{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:00:03Z","timestamp":1772827203974,"version":"3.50.1"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2020,2,18]],"date-time":"2020-02-18T00:00:00Z","timestamp":1581984000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,2,18]],"date-time":"2020-02-18T00:00:00Z","timestamp":1581984000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"name":"Research Committee of the Chinese University of Hong Kong"},{"name":"GRF project grant from the Hong Kong Research Grants Council","award":["CUHK14227216"],"award-info":[{"award-number":["CUHK14227216"]}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"crossref","award":["NIH-R01-DC010398"],"award-info":[{"award-number":["NIH-R01-DC010398"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Sign Process Syst"],"published-print":{"date-parts":[[2020,8]]},"DOI":"10.1007\/s11265-019-01511-3","type":"journal-article","created":{"date-parts":[[2020,2,18]],"date-time":"2020-02-18T11:04:03Z","timestamp":1582023843000},"page":"819-830","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["An End-to-End Approach to Automatic Speech Assessment for Cantonese-speaking People with Aphasia"],"prefix":"10.1007","volume":"92","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4606-7174","authenticated-orcid":false,"given":"Ying","family":"Qin","sequence":"first","affiliation":[]},{"given":"Yuzhong","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Tan","family":"Lee","sequence":"additional","affiliation":[]},{"given":"Anthony Pak Hin","family":"Kong","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,2,18]]},"reference":[{"key":"1511_CR1","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1093\/oso\/9780195089349.001.0001","volume-title":"Aphasia: A Clinical Perspective","author":"DF Benson","year":"1996","unstructured":"Benson, D.F., Benson, D.F., Ardila, A. (1996). Aphasia: A Clinical Perspective, (pp. 89\u201398). Oxford: Oxford University Press."},{"issue":"1","key":"1511_CR2","first-page":"153","volume":"10","author":"H Adam","year":"2014","unstructured":"Adam, H. (2014). Dysprosody in aphasia: an acoustic analysis evidence from palestinian arabic. Journal of Language and Linguistic Studies, 10(1), 153\u2013162.","journal-title":"Journal of Language and Linguistic Studies"},{"key":"1511_CR3","unstructured":"National Aphasia Association. (2018). Aphasia definitions. https:\/\/www.aphasia.org\/aphasia-definitions\/, accessed 9 August 2018."},{"key":"1511_CR4","unstructured":"Wikipedia contributors. (2018a). Aphasia \u2014 Wikipedia, the free encyclopedia. https:\/\/en.wikipedia.org\/wiki\/Aphasia, accessed 10 September 2018."},{"key":"1511_CR5","unstructured":"Wikipedia Contributors. (2018). Anomic aphasia \u2014 Wikipedia, the free encyclopedia. https:\/\/en.wikipedia.org\/wiki\/Anomic_aphasia, accessed 10 September 2018."},{"key":"1511_CR6","unstructured":"Peintner, B., Jarrold, W., Vergyri, D., Richey, C., Tempini, M.L.G., Ogar, J. (2008). Learning diagnostic models using speech and language measures. In Proceedings of Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBS) (pp. 4648\u20134651). Vancouver: IEEE."},{"key":"1511_CR7","unstructured":"Fraser, K.C., Rudzicz, F., Rochon, E. (2013). Using text and acoustic features to diagnose progressive aphasia and its subtypes. In Proceedings of Annual Conference of the International Speech Communication Association (INTERSPEECH) (pp. 2177\u20132181). Lyon: ISCA."},{"key":"1511_CR8","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1016\/j.cortex.2012.12.006","volume":"55","author":"KC Fraser","year":"2014","unstructured":"Fraser, K.C., Meltzer, J.A., Graham, N.L., Leonard, C., Hirst, G., Black, S.E., Rochon, E. (2014). Automated classification of primary progressive aphasia subtypes from narrative speech transcripts. Cortex, 55, 43\u201360.","journal-title":"Cortex"},{"key":"1511_CR9","unstructured":"Fraser, K.C., Rudzicz, F., Graham, N., Rochon, E. (2013). Automatic speech recognition in the diagnosis of primary progressive aphasia. In Proceedings of the 4th Workshop on Speech and Language Processing for Assistive Technologies (SLPAT) (pp. 47\u201354). Grenoble: ACL\/ISCA Special Interest Group."},{"key":"1511_CR10","unstructured":"Le, D., & Provost, E.M. (2016). Improving automatic recognition of aphasic speech with Aphasiabank. In Proceedings of Annual Conference of the International Speech Communication Association (INTERSPEECH) (pp. 2681\u20132685). San Francisco: ISCA."},{"key":"1511_CR11","doi-asserted-by":"crossref","unstructured":"Le, D., Licata, K., Provost, E.M. (2018). Automatic quantitative analysis of spontaneous aphasic speech. Speech Communication, 100, 1\u201312.","DOI":"10.1016\/j.specom.2018.04.001"},{"key":"1511_CR12","unstructured":"Kohlschein, C., Klischies, D., Meisen, T., Schuller, B.W., Werner, C.J. (2018). Automatic processing of clinical aphasia data collected during diagnosis sessions: challenges and prospects. In Proceedings of resources and processing of linguistic, para-linguistic and extra-linguistic Data from people with various forms of cognitive\/psychiatric impairments (RaPID-2), satellite of the 11th Language Resources and Evaluation Conference (LREC) (pp. 11\u201318). Miyazaki: ELRA."