: wav2vec 2.0: A framework for self-supervised learning of speech representations. In: Advances in Neural Information Processing Systems, vol. 33, pp. 12449\u201312460 (2020)"},{"key":"13_CR26","doi-asserted-by":"publisher","first-page":"3451","DOI":"10.1109\/TASLP.2021.3122291","volume":"29","author":"W-N Hsu","year":"2021","unstructured":"Hsu, W.-N., et al.: 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."},{"key":"13_CR27","doi-asserted-by":"crossref","unstructured":"Getman, Y., et al.: Wav2vec2-based speech rating system for children with speech sound disorder. In: Interspeech. International Speech Communication Association (ISCA) (2022)","DOI":"10.21437\/Interspeech.2022-10103"},{"key":"13_CR28","unstructured":"Wolf, T., et al.: HuggingFace's transformers: state-of-the-art natural language processing. arXiv (2019). abs\/1910.03771"},{"key":"13_CR29","unstructured":"Wiepert, D.A., et al.: Speech foundation models in healthcare: effect of layer selection on pathological speech feature prediction"},{"key":"13_CR30","doi-asserted-by":"crossref","unstructured":"Pasad, A., Shi, B., Livescu, K.: Comparative layer-wise analysis of self-supervised speech models. In: ICASSP 2023\u20132023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10096149"},{"key":"13_CR31","doi-asserted-by":"crossref","unstructured":"Pasad, A., Chou, J.-C., Livescu, K.: Layer-wise analysis of a self-supervised speech representation model. In: 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU). IEEE (2021)","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"13_CR32","doi-asserted-by":"crossref","unstructured":"McFee, B., et al.: librosa: Audio and music signal analysis in Python. In: SciPy (2015)","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"13_CR33","doi-asserted-by":"crossref","unstructured":"Eyben, F., W\u00f6llmer, M., Schuller, B.: Opensmile: the munich versatile and fast open-source audio feature extractor. In: Proceedings of the 18th ACM International Conference on Multimedia, Firenze, Italy, pp. 1459\u20131462. Association for Computing Machinery (2010)","DOI":"10.1145\/1873951.1874246"},{"key":"13_CR34","doi-asserted-by":"publisher","unstructured":"Jim\u00e9nez-Recio, C., Zlotnik, A., Gallardo-Antol\u00edn, A., Montero, J.M., Mart\u00ednez-Castrillo, J.C.: Prediction of the degree of Parkinson\u2019s condition using recordings of patients\u2019 voices. In: Abraham, A., Haqiq, A., Muda, A., Gandhi, N. (eds.) Proceedings of the Ninth International Conference on Soft Computing and Pattern Recognition (SoCPaR 2017), SoCPaR 2017. AISC, vol. 737, pp. 120\u2013129. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-76357-6_12","DOI":"10.1007\/978-3-319-76357-6_12"},{"key":"13_CR35","unstructured":"Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011)"}],"container-title":["Lecture Notes in Computer Science","HCI International 2025 \u2013 Late Breaking Papers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-13187-4_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T02:03:20Z","timestamp":1767319400000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-13187-4_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032131867","9783032131874"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-13187-4_13","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 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"HCII","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Human-Computer Interaction","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Gothenburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","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":"22 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"hcii2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2025.hci.international\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}