{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T16:58:31Z","timestamp":1768409911363,"version":"3.49.0"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2020,4,24]],"date-time":"2020-04-24T00:00:00Z","timestamp":1587686400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,4,24]],"date-time":"2020-04-24T00:00:00Z","timestamp":1587686400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001843","name":"Science and Engineering Research Board","doi-asserted-by":"crossref","award":["YSS\/2014\/000563"],"award-info":[{"award-number":["YSS\/2014\/000563"]}],"id":[{"id":"10.13039\/501100001843","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Circuits Syst Signal Process"],"published-print":{"date-parts":[[2020,11]]},"DOI":"10.1007\/s00034-020-01419-5","type":"journal-article","created":{"date-parts":[[2020,4,24]],"date-time":"2020-04-24T07:26:47Z","timestamp":1587713207000},"page":"5543-5567","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Improving Speech to Text Alignment Based on Repetition Detection for Dysarthric Speech"],"prefix":"10.1007","volume":"39","author":[{"given":"G.","family":"Diwakar","sequence":"first","affiliation":[]},{"given":"Veena","family":"Karjigi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,4,24]]},"reference":[{"key":"1419_CR1","unstructured":"Alignment results [online] available from: https:\/\/github.com\/ytyeung\/IS2015alignment"},{"key":"1419_CR2","unstructured":"B. Bigi, K. Klessa, L. Georgeton, C. Meunier, A syllable-based analysis of speech temporal organization: a comparison between speaking styles in dysarthric and healthy populations, in INTERSPEECH (2015), pp. 2977\u20132981"},{"issue":"9","key":"1419_CR3","doi-asserted-by":"publisher","first-page":"1510","DOI":"10.1109\/TNSRE.2016.2638830","volume":"25","author":"S Chandrakala","year":"2017","unstructured":"S. Chandrakala, N. Rajeswari, Representation learning based speech assistive system for persons with dysarthria. IEEE Trans. Neural Syst. Rehabil. Eng. 25(9), 1510\u20131517 (2017)","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"1419_CR4","unstructured":"CMU-Sphinx: Open Source Toolkit for Speech Recognition. http:\/\/cmusphinx.sourceforge.net"},{"key":"1419_CR5","unstructured":"G. Diwakar, V. Karjigi, Repetition detection in dysarthric speech, in IEEE International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET), Chennai (2017), pp. 1178\u20131181"},{"key":"1419_CR6","unstructured":"J.R. Glass, V.W. Zue, Multi-level acoustic segmentation of continuous speech, in IEEE International Conference on Acoustics, Speech, and Signal Processing (1988), pp. 429\u2013432"},{"key":"1419_CR7","doi-asserted-by":"crossref","unstructured":"A. Haubold, J.R. Kender, Alignment of speech to highly imperfect text transcriptions (2007)","DOI":"10.1109\/ICME.2007.4284627"},{"issue":"2","key":"1419_CR8","doi-asserted-by":"publisher","first-page":"743","DOI":"10.1016\/j.specom.2007.05.001","volume":"49","author":"AB Kain","year":"2007","unstructured":"A.B. Kain, J.-P. Hosom, X. Niu, J.P.H. van Santen, M. Fried-Oken, J. Staehely, Improving the intelligibility of dysarthric speech. Speech Commun. 49(2), 743\u2013759 (2007)","journal-title":"Speech Commun."},{"key":"1419_CR9","unstructured":"M. Kaushik, M. Trinkle, A.H. Sakhtsari, Automatic detection and removal of disfluencies from spontaneous speech, in Australasian International Conference on Speech Science and Technology (SST) (2010), pp. 98\u2013101"},{"key":"1419_CR10","unstructured":"H. Kim, M. Hasegawa-Johnson, A. Perlman, J. Gunderson, T.S. Huang, K. Watkin, S. Frame, Dysarthric speech database for universal access research, in INTERSPEECH (2008), pp. 1741\u20131744"},{"issue":"9","key":"1419_CR11","doi-asserted-by":"publisher","first-page":"1581","DOI":"10.1109\/TNSRE.2017.2681691","volume":"25","author":"M Kim","year":"2017","unstructured":"M. Kim, Y. Kim, J. Yoo, J. Wang, H. Kim, Regularized speaker adaptation of KL-HMM for dysarthric speech recognition. IEEE Trans. Neural Syst. Rehabil. Eng. 25(9), 1581\u20131591 (2017)","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"1419_CR12","unstructured":"J. Lopes, S. Giampiero, S. Gabriel, A. Alberto, G. Joakim, B. Fernando, M. Raveesh, T. Isabel, Detecting repetitions in spoken dialogue systems using phonetic distances, in INTERSPEECH (2015), pp. 1805\u20131809"},{"key":"1419_CR13","unstructured":"X. Menendez-Pidal, J.B. Polikoff, S.M. Peters, J.E. Leonzio, H.T. Bunnell, The Nemours database of dysarthric speech, in International Conference on Spoken Language (1996), pp. 1962\u20131965"},{"key":"1419_CR14","unstructured":"K.T. Mengistu, F. Rudzicz, Adapting acoustic and lexical models to dysarthric speech, in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2011), pp. 4924\u20134927"},{"key":"1419_CR15","unstructured":"O.C. Morales, S. Cox, Modelling