{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:54:06Z","timestamp":1776884046116,"version":"3.51.2"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031209796","type":"print"},{"value":"9783031209802","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20980-2_25","type":"book-chapter","created":{"date-parts":[[2022,11,12]],"date-time":"2022-11-12T19:03:09Z","timestamp":1668279789000},"page":"290-301","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Multi-label Dysfluency Classification"],"prefix":"10.1007","author":[{"given":"Melanie","family":"Jouaiti","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kerstin","family":"Dautenhahn","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,11,10]]},"reference":[{"key":"25_CR1","unstructured":"Aravind, P., Nechiyil, U., Paramparambath, N., et al.: Audio spoofing verification using deep convolutional neural networks by transfer learning. arXiv preprint arXiv:2008.03464 (2020)"},{"key":"25_CR2","doi-asserted-by":"crossref","unstructured":"Chee, L.S., Ai, O.C., Hariharan, M., Yaacob, S.: MFCC based recognition of repetitions and prolongations in stuttered speech using k-NN and LDA. In: 2009 IEEE Student Conference on Research and Development (SCOReD), pp. 146\u2013149. IEEE (2009)","DOI":"10.1109\/SCORED.2009.5443210"},{"key":"25_CR3","doi-asserted-by":"crossref","unstructured":"Deng, J., Zhang, Z., Marchi, E., Schuller, B.: Sparse autoencoder-based feature transfer learning for speech emotion recognition. In: 2013 Humaine Association Conference on Affective Computing and Intelligent Interaction, pp. 511\u2013516. IEEE (2013)","DOI":"10.1109\/ACII.2013.90"},{"issue":"2","key":"25_CR4","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/S0094-730X(99)00029-7","volume":"25","author":"Y Geetha","year":"2000","unstructured":"Geetha, Y., Pratibha, K., Ashok, R., Ravindra, S.K.: Classification of childhood disfluencies using neural networks. J. Fluen. Disord. 25(2), 99\u2013117 (2000)","journal-title":"J. Fluen. Disord."},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Georgila, K.: Using integer linear programming for detecting speech disfluencies. In: Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Short Papers, pp. 109\u2013112 (2009)","DOI":"10.3115\/1620853.1620885"},{"key":"25_CR6","doi-asserted-by":"crossref","unstructured":"Gerczuk, M., Amiriparian, S., Ottl, S., Schuller, B.W.: EmoNet: a transfer learning framework for multi-corpus speech emotion recognition. IEEE Trans. Affect. Comput. (2021)","DOI":"10.1109\/TAFFC.2021.3135152"},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Howell, P., Davis, S., Bartrip, J.: The university college London archive of stuttered speech (UCLASS) (2009)","DOI":"10.1044\/1092-4388(2009\/07-0129)"},{"key":"25_CR9","doi-asserted-by":"crossref","unstructured":"Howell, P., Sackin, S., Glenn, K.: Development of a two-stage procedure for the automatic recognition of dysfluencies in the speech of children who stutter: I. Psychometric procedures appropriate for selection of training material for lexical dysfluency classifiers. J. Speech Lang. Hear. Res. 40(5), 1073\u20131084 (1997)","DOI":"10.1044\/jslhr.4005.1073"},{"key":"25_CR10","doi-asserted-by":"publisher","unstructured":"Jouaiti, M., Dautenhahn, K.: Dysfluency classification in stuttered speech using deep learning for real-time applications. In: ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6482\u20136486 (2022). https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9746638","DOI":"10.1109\/ICASSP43922.2022.9746638"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Kourkounakis, T., Hajavi, A., Etemad, A.: Detecting multiple speech disfluencies using a deep residual network with bidirectional long short-term memory. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6089\u20136093. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053893"},{"key":"25_CR12","doi-asserted-by":"crossref","unstructured":"Kourkounakis, T., Hajavi, A., Etemad, A.: FluentNet: end-to-end detection of speech disfluency with deep learning. arXiv preprint arXiv:2009.11394 (2020)","DOI":"10.1109\/TASLP.2021.3110146"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Kunze, J., Kirsch, L., Kurenkov, I., Krug, A., Johannsmeier, J., Stober, S.: Transfer learning for speech recognition on a budget. arXiv preprint arXiv:1706.00290 (2017)","DOI":"10.18653\/v1\/W17-2620"},{"key":"25_CR14","doi-asserted-by":"crossref","unstructured":"Latif, S., Rana, R., Younis, S., Qadir, J., Epps, J.: Transfer learning for improving speech emotion classification accuracy. arXiv preprint arXiv:1801.06353 (2018)","DOI":"10.21437\/Interspeech.2018-1625"},{"key":"25_CR15","doi-asserted-by":"crossref","unstructured":"Lea, C., Mitra, V., Joshi, A., Kajarekar, S., Bigham, J.P.: Sep-28k: a dataset for stuttering event detection from podcasts with people who stutter. In: ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6798\u20136802. IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9413520"},{"key":"25_CR16","series-title":"Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","doi-asserted-by":"publisher","first-page":"298","DOI":"10.1007\/978-3-642-37949-9_26","volume-title":"Quality, Reliability, Security and Robustness in Heterogeneous Networks","author":"P Mahesha","year":"2013","unstructured":"Mahesha, P., Vinod, D.S.: Classification of speech dysfluencies using speech parameterization techniques and multiclass SVM. In: Singh, K., Awasthi, A.K. (eds.) QShine 2013. LNICST, vol. 115, pp. 298\u2013308. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-37949-9_26"},{"key":"25_CR17","doi-asserted-by":"crossref","unstructured":"Marcinek, L., Stone, M., Millman, R., Gaydecki, P.: N-MTTL SI model: non-intrusive multi-task transfer learning-based speech intelligibility prediction model with scenery classification. In: Interspeech (2021)","DOI":"10.21437\/Interspeech.2021-1878"},{"key":"25_CR18","doi-asserted-by":"crossref","unstructured":"Matassoni, M., Gretter, R., Falavigna, D., Giuliani, D.: Non-native children speech recognition through transfer learning. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6229\u20136233. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8462059"},{"key":"25_CR19","doi-asserted-by":"crossref","unstructured":"Oue, S., Marxer, R., Rudzicz, F.: Automatic dysfluency detection in dysarthric speech using deep belief networks. In: Proceedings of SLPAT 2015: 6th Workshop on Speech and Language Processing for Assistive Technologies, pp. 60\u201364 (2015)","DOI":"10.18653\/v1\/W15-5111"},{"key":"25_CR20","doi-asserted-by":"crossref","unstructured":"Padi, S., Sadjadi, S.O., Sriram, R.D., Manocha, D.: Improved speech emotion recognition using transfer learning and spectrogram augmentation. In: Proceedings of the 2021 International Conference on Multimodal Interaction, pp. 645\u2013652 (2021)","DOI":"10.1145\/3462244.3481003"},{"key":"25_CR21","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1016\/j.jfludis.2018.03.002","volume":"56","author":"NB Ratner","year":"2018","unstructured":"Ratner, N.B., MacWhinney, B.: Fluency bank: a new resource for fluency research and practice. J. Fluen. Disord. 56, 69\u201380 (2018)","journal-title":"J. Fluen. Disord."},{"key":"25_CR22","unstructured":"Ravikumar, K., Rajagopal, R., Nagaraj, H.: An approach for objective assessment of stuttered speech using MFCC. In: The International Congress for Global Science and Technology, p. 19 (2009)"},{"key":"25_CR23","first-page":"270","volume":"36","author":"K Ravikumar","year":"2008","unstructured":"Ravikumar, K., Reddy, B., Rajagopal, R., Nagaraj, H.: Automatic detection of syllable repetition in read speech for objective assessment of stuttered disfluencies. Proc. World Acad. Sci. Eng. Technol. 36, 270\u2013273 (2008)","journal-title":"Proc. World Acad. Sci. Eng. Technol."