{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T21:02:25Z","timestamp":1743022945009,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":40,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819947485"},{"type":"electronic","value":"9789819947492"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-981-99-4749-2_18","type":"book-chapter","created":{"date-parts":[[2023,7,29]],"date-time":"2023-07-29T23:02:17Z","timestamp":1690671737000},"page":"209-220","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Explainable Stuttering Recognition Using Axial Attention"],"prefix":"10.1007","author":[{"given":"Yu","family":"Ma","sequence":"first","affiliation":[]},{"given":"Yuting","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Kaixiang","family":"Yuan","sequence":"additional","affiliation":[]},{"given":"Guangzhe","family":"Xuan","sequence":"additional","affiliation":[]},{"given":"Yongzi","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Hengrui","family":"Zhong","sequence":"additional","affiliation":[]},{"given":"Rui","family":"Li","sequence":"additional","affiliation":[]},{"given":"Jian","family":"Shen","sequence":"additional","affiliation":[]},{"given":"Kun","family":"Qian","sequence":"additional","affiliation":[]},{"given":"Bin","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Bj\u00f6rn W.","family":"Schuller","sequence":"additional","affiliation":[]},{"given":"Yoshiharu","family":"Yamamoto","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,7,30]]},"reference":[{"issue":"2","key":"18_CR1","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1109\/TCSS.2022.3157522","volume":"9","author":"B Hu","year":"2022","unstructured":"Hu, B., Shen, J., Zhu, L., Dong, Q., Cai, H., Qian, K.: Fundamentals of computational psychophysiology: theory and methodology. IEEE Trans. Comput. Soc. Syst. 9(2), 349\u2013355 (2022)","journal-title":"IEEE Trans. Comput. Soc. Syst."},{"issue":"1","key":"18_CR2","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1109\/TAFFC.2019.2934412","volume":"13","author":"J Shen","year":"2022","unstructured":"Shen, J., Zhang, X., Hu, B., Wang, G., Ding, Z., Hu, B.: An improved empirical mode decomposition of electroencephalogram signals for depression detection. IEEE Trans. Affect. Comput. 13(1), 262\u2013271 (2022)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Zhang, X., Shen, J., ud Din, Z., Liu, J., Wang, G., Hu, B.: Multimodal depression detection: fusion of electroencephalography and paralinguistic behaviors using a novel strategy for classifier ensemble. IEEE J. Biomed. Health Inform. 23(6), 2265\u20132275 (2019)","DOI":"10.1109\/JBHI.2019.2938247"},{"key":"18_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11042-022-12817-z","volume":"81","author":"N Banerjee","year":"2022","unstructured":"Banerjee, N., Borah, S., Sethi, N.: Intelligent stuttering speech recognition: a succinct review. Multimed. Tools Appl. 81, 1\u201322 (2022)","journal-title":"Multimed. Tools Appl."},{"key":"18_CR5","unstructured":"Lickley, R.: Disfluency in typical and stuttered speech. Fattori Sociali E Biologici Nella Variazione Fonetica-Social and Biological Factors in Speech Variation (2017)"},{"issue":"6","key":"18_CR6","doi-asserted-by":"publisher","first-page":"456","DOI":"10.5455\/medarh.2021.75.456-461","volume":"75","author":"L Junuzovic-Zunic","year":"2021","unstructured":"Junuzovic-Zunic, L., Sinanovic, O., Majic, B.: Neurogenic stuttering: etiology, symptomatology, and treatment. Med. Arch. 75(6), 456 (2021)","journal-title":"Med. Arch."},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Catalano, G., Robben, D.L., Catalano, M.C., Kahn, D.A.: Olanzapine for the treatment of acquired neurogenic stuttering. J. Psychiatr. Pract.\u00ae 15(6), 484\u2013488 (2009)","DOI":"10.1097\/01.pra.0000364292.93704.65"},{"key":"18_CR8","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":"18_CR9","doi-asserted-by":"crossref","unstructured":"Sheikh, S.A., Sahidullah, M., Hirsch, F., Ouni, S.: StutterNet: stuttering detection using time delay neural network. In: 29th European Signal Processing Conference (EUSIPCO), pp. 426\u2013430 (2021)","DOI":"10.23919\/EUSIPCO54536.2021.9616063"},{"issue":"4","key":"18_CR10","doi-asserted-by":"publisher","first-page":"1000","DOI":"10.1007\/s10439-019-02217-0","volume":"47","author":"K Qian","year":"2019","unstructured":"Qian, K., et al.: A bag of wavelet features for snore sound classification. Ann. Biomed. Eng. 47(4), 1000\u20131011 (2019)","journal-title":"Ann. Biomed. Eng."},{"issue":"4","key":"18_CR11","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1109\/MSP.2021.3057298","volume":"38","author":"K Qian","year":"2021","unstructured":"Qian, K., Zhang, Z., Yamamoto, Y., Schuller, B.W.: Artificial intelligence Internet of Things for the elderly: from assisted living to health-care monitoring. IEEE Signal Process. Mag. 38(4), 78\u201388 (2021)","journal-title":"IEEE Signal Process. Mag."