{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T17:23:35Z","timestamp":1769880215995,"version":"3.49.0"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2019,4,4]],"date-time":"2019-04-04T00:00:00Z","timestamp":1554336000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J AUDIO SPEECH MUSIC PROC."],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1186\/s13636-019-0149-9","type":"journal-article","created":{"date-parts":[[2019,4,4]],"date-time":"2019-04-04T14:03:14Z","timestamp":1554386594000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Feature trajectory dynamic time warping for clustering of speech segments"],"prefix":"10.1186","volume":"2019","author":[{"given":"Lerato","family":"Lerato","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7341-1017","authenticated-orcid":false,"given":"Thomas","family":"Niesler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,4,4]]},"reference":[{"issue":"1","key":"149_CR1","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1109\/TASSP.1978.1163055","volume":"26","author":"H. Sakoe","year":"1978","unstructured":"H. Sakoe, S. Chiba, Dynamic programming algorithm optimization for spoken word recognition. IEEE Trans. Acoust. Speech Signal Proc.26(1), 43\u201349 (1978).","journal-title":"IEEE Trans. Acoust. Speech Signal Proc."},{"issue":"6","key":"149_CR2","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1109\/TASSP.1980.1163491","volume":"28","author":"C. Myers","year":"1980","unstructured":"C. Myers, L. R. Rabiner, A. E. Rosenberg, Performance tradeoffs in dynamic time warping algorithms for isolated word recognition. IEEE Trans. Acoust. Speech Signal Proc.28(6), 623\u2013635 (1980).","journal-title":"IEEE Trans. Acoust. Speech Signal Proc."},{"key":"149_CR3","first-page":"138","volume":"2","author":"L. Muda","year":"2010","unstructured":"L. Muda, M. Begam, I. Elamvazuthi, Voice recognition algorithms using mel frequency cepstral coefficient (MFCC) and dynamic time warping (DTW) techniques. J. Comput.2:, 138\u2013143 (2010).","journal-title":"J. Comput."},{"issue":"2","key":"149_CR4","doi-asserted-by":"publisher","first-page":"e85458","DOI":"10.1371\/journal.pone.0085458","volume":"9","author":"X. Zhang","year":"2014","unstructured":"X. Zhang, J. Sun, Z. Luo, One-against-all weighted dynamic time warping for language-independent and speaker-dependent speech recognition in adverse conditions. PloS ONE. 9(2), e85458 (2014).","journal-title":"PloS ONE"},{"key":"149_CR5","first-page":"398","volume-title":"Proc. IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","author":"Y. Zhang","year":"2009","unstructured":"Y. Zhang, J. R. Glass, in Proc. IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU). Unsupervised spoken keyword spotting via segmental DTW on Gaussian posteriorgrams (IEEEMerano, 2009), pp. 398\u2013403."},{"key":"149_CR6","first-page":"1","volume-title":"Proc. Interspeech","author":"X. Anguera","year":"2013","unstructured":"X. Anguera, in Proc. Interspeech. Information retrieval-based dynamic time warping (International Speech Communication AssociationLyon, 2013), pp. 1\u20135."},{"issue":"9","key":"149_CR7","doi-asserted-by":"publisher","first-page":"1389","DOI":"10.1109\/TASLP.2015.2438543","volume":"23","author":"L. -S. Lee","year":"2015","unstructured":"L. -S. Lee, J. Glass, H. -Y. Lee, C. -A. Chan, Spoken content retrieval\u2014beyond cascading speech recognition with text retrieval. Audio Speech Lang. Process. IEEE\/ACM Trans.23(9), 1389\u20131420 (2015).","journal-title":"Audio Speech Lang. Process. IEEE\/ACM Trans."