{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T04:13:26Z","timestamp":1749615206478,"version":"3.41.0"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319459240"},{"type":"electronic","value":"9783319459257"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-45925-7_7","type":"book-chapter","created":{"date-parts":[[2016,9,20]],"date-time":"2016-09-20T14:11:34Z","timestamp":1474380694000},"page":"80-95","source":"Crossref","is-referenced-by-count":3,"title":["Articulatory Gesture Rich Representation Learning of Phonological Units in Low Resource Settings"],"prefix":"10.1007","author":[{"given":"Brij Mohan Lal","family":"Srivastava","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manish","family":"Shrivastava","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,9,21]]},"reference":[{"key":"7_CR1","unstructured":"Anguera, X., Dupoux, E., Jansen, A., Versteegh, M., Schatz, T., Thiolli\u00e8re, R., Ludusan, B.: The zero resource speech challenge"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Badino, L., Mereta, A., Rosasco, L.: Discovering discrete subword units with binarized autoencoders and hidden-Markov-model encoders. In: Sixteenth Annual Conference of the International Speech Communication Association (2015)","DOI":"10.21437\/Interspeech.2015-639"},{"issue":"6","key":"7_CR3","doi-asserted-by":"crossref","first-page":"1373","DOI":"10.1162\/089976603321780317","volume":"15","author":"M Belkin","year":"2003","unstructured":"Belkin, M., Niyogi, P.: Laplacian eigenmaps for dimensionality reduction and data representation. Neural Comput. 15(6), 1373\u20131396 (2003)","journal-title":"Neural Comput."},{"issue":"4","key":"7_CR4","doi-asserted-by":"crossref","first-page":"1001","DOI":"10.1121\/1.383319","volume":"66","author":"SE Blumstein","year":"1979","unstructured":"Blumstein, S.E., Stevens, K.N.: Acoustic invariance in speech production: evidence from measurements of the spectral characteristics of stop consonants. J. Acoust. Soc. Am. 66(4), 1001\u20131017 (1979)","journal-title":"J. Acoust. Soc. Am."},{"issue":"02","key":"7_CR5","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1017\/S0952675700001019","volume":"6","author":"CP Browman","year":"1989","unstructured":"Browman, C.P., Goldstein, L.: Articulatory gestures as phonological units. Phonology 6(02), 201\u2013251 (1989)","journal-title":"Phonology"},{"issue":"3\u20134","key":"7_CR6","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1159\/000261913","volume":"49","author":"CP Browman","year":"1992","unstructured":"Browman, C.P., Goldstein, L.: Articulatory phonology: an overview. Phonetica 49(3\u20134), 155\u2013180 (1992)","journal-title":"Phonetica"},{"key":"7_CR7","first-page":"175","volume-title":"Mind as Motion","author":"CP Browman","year":"1995","unstructured":"Browman, C.P., Goldstein, L.: Dynamics and articulatory phonology. In: Port, R.F., van Gelder, T. (eds.) Mind as Motion, pp. 175\u2013193. MIT Press, Cambridge (1995)"},{"issue":"01","key":"7_CR8","first-page":"219","volume":"3","author":"CP Browman","year":"1986","unstructured":"Browman, C.P., Goldstein, L.M.: Towards an articulatory phonology. Phonology 3(01), 219\u2013252 (1986)","journal-title":"Phonology"},{"key":"7_CR9","unstructured":"Chollet, F.: Keras (2015). https:\/\/github.com\/fchollet\/keras"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Errity, A., McKenna, J.: An investigation of manifold learning for speech analysis. In: INTERSPEECH. Citeseer (2006)","DOI":"10.21437\/Interspeech.2006-628"},{"issue":"4","key":"7_CR11","doi-asserted-by":"crossref","first-page":"653","DOI":"10.1007\/s11390-010-9355-8","volume":"25","author":"D G\u00f6r\u00fcr","year":"2010","unstructured":"G\u00f6r\u00fcr, D., Rasmussen, C.E.: Dirichlet process gaussian mixture models: choice of the base distribution. J. Comput. Sci. Technol. 25(4), 653\u2013664 (2010)","journal-title":"J. Comput. Sci. Technol."},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Greenberg, S., Kingsbury, B.E.: The modulation spectrogram: in pursuit of an invariant representation of speech. In: 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 1997, vol. 3, pp. 1647\u20131650. IEEE (1997)","DOI":"10.1109\/ICASSP.1997.598826"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1026\u20131034 (2015)","DOI":"10.1109\/ICCV.2015.123"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Kamper, H., Elsner, M., Jansen, A., Goldwater, S.: Unsupervised neural network based feature extraction using weak top-down constraints. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5818\u20135822. IEEE (2015)","DOI":"10.1109\/ICASSP.2015.7179087"},{"key":"7_CR15","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization (2014). arXiv preprint arXiv:1412.6980"},{"issue":"5","key":"7_CR16","doi-asserted-by":"crossref","first-page":"1089","DOI":"10.1109\/JPROC.2013.2238591","volume":"101","author":"C-H Lee","year":"2013","unstructured":"Lee, C.-H., Siniscalchi, S.M.: An information-extraction approach to speech processing: analysis, detection, verification, and recognition. Proc. IEEE 101(5), 1089\u20131115 (2013)","journal-title":"Proc. IEEE"},{"key":"7_CR17","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/j.sigpro.2014.09.005","volume":"112","author":"B Leng","year":"2015","unstructured":"Leng, B., Guo, S., Zhang, X., Xiong, Z.: 3D object retrieval with stacked local convolutional autoencoder. Sig. Process. 112, 119\u2013128 (2015)","journal-title":"Sig. Process."},{"key":"7_CR18","unstructured":"Makhzani, A., Frey, B.J.: Winner-take-all autoencoders. In: Advances in Neural Information Processing Systems, pp. 2773\u20132781 (2015)"},{"key":"7_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1007\/978-3-642-21735-7_7","volume-title":"Artificial Neural Networks and Machine Learning \u2013 ICANN 2011","author":"J Masci","year":"2011","unstructured":"Masci, J., Meier, U., Cire\u015fan, D., Schmidhuber, J.: Stacked convolutional auto-encoders for hierarchical feature extraction. In: Honkela, T. (ed.) ICANN 2011, Part I. LNCS, vol. 6791, pp. 52\u201359. Springer, Heidelberg (2011)"},{"key":"7_CR20","unstructured":"Ostendorf, M.: Moving beyond the \u2018beads-on-a-string\u2019 model of speech. In: Proceedings of the IEEE ASRU Workshop, pp. 79\u201384. Citeseer (1999)"},{"key":"7_CR21","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., Duchesnay, E.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011)","journal-title":"J. Mach. Learn. Res."},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Renshaw, D., Kamper, H., Jansen, A., Goldwater, S.: A comparison of neural network methods for unsupervised representation learning on the zero resource speech challenge. In: Proceedings of the Interspeech (2015)","DOI":"10.21437\/Interspeech.2015-644"},{"issue":"5500","key":"7_CR23","doi-asserted-by":"crossref","first-page":"2323","DOI":"10.1126\/science.290.5500.2323","volume":"290","author":"ST Roweis","year":"2000","unstructured":"Roweis, S.T., Saul, L.K.: Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500), 2323\u20132326 (2000)","journal-title":"Science"},{"issue":"5500","key":"7_CR24","doi-asserted-by":"crossref","first-page":"2319","DOI":"10.1126\/science.290.5500.2319","volume":"290","author":"JB Tenenbaum","year":"2000","unstructured":"Tenenbaum, J.B., Langford, J.C., De Silva, V.: A global geometric framework for nonlinear dimensionality reduction. Science 290(5500), 2319\u20132323 (2000)","journal-title":"Science"},{"key":"7_CR25","doi-asserted-by":"crossref","unstructured":"Tomar, V.S., Rose, R.C.: Application of a locality preserving discriminant analysis approach to ASR. In: 2012 11th International Conference on Information Science, Signal Processing and their Applications (ISSPA), pp. 103\u2013107. IEEE (2012)","DOI":"10.1109\/ISSPA.2012.6310443"},{"key":"7_CR26","doi-asserted-by":"crossref","unstructured":"Tomar, V.S., Rose, R.C.: Efficient manifold learning for speech recognition using locality sensitive hashing. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6995\u20136999. IEEE (2013)","DOI":"10.1109\/ICASSP.2013.6639018"},{"key":"7_CR27","doi-asserted-by":"crossref","unstructured":"Tomar, V.S., Rose, R.C.: Noise aware manifold learning for robust speech recognition. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7087\u20137091. IEEE (2013)","DOI":"10.1109\/ICASSP.2013.6639037"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"You, M., Chen, C., Bu, J., Liu, J., Tao, J.: Emotional speech analysis on nonlinear manifold. In: 18th International Conference on Pattern Recognition, ICPR 2006, vol. 3, pp. 91\u201394. IEEE (2006)","DOI":"10.1109\/ICPR.2006.490"}],"container-title":["Lecture Notes in Computer Science","Statistical Language and Speech Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-45925-7_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T20:17:11Z","timestamp":1749586631000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-45925-7_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319459240","9783319459257"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-45925-7_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]}}}