},{"key":"18_CR12","doi-asserted-by":"publisher","first-page":"5","DOI":"10.3389\/fdgth.2020.00005","volume":"2","author":"K Qian","year":"2020","unstructured":"Qian, K., et al.: Computer audition for healthcare: opportunities and challenges. Front. Digit. Health 2, 5 (2020)","journal-title":"Front. Digit. Health"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Shen, J., Zhao, S., Yao, Y., Wang, Y., Feng, L.: A novel depression detection method based on pervasive EEG and EEG splitting criterion. In: 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 1879\u20131886. IEEE (2017)","DOI":"10.1109\/BIBM.2017.8217946"},{"issue":"7","key":"18_CR14","doi-asserted-by":"publisher","first-page":"2545","DOI":"10.1109\/JBHI.2020.3045718","volume":"25","author":"J Shen","year":"2020","unstructured":"Shen, J., et al.: An optimal channel selection for EEG-based depression detection via kernel-target alignment. IEEE J. Biomed. Health Inform. 25(7), 2545\u20132556 (2020)","journal-title":"IEEE J. Biomed. Health Inform."},{"issue":"3","key":"18_CR15","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1109\/MWC.001.2000394","volume":"28","author":"M Yang","year":"2021","unstructured":"Yang, M., Ma, Y., Liu, Z., Cai, H., Hu, X., Hu, B.: Undisturbed mental state assessment in the 5G era: a case study of depression detection based on facial expressions. IEEE Wirel. Commun. 28(3), 46\u201353 (2021)","journal-title":"IEEE Wirel. Commun."},{"issue":"1","key":"18_CR16","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1080\/21642583.2022.2057370","volume":"10","author":"K Zhang","year":"2022","unstructured":"Zhang, K., et al.: Research on mine vehicle tracking and detection technology based on YOLOv5. Syst. Sci. Control Eng. 10(1), 347\u2013366 (2022)","journal-title":"Syst. Sci. Control Eng."},{"key":"18_CR17","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1109\/TNSRE.2022.3221962","volume":"31","author":"J Shen","year":"2022","unstructured":"Shen, J., et al.: Exploring the intrinsic features of EEG signals via empirical mode decomposition for depression recognition. IEEE Trans. Neural Syst. Rehabil. Eng. 31, 356\u2013365 (2022)","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"18_CR18","doi-asserted-by":"publisher","first-page":"3234","DOI":"10.1109\/JBHI.2023.3265805","volume":"27","author":"J Shen","year":"2023","unstructured":"Shen, J., et al.: Depression recognition from EEG signals using an adaptive channel fusion method via improved focal loss. IEEE J. Biomed. Health Inform. 27, 3234\u20133245 (2023)","journal-title":"IEEE J. Biomed. Health Inform."},{"issue":"2","key":"18_CR19","doi-asserted-by":"publisher","first-page":"e0247408","DOI":"10.1371\/journal.pone.0247408","volume":"16","author":"J Rosenberg","year":"2021","unstructured":"Rosenberg, J., et al.: Conflict processing networks: a directional analysis of stimulus-response compatibilities using MEG. PLoS ONE 16(2), e0247408 (2021)","journal-title":"PLoS ONE"},{"issue":"3","key":"18_CR20","doi-asserted-by":"publisher","first-page":"971","DOI":"10.3233\/JAD-190973","volume":"75","author":"Q Dong","year":"2020","unstructured":"Dong, Q., et al.: Integrating convolutional neural networks and multi-task dictionary learning for cognitive decline prediction with longitudinal images. J. Alzheimer\u2019s Dis. 75(3), 971\u2013992 (2020)","journal-title":"J. Alzheimer\u2019s Dis."},{"issue":"4","key":"18_CR21","doi-asserted-by":"publisher","first-page":"865","DOI":"10.1109\/TCDS.2020.3003674","volume":"13","author":"Y Wu","year":"2020","unstructured":"Wu, Y., et al.: Person reidentification by multiscale feature representation learning with random batch feature mask. IEEE Trans. Cogn. Dev. Syst. 13(4), 865\u2013874 (2020)","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Demir, F., Sengur, A., Cummins, N., Amiriparian, S., Schuller, B.W.: Low level texture features for snore sound discrimination. In: 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 413\u2013416 (2018)","DOI":"10.1109\/EMBC.2018.8512459"},{"key":"18_CR23","doi-asserted-by":"publisher","first-page":"1160","DOI":"10.1109\/TASLP.2022.3155295","volume":"30","author":"L Barrett","year":"2022","unstructured":"Barrett, L., Hu, J., Howell, P.: Systematic review of machine learning approaches for detecting developmental stuttering. IEEE\/ACM Trans. Audio Speech Lang. Process. 