},{"key":"149_CR8","doi-asserted-by":"crossref","unstructured":"R. Menon, H. Kamper, E. Yilmaz, J. Quinn, T. Niesler, in Proc. The 6th Intl. Workshop on Spoken Language Technologies for Under-Resourced Languages. ASR-free CNN-DTW keyword spotting using multilingual bottleneck features for almost zero-resource languages (Gurugram, 2018), pp. 20\u201324.","DOI":"10.21437\/SLTU.2018-38"},{"key":"149_CR9","doi-asserted-by":"publisher","first-page":"2608","DOI":"10.21437\/Interspeech.2018-1580","volume-title":"Interspeech","author":"R. Menon","year":"2018","unstructured":"R. Menon, H. Kamper, J. Quinn, T. Niesler, in Interspeech. Fast ASR-free and almost zero-resource keyword spotting using DTW and CNNs for humanitarian monitoring (ISCAHyderabad, 2018), pp. 2608\u20132612."},{"key":"149_CR10","first-page":"53","volume-title":"Proc. IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","author":"A. Park","year":"2005","unstructured":"A. Park, J. Glass, in Proc. IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU). Towards unsupervised pattern discovery in speech (IEEESan Juan, 2005), pp. 53\u201358."},{"key":"149_CR11","first-page":"386","volume-title":"Proc. IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","author":"O. Walter","year":"2013","unstructured":"O. Walter, T. Korthals, R. Haeb-Umbach, B. Raj, in Proc. IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU). A hierarchical system for word discovery exploiting DTW-based initialization (IEEEOlomouc, 2013), pp. 386\u2013391."},{"key":"149_CR12","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1016\/j.eswa.2016.06.012","volume":"62","author":"M. \u0141uczak","year":"2016","unstructured":"M. \u0141uczak, Hierarchical clustering of time series data with parametric derivative dynamic time warping. Expert Syst. Appl.62:, 116\u2013130 (2016).","journal-title":"Expert Syst. Appl."},{"issue":"9","key":"149_CR13","doi-asserted-by":"publisher","first-page":"2231","DOI":"10.1016\/j.patcog.2010.09.022","volume":"44","author":"Y. -S. Jeong","year":"2011","unstructured":"Y. -S. Jeong, M. K. Jeong, O. A. Omitaomu, Weighted dynamic time warping for time series classification. Pattern Recog.44(9), 2231\u20132240 (2011).","journal-title":"Pattern Recog."},{"issue":"12","key":"149_CR14","doi-asserted-by":"publisher","first-page":"1407","DOI":"10.1016\/j.patrec.2007.02.016","volume":"28","author":"A. P. Shanker","year":"2007","unstructured":"A. P. Shanker, A. Rajagopalan, Off-line signature verification using DTW. Pattern Recogn. Lett.28(12), 1407\u20131414 (2007).","journal-title":"Pattern Recogn. Lett."},{"key":"149_CR15","first-page":"99","volume-title":"Proc. IEEE Workshop on Automatic Speech Recognition and Understanding","author":"S. Sagayama","year":"1999","unstructured":"S. Sagayama, S. Matsuda, M. Nakai, H. Shimodaira, in Proc. IEEE Workshop on Automatic Speech Recognition and Understanding. Asynchronous-transition HMM for acoustic modeling (IEEEKeystone, 1999), pp. 99\u2013102."},{"key":"149_CR16","first-page":"729","volume-title":"Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"T. Svendsen","year":"1989","unstructured":"T. Svendsen, K. K. Paliwal, E. Harborg, P. O. Husoy, in Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). An improved sub-word based speech recognizer (IEEEGlasgow, 1989), pp. 729\u2013732."},{"key":"149_CR17","first-page":"108","volume-title":"Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"K. K. Paliwal","year":"1990","unstructured":"K. K. Paliwal, in Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Lexicon-building methods for an acoustic sub-word based speech recognizer (IEEEAlbuquerque, 1990), pp. 108\u2013111."},{"key":"149_CR18","first-page":"2297","volume-title":"Proc. Interspeech","author":"H. Wang","year":"2013","unstructured":"H. Wang, T. Lee, C. Leung, B. Ma, H. Li, in Proc. Interspeech. Unsupervised mining of acoustic subword units with segment-level Gaussian posteriograms (ISCALyon, 2013), pp. 2297\u20132301."