{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T02:29:54Z","timestamp":1760149794115,"version":"build-2065373602"},"reference-count":51,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Speech & Language"],"published-print":{"date-parts":[[2018,1]]},"DOI":"10.1016\/j.csl.2017.08.004","type":"journal-article","created":{"date-parts":[[2017,9,1]],"date-time":"2017-09-01T16:36:06Z","timestamp":1504283766000},"page":"333-350","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":7,"special_numbering":"C","title":["Sparse coding based features for speech units classification"],"prefix":"10.1016","volume":"47","author":[{"given":"Pulkit","family":"Sharma","sequence":"first","affiliation":[]},{"given":"Vinayak","family":"Abrol","sequence":"additional","affiliation":[]},{"given":"A.D.","family":"Dileep","sequence":"additional","affiliation":[]},{"given":"Anil Kumar","family":"Sao","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.csl.2017.08.004_bib0001","series-title":"Proceedings of the INTERSPEECH","first-page":"3274","article-title":"Speech enhancement using compressed sensing","author":"Abrol","year":"2013"},{"key":"10.1016\/j.csl.2017.08.004_bib0002","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1016\/j.patrec.2016.04.014","article-title":"Greedy dictionary learning for kernel sparse representation based classifier","volume":"78","author":"Abrol","year":"2016","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.csl.2017.08.004_bib0003","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1016\/j.specom.2016.09.004","article-title":"Greedy double sparse dictionary learning for sparse representation of speech signals","volume":"85","author":"Abrol","year":"2016","journal-title":"Speech Commun."},{"issue":"11","key":"10.1016\/j.csl.2017.08.004_bib0004","doi-asserted-by":"crossref","first-page":"4311","DOI":"10.1109\/TSP.2006.881199","article-title":"K-SVD: an algorithm for designing overcomplete dictionaries for sparse representation","volume":"54","author":"Aharon","year":"2006","journal-title":"IEEE Trans. Signal Process."},{"issue":"4","key":"10.1016\/j.csl.2017.08.004_bib0005","doi-asserted-by":"crossref","first-page":"803","DOI":"10.1137\/S1052623497323194","article-title":"Linear programming in O([n\n3\/ln\u2009n]L) operations","volume":"9","author":"Anstreicher","year":"1999","journal-title":"SIAM J. Optim."},{"issue":"11","key":"10.1016\/j.csl.2017.08.004_bib0006","doi-asserted-by":"crossref","first-page":"1788","DOI":"10.1109\/TASLP.2015.2450491","article-title":"Coupled dictionaries for exemplar-based speech enhancement and automatic speech recognition","volume":"23","author":"Baby","year":"2015","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"issue":"3","key":"10.1016\/j.csl.2017.08.004_bib0007","doi-asserted-by":"crossref","first-page":"864","DOI":"10.1109\/TMM.2014.2301977","article-title":"Robust multi-speaker tracking via dictionary learning and identity modeling","volume":"16","author":"Barnard","year":"2014","journal-title":"IEEE Trans. Multimedia"},{"issue":"7","key":"10.1016\/j.csl.2017.08.004_bib0008","doi-asserted-by":"crossref","first-page":"4680","DOI":"10.1109\/TIT.2011.2146090","article-title":"Orthogonal matching pursuit for sparse signal recovery with noise","volume":"57","author":"Cai","year":"2011","journal-title":"IEEE Trans. Inf. Theory"},{"issue":"12","key":"10.1016\/j.csl.2017.08.004_bib0009","doi-asserted-by":"crossref","first-page":"6340","DOI":"10.1109\/TSP.2012.2215026","article-title":"Simultaneous codeword optimization (SimCO) for dictionary update and learning","volume":"60","author":"Dai","year":"2012","journal-title":"IEEE Trans. Signal Process."