30, 1160\u20131172 (2022)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"18_CR24","unstructured":"Howell, P., Sackin, S.: Automatic recognition of repetitions and prolongations in stuttered speech. In: Proceedings of the First World Congress on Fluency Disorders, vol. 2, pp. 372\u2013374. University Press Nijmegen Nijmegen, The Netherlands (1995)"},{"issue":"9","key":"18_CR25","first-page":"1","volume":"11","author":"S Gupta","year":"2020","unstructured":"Gupta, S., Shukla, R.S., Shukla, R.K., Verma, R.: Deep learning bidirectional LSTM based detection of prolongation and repetition in stuttered speech using weighted MFCC. Int. J. Adv. Comput. Sci. Appl. 11(9), 1\u201312 (2020)","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"18_CR26","first-page":"347","volume":"3","author":"I \u015awietlicka","year":"2009","unstructured":"\u015awietlicka, I., Kuniszyk-J\u00f3\u017akowiak, W., Smo\u0142ka, E.: Artificial neural networks in the disabled speech analysis. Comput. Recogn. Syst. 3, 347\u2013354 (2009)","journal-title":"Comput. Recogn. Syst."},{"issue":"1","key":"18_CR27","first-page":"19","volume":"9","author":"KM Ravikumar","year":"2009","unstructured":"Ravikumar, K.M., Rajagopal, R., Nagaraj, H.: An approach for objective assessment of stuttered speech using MFCC features. ICGST Int. J. Digit. Signal Process. 9(1), 19\u201324 (2009)","journal-title":"ICGST Int. J. Digit. Signal Process."},{"key":"18_CR28","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"},{"issue":"2","key":"18_CR29","doi-asserted-by":"publisher","first-page":"2157","DOI":"10.1016\/j.eswa.2011.07.065","volume":"39","author":"OC Ai","year":"2012","unstructured":"Ai, O.C., Hariharan, M., Yaacob, S., Chee, L.S.: Classification of speech dysfluencies with MFCC and LPCC features. Expert Syst. Appl. 39(2), 2157\u20132165 (2012)","journal-title":"Expert Syst. Appl."},{"issue":"3\u20134","key":"18_CR30","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1504\/IJGUC.2015.070680","volume":"6","author":"P Mahesha","year":"2015","unstructured":"Mahesha, P., Vinod, D.: Support vector machine-based stuttering dysfluency classification using gmm supervectors. Int. J. Grid Util. Comput. 6(3\u20134), 143\u2013149 (2015)","journal-title":"Int. J. Grid Util. Comput."},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"18_CR32","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.: MobilenetV2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"18_CR33","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 (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"1","key":"18_CR34","doi-asserted-by":"publisher","first-page":"502","DOI":"10.1109\/TPAMI.2020.3012548","volume":"44","author":"H Xu","year":"2020","unstructured":"Xu, H., Ma, J., Jiang, J., Guo, X., Ling, H.: U2Fusion: a unified unsupervised image fusion network. IEEE Trans. Pattern Anal. Mach. Intell. 44(1), 502\u2013518 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"18_CR35","unstructured":"Tan, M., Le, Q.: EfficientnetV2: smaller models and faster training. In: International Conference on Machine Learning (ICML), pp. 10096\u201310106 (2021)"},{"key":"18_CR36","unstructured":"Ho, J., Kalchbrenner, N., Weissenborn, D., Salimans, T.: Axial attention in multidimensional transformers. arXiv preprint arXiv:1912.12180 (2019)"},{"key":"18_CR37","unstructured":"Bayerl, S.P., von Gudenberg, A.W., H\u00f6nig, F., N\u00f6th, E., Riedhammer, K.: KSoF: the Kassel state of fluency dataset\u2013a therapy centered dataset of stuttering. arXiv preprint arXiv:2203.05383 (2022)"},{"key":"18_CR38","doi-asserted-by":"crossref","unstructured":"Schuller, B.W., et al.: The ACM Multimedia 2022 Computational Paralinguistics Challenge: Vocalisations, Stuttering, Activity, & Mosquitoes, pp. 1\u20135. arXiv Preprint arXiv:2205.06799 (2022)","DOI":"10.1145\/3503161.3551591"},{"key":"18_CR39","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. 8, pp. 18\u201325 (2015)","DOI":"10.25080\/Majora-7b98e3ed-003"},{"issue":"03","key":"18_CR40","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1109\/MCSE.2007.55","volume":"9","author":"JD Hunter","year":"2007","unstructured":"Hunter, J.D.: Matplotlib: a 2D graphics environment. Comput. Sci. Eng. 9(03), 90\u201395 (2007)","journal-title":"Comput. Sci. Eng."}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-4749-2_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T06:04:44Z","timestamp":1693548284000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-4749-2_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819947485","9789819947492"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-4749-2_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"30 July 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Zhengzhou","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 August 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2023a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2023\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}