},{"issue":"6","key":"149_CR19","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1109\/MSP.2012.2210952","volume":"29","author":"K. Livescu","year":"2012","unstructured":"K. Livescu, E. Fosler-Lussier, F. Metze, Subword modeling for automatic speech recognition: past, present, and emerging approaches. IEEE Signal Proc. Mag.29(6), 44\u201357 (2012).","journal-title":"IEEE Signal Proc. Mag."},{"key":"149_CR20","volume-title":"Proc. IEEE Spoken Language Technology Workshop (SLT)","author":"H. Kamper","year":"2014","unstructured":"H. Kamper, A. Jansen, S. King, S. Goldwater, in Proc. IEEE Spoken Language Technology Workshop (SLT). Unsupervised lexical clustering of speech segments using fixed-dimensional acoustic embeddings (IEEESouth Lake Tahoe, 2014)."},{"key":"149_CR21","doi-asserted-by":"crossref","unstructured":"E. J Keogh, M. J. Pazzani, in Proc. SIAM International Conference on Data Mining, 1. Derivative Dynamic Time Warping (Society for Industrial and Applied Mathematics, 2001), pp. 1\u201311.","DOI":"10.1137\/1.9781611972719.1"},{"key":"149_CR22","volume-title":"Algorithms for Clustering Data","author":"A. K. Jain","year":"1988","unstructured":"A. K. Jain, R. C. Dubes, Algorithms for Clustering Data (Prentice-Hall, Inc., Upper Saddle River, 1988)."},{"key":"149_CR23","unstructured":"F. Murtagh, P. Contreras, Methods of hierarchical clustering. Comput. Res. Repository. abs\/1105.0121: (2011). http:\/\/arxiv.org\/abs\/1105.0121. Accessed 12 Sept 2018."},{"issue":"4","key":"149_CR24","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1007\/s10791-008-9066-8","volume":"12","author":"E. Amigo","year":"2009","unstructured":"E. Amigo, J. A. J. Gonzalo, F. Verdejo, A comparison of extrinsic clustering evaluation metrics based on formal constraints. Inf. Retr.12(4), 461\u2013486 (2009).","journal-title":"Inf. Retr."},{"key":"149_CR25","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1145\/312129.312186","volume-title":"Proc. Fifth ACM SIGKDD Conference on Knowledge Discovery and Data Mining","author":"B. Larsen","year":"1999","unstructured":"B. Larsen, C. Aone, in Proc. Fifth ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Fast and effective text mining using linear-time document clustering (ACMNew York, 1999), pp. 16\u201322."},{"key":"149_CR26","first-page":"2837","volume":"11","author":"N. X. Vinh","year":"2010","unstructured":"N. X. Vinh, J. Epps, J. Bailey, Information theoretic measures for clusterings comparison: variants, properties, normalisation and correction for chance. J. Mach. Learn. Res.11:, 2837\u20132854 (2010).","journal-title":"J. Mach. Learn. Res."},{"issue":"10-12","key":"149_CR27","doi-asserted-by":"publisher","first-page":"2319","DOI":"10.1016\/j.neucom.2008.12.011","volume":"72","author":"J. Wu","year":"2009","unstructured":"J. Wu, H. Xiong, J. Chen, Towards understanding hierarchical clustering: a data distribution perspective. Neurocomputing. 72(10-12), 2319\u20132330 (2009).","journal-title":"Neurocomputing"},{"key":"149_CR28","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1109\/SBRN.2012.25","volume-title":"2012 Brazilian Symposium on Neural Networks","author":"M. C. P. de Souto","year":"2012","unstructured":"M. C. P. de Souto, A. L. V. Coelho, K. Faceli, T. C. Sakata, V. Bonadia, I. G. Costa, in 2012 Brazilian Symposium on Neural Networks. A comparison of external clustering evaluation indices in the context of imbalanced data sets (IEEE Computer SocietyCuritiba, 2012), pp. 49\u201354."},{"issue":"3","key":"149_CR29","doi-asserted-by":"publisher","first-page":"645","DOI":"10.1109\/TNN.2005.845141","volume":"16","author":"R. Xu","year":"2005","unstructured":"R. Xu, D. Wunsch, Survey of clustering algorithms. IEEE Trans. Neural Netw.16(3), 645\u2013678 (2005).","journal-title":"IEEE Trans. Neural Netw."