},{"issue":"4","key":"10.1016\/j.csl.2017.08.004_bib0010","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","article-title":"Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences","volume":"28","author":"Davis","year":"1980","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"issue":"12","key":"10.1016\/j.csl.2017.08.004_bib0011","doi-asserted-by":"crossref","first-page":"2570","DOI":"10.1109\/TASL.2013.2279338","article-title":"HMM based intermediate matching Kernel for classification of sequential patterns of speech using support vector machines","volume":"21","author":"Dileep","year":"2013","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"7","key":"10.1016\/j.csl.2017.08.004_bib0012","doi-asserted-by":"crossref","first-page":"1838","DOI":"10.1109\/TIP.2011.2108306","article-title":"Image Deblurring and super-resolution by adaptive sparse domain selection and adaptive regularization","volume":"20","author":"Dong","year":"2011","journal-title":"IEEE Trans. Image Process."},{"issue":"3","key":"10.1016\/j.csl.2017.08.004_bib0013","doi-asserted-by":"crossref","first-page":"906","DOI":"10.1137\/0149053","article-title":"Uncertainty principles and signal recovery","volume":"49","author":"Donoho","year":"1989","journal-title":"SIAM J. Appl. Math."},{"issue":"11","key":"10.1016\/j.csl.2017.08.004_bib0014","doi-asserted-by":"crossref","first-page":"4789","DOI":"10.1109\/TIT.2008.929958","article-title":"Fast solution of l1-norm minimization problems when the solution may be sparse","volume":"54","author":"Donoho","year":"2008","journal-title":"IEEE Trans. Inf. Theory"},{"year":"2001","author":"Duda","series-title":"Pattern Classification","key":"10.1016\/j.csl.2017.08.004_bib0015"},{"year":"2010","author":"Elad","series-title":"Sparse and Redundant Representations - From Theory to Applications in Signal and Image Processing","key":"10.1016\/j.csl.2017.08.004_bib0016"},{"doi-asserted-by":"crossref","unstructured":"Garofolo, J. S., Lamel, L. F., Fisher, W. M., Fiscus, J. G., Pallett, D. S., Dahlgren, N. L., 1993. DARPA TIMIT Acoustic Phonetic Continuous Speech Corpus (Tech. Rep. NISTIR 4930, NIST).","key":"10.1016\/j.csl.2017.08.004_bib0017","DOI":"10.6028\/NIST.IR.4930"},{"issue":"7","key":"10.1016\/j.csl.2017.08.004_bib0018","doi-asserted-by":"crossref","first-page":"2067","DOI":"10.1109\/TASL.2011.2112350","article-title":"Exemplar-based sparse representations for noise robust automatic speech recognition","volume":"19","author":"Gemmeke","year":"2011","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"1","key":"10.1016\/j.csl.2017.08.004_bib0019","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1109\/LSP.2009.2034560","article-title":"Retrieving sparse patterns using a compressed sensing framework: applications to speech coding based on sparse linear prediction","volume":"17","author":"Giacobello","year":"2010","journal-title":"IEEE Signal Process. Lett."},{"key":"10.1016\/j.csl.2017.08.004_bib0020","series-title":"Proceedings of the IEEE Conference on Acoustics, Speech and Signal Processing","first-page":"4785","article-title":"Sparse representation over learned and discriminatively learned dictionaries for speaker verification","author":"Haris","year":"2012"},{"issue":"4","key":"10.1016\/j.csl.2017.08.004_bib0021","doi-asserted-by":"crossref","first-page":"1738","DOI":"10.1121\/1.399423","article-title":"Perceptual linear prediction (PLP) analysis for speech","volume":"87","author":"Hermansky","year":"1990","journal-title":"J. Acoust. Soc. Am."},{"key":"10.1016\/j.csl.2017.08.004_bib0022","series-title":"Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing","first-page":"1635","article-title":"Tandem connectionist feature extraction for conventional HMM systems","volume":"Vol.\u00a03","author":"Hermansky","year":"2000"},{"unstructured":"ISOLET Corpus, Release 1.1, Oregon Graduate Institute, Center for Spoken Language Understanding. 2000.","key":"10.1016\/j.csl.2017.08.004_bib0023"},{"issue":"5","key":"10.1016\/j.csl.2017.08.004_bib0024","doi-asserted-by":"crossref","first-page":"1025","DOI":"10.1109\/JSTSP.2011.2157892","article-title":"Fast dictionary learning for sparse representations of speech signals","volume":"5","author":"Jafari","year":"2011","journal-title":"IEEE J. Sel. Topics Signal Process."