},{"key":"25_CR24","first-page":"514","volume":"19","author":"J Santoso","year":"2019","unstructured":"Santoso, J., Yamada, T., Makino, S.: Categorizing error causes related to utterance characteristics in speech recognition. Proc. NCSP 19, 514\u2013517 (2019)","journal-title":"Proc. NCSP"},{"key":"25_CR25","doi-asserted-by":"crossref","unstructured":"Sheikh, S.A., Sahidullah, M., Hirsch, F., Ouni, S.: StutterNet: stuttering detection using time delay neural network. arXiv preprint arXiv:2105.05599 (2021)","DOI":"10.23919\/EUSIPCO54536.2021.9616063"},{"key":"25_CR26","doi-asserted-by":"crossref","unstructured":"Sheikh, S.A., Sahidullah, M., Hirsch, F., Ouni, S.: Machine learning for stuttering identification: review, challenges & future directions. arXiv preprint arXiv:2107.04057 (2021)","DOI":"10.1016\/j.neucom.2022.10.015"},{"key":"25_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101077","volume":"63","author":"PG Shivakumar","year":"2020","unstructured":"Shivakumar, P.G., Georgiou, P.: Transfer learning from adult to children for speech recognition: evaluation, analysis and recommendations. Comput. Speech Lang. 63, 101077 (2020)","journal-title":"Comput. Speech Lang."},{"issue":"1","key":"25_CR28","first-page":"1","volume":"1","author":"W Suszy\u0144ski","year":"2015","unstructured":"Suszy\u0144ski, W., Kuniszyk-J\u00f3\u017akowiak, W., Smo\u0142ka, E., Dzie\u0144kowski, M.: Prolongation detection with application of fuzzy logic. Ann. Universitatis Mariae Curie-Sklodowska Sectio AI-Informatica 1(1), 1\u20138 (2015)","journal-title":"Ann. Universitatis Mariae Curie-Sklodowska Sectio AI-Informatica"},{"key":"25_CR29","unstructured":"Szczurowska, I., Kuniszyk-J\u00f3\u017akowiak, W., Smo\u0142ka, E.: The application of Kohonen and multilayer perceptron networks in the speech nonfluency analysis. Arch. Acoust. 31(4(S)), 205\u2013210 (2014)"},{"key":"25_CR30","doi-asserted-by":"crossref","unstructured":"Villegas, B., Flores, K.M., Acu\u00f1a, K.J., Pacheco-Barrios, K., Elias, D.: A novel stuttering disfluency classification system based on respiratory biosignals. In: 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 4660\u20134663. IEEE (2019)","DOI":"10.1109\/EMBC.2019.8857891"},{"key":"25_CR31","doi-asserted-by":"crossref","unstructured":"Wang, D., Zheng, T.F.: Transfer learning for speech and language processing. In: 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA), pp. 1225\u20131237. IEEE (2015)","DOI":"10.1109\/APSIPA.2015.7415532"},{"issue":"1","key":"25_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-016-0043-6","volume":"3","author":"K Weiss","year":"2016","unstructured":"Weiss, K., Khoshgoftaar, T.M., Wang, D.D.: A survey of transfer learning. J. Big Data 3(1), 1\u201340 (2016). https:\/\/doi.org\/10.1186\/s40537-016-0043-6","journal-title":"J. Big Data"},{"issue":"1","key":"25_CR33","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1109\/TASL.2008.2006728","volume":"17","author":"S Yildirim","year":"2009","unstructured":"Yildirim, S., Narayanan, S.: Automatic detection of disfluency boundaries in spontaneous speech of children using audio-visual information. IEEE Trans. Audio Speech Lang. Process. 17(1), 2\u201312 (2009)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"25_CR34","doi-asserted-by":"crossref","unstructured":"Zayats, V., Ostendorf, M., Hajishirzi, H.: Disfluency detection using a bidirectional LSTM. arXiv preprint arXiv:1604.03209 (2016)","DOI":"10.21437\/Interspeech.2016-1247"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20980-2_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,12]],"date-time":"2022-11-12T19:06:27Z","timestamp":1668279987000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20980-2_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031209796","9783031209802"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20980-2_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"10 November 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SPECOM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Speech and Computer","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Gurugram","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 November 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.specom.co.in","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"99","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"60","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"61% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}