},{"key":"1511_CR13","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/j.sbspro.2013.09.032","volume":"94","author":"T Lee","year":"2013","unstructured":"Lee, T., Kong, A., Chan, V., Wang, H. (2013). Analysis of auto-aligned and auto-segmented oral discourse by speakers with aphasia: a preliminary study on the acoustic parameter of duration. Procedia, Social and Behavioral Sciences, 94, 71\u201372.","journal-title":"Procedia, Social and Behavioral Sciences"},{"key":"1511_CR14","unstructured":"Lee, T., Liu, Y., Huang, P.W., Chien, J.T., Lam, W.K., Yeung, Y.T., Law, T.K., Lee, K.Y., Kong, A.P.H., Law, S.P. (2016). Automatic speech recognition for acoustical analysis and assessment of cantonese pathological voice and speech. In Proceedings of International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 6475\u20136479). Shanghai: IEEE."},{"key":"1511_CR15","doi-asserted-by":"crossref","unstructured":"Qin, Y., Lee, T., Kong, A.P.H. (2018a). Automatic speech assessment for aphasic patients based on syllable-level embedding and supra-segmental duration features. In Proceedings of International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (pp. 5994\u20135998). Calgary: IEEE.","DOI":"10.1109\/ICASSP.2018.8461289"},{"key":"1511_CR16","doi-asserted-by":"crossref","unstructured":"Qin, Y., Lee, T., Feng, S., Kong, A.P.H. (2018b). Automatic speech assessment for people with aphasia using TDNN-BLSTM with multi-task learning. In Proceedings of Annual Conference of the International Speech Communication Association (INTERSPEECH) (pp. 3418\u20133422). Hyderabad: ISCA.","DOI":"10.21437\/Interspeech.2018-1630"},{"key":"1511_CR17","unstructured":"Graves, A., & Jaitly, N. (2014). Towards end-to-end speech recognition with recurrent neural networks. In Proceedings of International Conference on Machine Learning (ICML) (pp. 1764\u20131772). Beijing: IMLS."},{"key":"1511_CR18","unstructured":"Wu, Y., Schuster, M., Chen, Z., Le, Q.V., Norouzi, M., Macherey, W., Krikun, M., Cao, Y., Gao, Q., Macherey, K., et al. (2016). Google\u2019s neural machine translation system: Bridging the gap between human and machine translation. arXiv:cs.CL\/1609.08144."},{"issue":"8","key":"1511_CR19","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735\u20131780.","journal-title":"Neural Computation"},{"key":"1511_CR20","unstructured":"Cho, K., Van Merri\u00ebnboer, B., Bahdanau, D., Bengio, Y. (1259). On the properties of neural machine translation: Encoder-decoder approaches. arXiv:cs.CL\/1409."},{"key":"1511_CR21","unstructured":"Tang, Y., Huang, Y., Wu, Z., Meng, H., Xu, M., Cai, L. (2016). Question detection from acoustic features using recurrent neural network with gated recurrent unit. In Proceedings of International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (pp. 6125\u20136129). Shanghai: IEEE."},{"key":"1511_CR22","unstructured":"Rana, R. (2016). Gated Recurrent Unit (GRU) for emotion classification from noisy speech. arXiv:cs.HC\/1612.07778."},{"key":"1511_CR23","unstructured":"Chung, H., Lee, Y.K., Lee, S.J., Park, J.G. (2017). Spoken english fluency scoring using convolutional neural networks. In Proceedings of Conference of the Oriental Chapter of the International Coordinating Committee on Speech Databases and Speech I\/O Systems and Assessment (O-COCOSDA) (pp. 1\u20136). Seoul: COCOSDA."},{"key":"1511_CR24","unstructured":"V\u00e1squez-Correa, J., Orozco-Arroyave, J.R., N\u00f6th, E. (2017). Convolutional neural network to model articulation impairments in patients with Parkinson\u2019s disease. In Proceedings of Annual Conference of the International Speech Communication Association (INTERSPEECH) (pp. 314\u2013318). Stockholm: ISCA."},{"key":"1511_CR25","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A. (2016). Learning deep features for discriminative localization. In Proceedings of Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 2921\u20132929). Las Vegas: IEEE."},{"key":"1511_CR26","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D. (2017). Grad-CAM: Visual explanations from deep networks via gradient-based localization. In Proceedings of International Conference on Computer Vision (ICCV) (pp. 618\u2013626). Venice: CVF."},{"key":"1511_CR27","unstructured":"Wu, Y., & Lee, T. (2019). Enhancing sound texture in CNN-based acoustic scene classification. arXiv:cs.SD\/1901.01502."},{"key":"1511_CR28","unstructured":"Kong, A.P.H., & Law, S.P. (2018). Cantonese Aphasiabank: An annotated database of spoken discourse and co-verbal gestures by healthy and language-impaired native cantonese speakers. Behavior research methods, pp. 1\u201314."