},{"key":"10.1016\/j.csl.2017.08.004_bib0025","series-title":"Proceedings of the INTERSPEECH","first-page":"78","article-title":"Fixed-size Kernel logistic regression for phoneme classification","author":"Karsmakers","year":"2007"},{"issue":"11","key":"10.1016\/j.csl.2017.08.004_bib0026","doi-asserted-by":"crossref","first-page":"1641","DOI":"10.1109\/29.46546","article-title":"Speaker-independent phone recognition using hidden Markov models","volume":"37","author":"Lee","year":"1989","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"issue":"6","key":"10.1016\/j.csl.2017.08.004_bib0027","doi-asserted-by":"crossref","first-page":"757","DOI":"10.1016\/j.specom.2013.03.003","article-title":"Compressive speech enhancement","volume":"55","author":"Low","year":"2013","journal-title":"Speech Commun."},{"key":"10.1016\/j.csl.2017.08.004_bib0028","first-page":"2579","article-title":"Visualizing high-dimensional data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.csl.2017.08.004_bib0029","series-title":"Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"3445","article-title":"A low complexity orthogonal matching pursuit for sparse signal approximation with shift-invariant dictionaries","author":"Mailhe","year":"2009"},{"issue":"7","key":"10.1016\/j.csl.2017.08.004_bib0030","doi-asserted-by":"crossref","first-page":"1913","DOI":"10.1109\/TASL.2010.2103058","article-title":"Articulatory information for noise robust speech recognition","volume":"19","author":"Mitra","year":"2011","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"1","key":"10.1016\/j.csl.2017.08.004_bib0031","doi-asserted-by":"crossref","first-page":"146","DOI":"10.3758\/BF03211378","article-title":"The perception of face gender: the role of stimulus structure in recognition and classification","volume":"26","author":"O\u2019Toole","year":"1997","journal-title":"Mem. Cognit."},{"issue":"2","key":"10.1016\/j.csl.2017.08.004_bib0032","doi-asserted-by":"crossref","first-page":"208","DOI":"10.3758\/BF03208892","article-title":"Structural aspects of face recognition and the other race effect","volume":"22","author":"O\u2019Toole","year":"1994","journal-title":"Mem. Cognition"},{"key":"10.1016\/j.csl.2017.08.004_bib0033","series-title":"Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing.","first-page":"961","article-title":"fMPE: discriminatively trained features for speech recognition","volume":"Vol.\u00a01","author":"Povey","year":"2005"},{"year":"2010","author":"Rabiner","series-title":"Theory and Applications of Digital Speech Processing","key":"10.1016\/j.csl.2017.08.004_bib0034"},{"key":"10.1016\/j.csl.2017.08.004_sbref0033","series-title":"Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition","article-title":"Word image matching using dynamic time warping","volume":"Vol.\u00a02","author":"Rath","year":"2003"},{"unstructured":"Rubinstein, R., Zibulevsky, M., Elad, M., 2008. Efficient implementation of the K-SVD algorithm using batch orthogonal matching pursuit, CS Technion.","key":"10.1016\/j.csl.2017.08.004_bib0036"},{"issue":"9","key":"10.1016\/j.csl.2017.08.004_bib0037","doi-asserted-by":"crossref","first-page":"1700","DOI":"10.1109\/TPAMI.2008.303","article-title":"Multistream articulatory feature-based models for visual speech recognition","volume":"31","author":"Saenko","year":"2009","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.csl.2017.08.004_bib0038","series-title":"Proceedings of the IEEE International Conference on Acoustics Speech and Signal Processing","first-page":"4370","article-title":"Bayesian compressive sensing for phonetic classification","author":"Sainath","year":"2010"},{"key":"10.1016\/j.csl.2017.08.004_bib0039","series-title":"Proceedings of the INTERSPEECH","first-page":"2254","article-title":"Sparse representation features for speech recognition","author":"Sainath","year":"2010"},{"issue":"8","key":"10.1016\/j.csl.2017.08.004_bib0040","doi-asserted-by":"crossref","first-page":"2598","DOI":"10.1109\/TASL.2011.2155060","article-title":"Exemplar-based sparse representation features: from TIMIT to LVCSR","volume":"19","author":"Sainath","year":"2011","journal-title":"IEEE Trans. Audio Speech Lang Process."