confusion matrices to improve speech recognition accuracy, with an application to dysarthric speech, in INTERSPEECH (2007), pp. 1565\u20131568"},{"key":"1419_CR16","unstructured":"T. Nagarajan, H.A. Murthy, R.M. Hegde, Segmentation of speech into syllable-like units, in European Conference on Speech Communication and Technology (2003), pp. 2893\u20132896"},{"key":"1419_CR17","unstructured":"S. Oue, R. Marxer, F. Rudzicz, Automatic dysfluency detection in Dysarthric speech using deep belief networks, in Workshop on Speech and Language Processing for Assistive Technologies (SLPAT) (2015), pp. 60\u201364"},{"key":"1419_CR18","unstructured":"D. Povey, A. Ghoshal, G. Boulianne, L. Burget, O. Glembek, N. Goel, M. Hannemann, The Kaldi speech recognition toolkit, in IEEE Workshop on Automatic Speech Recognition and Understanding (2011)"},{"key":"1419_CR19","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1016\/j.cognition.2017.11.003","volume":"171","author":"O R\u00e4s\u00e4nen","year":"2018","unstructured":"O. R\u00e4s\u00e4nen, G. Doyle, M.C. Frank, Pre-linguistic segmentation of speech into syllable-like units. Cognition 171, 130\u2013150 (2018)","journal-title":"Cognition"},{"key":"1419_CR20","unstructured":"K.M. Ravikumar, B. Reddy, R. Rajagopal, H.C. Nagaraj, Automatic detection of syllable repetition in read speech for objective assessment of stuttered disfluencies, in World Academy Science, Engineering and Technology (2008), pp. 270\u2013273"},{"key":"1419_CR21","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1007\/s10579-011-9145-0","volume":"46","author":"F Rudzicz","year":"2012","unstructured":"F. Rudzicz, A.K. Namasivayam, T. Wolff, The TORGO database of acoustic and articulatory speech from speakers with dysarthria. Lang. Resour. Eval. 46, 523\u2013541 (2012)","journal-title":"Lang. Resour. Eval."},{"key":"1419_CR22","unstructured":"M. Sharma, R. Mammone, Blind speech segmentation: automatic segmentation of speech without linguistic knowledge, in International Conference on Spoken Language, ICSLP (1996), pp. 1237\u20131240"},{"key":"1419_CR23","unstructured":"Sphinx Knowledge Base Tool\u2014VERSION 3 [online] available from: http:\/\/www.speech.cs.cmu.edu\/tools\/lmtool-new.html"},{"key":"1419_CR24","doi-asserted-by":"crossref","unstructured":"R. Sriranjani, S. Umesh, M.R. Reddy, Pronunciation adaptation for disordered speech recognition using state-specific vectors of phone-cluster adaptive training, in Workshop on Speech and Language Processing for Assistive Technologies (2015)","DOI":"10.18653\/v1\/W15-5113"},{"key":"1419_CR25","unstructured":"T. Svendsen, F. Soong, On the automatic segmentation of speech signals, in IEEE International Conference on Acoustics, Speech, and Signal Processing (1987), pp. 77\u201380"},{"key":"1419_CR26","doi-asserted-by":"publisher","first-page":"1008","DOI":"10.1109\/78.80941","volume":"39","author":"JP Van Hemert","year":"1991","unstructured":"J.P. Van Hemert, Automatic segmentation of speech. IEEE Trans. Signal Process. 39, 1008\u20131012 (1991)","journal-title":"IEEE Trans. Signal Process."},{"key":"1419_CR27","unstructured":"Y.T. Yeung, K.H. Wong, H. Meng, Improving automatic forced alignment for dysarthric speech transcription, in INTERSPEECH (2015), pp. 2991\u20132995"},{"key":"1419_CR28","volume-title":"Clinical Management of Dysarthric Speakers","author":"KM Yorkston","year":"1988","unstructured":"K.M. Yorkston, D.R. Beukelman, K.R. Bell, Clinical Management of Dysarthric Speakers (College-Hill Press, San Diego, CA, 1988)"},{"key":"1419_CR29","volume-title":"The HTK Book","author":"S Young","year":"1995","unstructured":"S. Young, J. Odell, D. Ollason, V. Valtchev, P. Woodland, The HTK Book (Cambridge University, Cambridge, 1995)"}],"container-title":["Circuits, Systems, and Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-020-01419-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00034-020-01419-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-020-01419-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,25]],"date-time":"2021-04-25T06:09:14Z","timestamp":1619330954000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00034-020-01419-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4,24]]},"references-count":29,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2020,11]]}},"alternative-id":["1419"],"URL":"https:\/\/doi.org\/10.1007\/s00034-020-01419-5","relation":{},"ISSN":["0278-081X","1531-5878"],"issn-type":[{"value":"0278-081X","type":"print"},{"value":"1531-5878","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,4,24]]},"assertion":[{"value":"11 May 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 April 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 April 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 April 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}