},{"issue":"11","key":"1511_CR29","doi-asserted-by":"publisher","first-page":"1286","DOI":"10.1080\/02687038.2011.589893","volume":"25","author":"B MacWhinney","year":"2011","unstructured":"MacWhinney, B., Fromm, D., Forbes, M., Holland, A. (2011). Aphasiabank: Methods for studying discourse. Aphasiology, 25(11), 1286\u20131307.","journal-title":"Aphasiology"},{"issue":"1","key":"1511_CR30","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1007\/s10919-014-0200-6","volume":"39","author":"APH Kong","year":"2015","unstructured":"Kong, A.P.H., Law, S.P., Kwan, C.C.Y., Lai, C., Lam, V. (2015). A coding system with independent annotations of gesture forms and functions during verbal communication: Development of a database of speech and gesture (DoSaGE). Journal of Nonverbal Behavior, 39(1), 93\u2013111.","journal-title":"Journal of Nonverbal Behavior"},{"issue":"4","key":"1511_CR31","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1016\/0911-6044(92)90025-R","volume":"7","author":"EM Yiu","year":"1992","unstructured":"Yiu, E.M. (1992). Linguistic assessment of Chinese-speaking aphasics: Development of a Cantonese Aphasia Battery. Journal of Neurolinguistics, 7(4), 379\u2013424.","journal-title":"Journal of Neurolinguistics"},{"key":"1511_CR32","doi-asserted-by":"crossref","unstructured":"Kong, A.P.H. (2016). Analysis of neurogenic disordered discourse production: From theory to practice. Routledge.","DOI":"10.4324\/9781315639376"},{"key":"1511_CR33","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E. (2012). ImageNet classification with deep convolutional neural networks. In Proceedings of Annual Conference on Neural Information Processing Systems (NIPS) (pp. 1097\u20131105). Lake Tahoe: NIPS Foundation."},{"key":"1511_CR34","unstructured":"Simonyan, K., & Zisserman, A. (1556). Very deep convolutional networks for large-scale image recognition. arXiv:cs.CV\/1409."},{"key":"1511_CR35","unstructured":"Lin, M., Chen, Q., Yan, S. (2013). Network in network. arXiv:cs.NE\/1312.4400."},{"key":"1511_CR36","unstructured":"Kingma, DP, & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv:cs.LG\/1412.6980."},{"key":"1511_CR37","unstructured":"Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., DeVito, Z., Lin, Z., Desmaison, A., Antiga, L., Lerer, A. (2017). Automatic differentiation in pytorch In Conference on Neural Information Processing Systems Workshop (NIPS-w), NIPS Foundation, Long Beach."},{"issue":"1","key":"1511_CR38","first-page":"89","volume":"3","author":"M Vuk","year":"2006","unstructured":"Vuk, M., & Curk, T. (2006). ROC Curve, lift chart and calibration plot. Metodoloski zvezki, 3(1), 89.","journal-title":"Metodoloski zvezki"},{"issue":"8","key":"1511_CR39","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1016\/j.patrec.2005.10.010","volume":"27","author":"T Fawcett","year":"2006","unstructured":"Fawcett, T. (2006). An introduction to ROC analysis. Pattern Recognition Letters, 27(8), 861\u2013874.","journal-title":"Pattern Recognition Letters"},{"issue":"2","key":"1511_CR40","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1007\/BF02295996","volume":"12","author":"Q McNemar","year":"1947","unstructured":"McNemar, Q. (1947). Note on the sampling error of the difference between correlated proportions or percentages. Psychometrika, 12(2), 153\u2013157.","journal-title":"Psychometrika"},{"issue":"7","key":"1511_CR41","doi-asserted-by":"publisher","first-page":"1895","DOI":"10.1162\/089976698300017197","volume":"10","author":"TG Dietterich","year":"1998","unstructured":"Dietterich, T.G. (1998). Approximate statistical tests for comparing supervised classification learning algorithms. Neural Computation, 10(7), 1895\u20131923.","journal-title":"Neural Computation"}],"container-title":["Journal of Signal Processing Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-019-01511-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11265-019-01511-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-019-01511-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,31]],"date-time":"2024-07-31T19:08:22Z","timestamp":1722452902000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11265-019-01511-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2,18]]},"references-count":41,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2020,8]]}},"alternative-id":["1511"],"URL":"https:\/\/doi.org\/10.1007\/s11265-019-01511-3","relation":{},"ISSN":["1939-8018","1939-8115"],"issn-type":[{"value":"1939-8018","type":"print"},{"value":"1939-8115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,2,18]]},"assertion":[{"value":"15 February 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 October 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 December 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 February 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}