},{"issue":"8","key":"10.1016\/j.csl.2017.08.004_bib0041","doi-asserted-by":"crossref","first-page":"2328","DOI":"10.1109\/TIP.2015.2414879","article-title":"Approximation and compression with sparse orthonormal transforms","volume":"24","author":"Sezer","year":"2015","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.csl.2017.08.004_bib0042","series-title":"Proceedings of the INTERSPEECH","first-page":"712","article-title":"Sparse coding based features for speech units classification","author":"Sharma","year":"2015"},{"key":"10.1016\/j.csl.2017.08.004_bib0043","series-title":"Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing","article-title":"Sparse overcomplete decomposition for single channel speaker separation","volume":"Vol.\u00a02","author":"Shashanka","year":"2007"},{"key":"10.1016\/j.csl.2017.08.004_bib0044","series-title":"Proceedings of the International Conference of the Biometrics Special Interest Group (BIOSIG)","first-page":"1","article-title":"Significance of dictionary for sparse coding based face recognition","author":"Shejin","year":"2012"},{"key":"10.1016\/j.csl.2017.08.004_bib0045","series-title":"Proceedings of the IEEE Conference on Acoustics Speech and Signal Processing","first-page":"4346","article-title":"Sparse coding for speech recognition","author":"Sivaram","year":"2010"},{"issue":"2","key":"10.1016\/j.csl.2017.08.004_bib0046","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1109\/MSP.2010.939537","article-title":"Dictionary learning","volume":"28","author":"Tosic","year":"2011","journal-title":"IEEE Signal Process. Mag."},{"issue":"12","key":"10.1016\/j.csl.2017.08.004_bib0047","doi-asserted-by":"crossref","first-page":"4655","DOI":"10.1109\/TIT.2007.909108","article-title":"Signal recovery from random measurements via orthogonal matching pursuit","volume":"53","author":"Tropp","year":"2007","journal-title":"IEEE Trans. Inf. Theory"},{"issue":"3","key":"10.1016\/j.csl.2017.08.004_bib0048","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1016\/0167-6393(93)90095-3","article-title":"Assessment for automatic speech recognition: II. NOISEX-92: a database and an experiment to study the effect of additive noise on speech recognition systems","volume":"12","author":"Varga","year":"1993","journal-title":"Speech Commun."},{"issue":"3","key":"10.1016\/j.csl.2017.08.004_bib0049","doi-asserted-by":"crossref","first-page":"432","DOI":"10.1016\/j.specom.2012.12.003","article-title":"Sparse coding with adaptive dictionary learning for underdetermined blind speech separation","volume":"55","author":"Xu","year":"2013","journal-title":"Speech Commun."},{"issue":"8","key":"10.1016\/j.csl.2017.08.004_bib0050","doi-asserted-by":"crossref","first-page":"1306","DOI":"10.1109\/TASLP.2014.2329188","article-title":"Noise robust exemplar matching using sparse representations of speech","volume":"22","author":"Yilmaz","year":"2014","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"3","key":"10.1016\/j.csl.2017.08.004_bib0051","doi-asserted-by":"crossref","first-page":"960","DOI":"10.1016\/j.dsp.2013.01.004","article-title":"Dictionary learning based sparse coefficients for audio classification with max and average pooling","volume":"23","author":"Zubair","year":"2013","journal-title":"Digit. Signal Process."}],"container-title":["Computer Speech & Language"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0885230816301565?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0885230816301565?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T20:41:57Z","timestamp":1760128917000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0885230816301565"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,1]]},"references-count":51,"alternative-id":["S0885230816301565"],"URL":"https:\/\/doi.org\/10.1016\/j.csl.2017.08.004","relation":{},"ISSN":["0885-2308"],"issn-type":[{"type":"print","value":"0885-2308"}],"subject":[],"published":{"date-parts":[[2018,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Sparse coding based features for speech units classification","name":"articletitle","label":"Article Title"},{"value":"Computer Speech & Language","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.csl.2017.08.004","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2017 Elsevier Ltd. All rights reserved.","name":"copyright","label":"Copyright"}]}}