},{"issue":"3","key":"149_CR30","doi-asserted-by":"publisher","first-page":"274","DOI":"10.1007\/s00357-014-9161-z","volume":"31","author":"F. Murtagh","year":"2014","unstructured":"F. Murtagh, P. Legendre, Ward\u2019s hierarchical agglomerative clustering method: which algorithms implement Ward\u2019s criterion?J. Classif.31(3), 274\u2013295 (2014). \n                    https:\/\/doi.org\/10.1007\/s00357-014-9161-z\n                    \n                  .","journal-title":"J. Classif."},{"key":"149_CR31","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511809071","volume-title":"Introduction to Information Retrieval","author":"C. D. Manning","year":"2008","unstructured":"C. D. Manning, P. Raghavan, Introduction to Information Retrieval (Cambridge University Press, New York, 2008)."},{"key":"149_CR32","first-page":"27403","volume":"93","author":"J. S. Garofolo","year":"1993","unstructured":"J. S. Garofolo, L. F. Lamel, W. M. Fisher, J. G. Fiscus, D. S. Pallett, N. Dahlgren, V. Zue, DARPA TIMIT acoustic-phonetic continous speech corpus CD-ROM. NIST speech disc 1-1.1. NASA STI\/Recon Technical Report n. 93:, 27403 (1993).","journal-title":"NASA STI\/Recon Technical Report n"},{"issue":"4","key":"149_CR33","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1016\/S0167-6393(02)00048-1","volume":"39","author":"B. Imperl","year":"2003","unstructured":"B. Imperl, Z. Kacic, B. Horvat, A. Zgank, Clustering of triphones using phoneme similarity estimation for the definition of a multilingual set of triphones. Speech Comm.39(4), 353\u2013366 (2003).","journal-title":"Speech Comm."},{"key":"149_CR34","unstructured":"M. Lichman, UCI machine learning repository (2013). \n                    http:\/\/archive.ics.uci.edu\/ml\n                    \n                  . Accessed 25 Oct 2018."},{"issue":"4","key":"149_CR35","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","volume":"28","author":"S. B. Davis","year":"1980","unstructured":"S. B. Davis, P. Mermelstein, Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Trans. Acoust. Speech Sig. Process.28(4), 357\u2013366 (1980).","journal-title":"IEEE Trans. Acoust. Speech Sig. Process."},{"issue":"4","key":"149_CR36","doi-asserted-by":"publisher","first-page":"1738","DOI":"10.1121\/1.399423","volume":"87","author":"H. Hermansky","year":"1990","unstructured":"H. Hermansky, Perceptual linear predictive (PLP) analysis of speech. J. Acoust. Soc. Am.87(4), 1738\u20131752 (1990).","journal-title":"J. Acoust. Soc. Am."},{"key":"149_CR37","volume-title":"The HTK Book, Version 3.4","author":"S. J. Young","year":"2006","unstructured":"S. J. Young, G. Evermann, M. J. F. Gales, T. Hain, D. Kershaw, G. Moore, J. Odell, D. Ollason, D. Povey, V. Valtchev, P. C. Woodland, The HTK Book, Version 3.4 (Cambridge University Engineering Department, Cambridge, 2006)."}],"container-title":["EURASIP Journal on Audio, Speech, and Music Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13636-019-0149-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s13636-019-0149-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13636-019-0149-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,4,2]],"date-time":"2020-04-02T23:04:37Z","timestamp":1585868677000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmp-eurasipjournals.springeropen.com\/articles\/10.1186\/s13636-019-0149-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4,4]]},"references-count":37,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2019,12]]}},"alternative-id":["149"],"URL":"https:\/\/doi.org\/10.1186\/s13636-019-0149-9","relation":{},"ISSN":["1687-4722"],"issn-type":[{"value":"1687-4722","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,4,4]]},"assertion":[{"value":"7 November 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 March 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 April 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare that they have no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Publisher\u2019s Note"}}],"article-number":"6"}}