{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T04:16:08Z","timestamp":1746159368244,"version":"3.40.4"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2014,2,18]],"date-time":"2014-02-18T00:00:00Z","timestamp":1392681600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Circuits Syst Signal Process"],"published-print":{"date-parts":[[2014,7]]},"DOI":"10.1007\/s00034-014-9748-y","type":"journal-article","created":{"date-parts":[[2014,2,17]],"date-time":"2014-02-17T15:21:13Z","timestamp":1392650473000},"page":"2267-2291","source":"Crossref","is-referenced-by-count":6,"title":["Sparse Representation with Optimized Learned Dictionary for Robust Voice Activity Detection"],"prefix":"10.1007","volume":"33","author":[{"given":"Datao","family":"You","sequence":"first","affiliation":[]},{"given":"Jiqing","family":"Han","sequence":"additional","affiliation":[]},{"given":"Guibin","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Tieran","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Jie","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2014,2,18]]},"reference":[{"key":"9748_CR1","doi-asserted-by":"crossref","first-page":"4311","DOI":"10.1109\/TSP.2006.881199","volume":"54","author":"M Aharon","year":"2006","unstructured":"M. Aharon, M. Elad, A.M. Bruckstein, The K-SVD: an algorithm for designing of overcomplete dictionaries for sparse representations. IEEE Trans. Signal Process. 54, 4311\u20134322 (2006)","journal-title":"IEEE Trans. Signal Process."},{"issue":"3","key":"9748_CR2","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1109\/97.995824","volume":"9","author":"F Beritelli","year":"2002","unstructured":"F. Beritelli, S. Casale, G. Rugeri, Performance evaluation and comparison of G.729\/AMR\/Fuzzy voice activity detectors. IEEE Signal Process. Lett. 9(3), 85\u201388 (2002)","journal-title":"IEEE Signal Process. Lett."},{"key":"9748_CR3","volume-title":"Nonlinear Programming","author":"D Bertsekas","year":"1999","unstructured":"D. Bertsekas, Nonlinear Programming (Athena Scientific, Belmont, 1999)"},{"key":"9748_CR4","doi-asserted-by":"crossref","unstructured":"C. Breithaupt, T. Gerkmann, and R. Martin, A novel a priori SNR estimation approach based on selective cepstro-temporal smoothing, in IEEE International Conference Acoustics, Speech, and Signal Processing, 2008, pp. 4897\u20134900","DOI":"10.1109\/ICASSP.2008.4518755"},{"issue":"2","key":"9748_CR5","doi-asserted-by":"crossref","first-page":"489","DOI":"10.1109\/TIT.2005.862083","volume":"52","author":"EJ Candes","year":"2006","unstructured":"E.J. Candes, J. Romberg, T. Tao, Robust uncertianty principles: exact signal reconstruction from highly incomplete frequency information. IEEE Trans. Inf. Theory 52(2), 489\u2013509 (2006)","journal-title":"IEEE Trans. Inf. Theory"},{"issue":"7","key":"9748_CR6","doi-asserted-by":"crossref","first-page":"632","DOI":"10.1049\/el:20030392","volume":"39","author":"JH Chang","year":"2003","unstructured":"J.H. Chang, N.S. Kim, Voice activity detection based on complex Laplacianmodel. IEE Electron. Lett. 39(7), 632\u2013634 (2003)","journal-title":"IEE Electron. Lett."},{"key":"9748_CR7","doi-asserted-by":"crossref","first-page":"1327","DOI":"10.1016\/j.patrec.2006.11.023","volume":"28","author":"SH Chen","year":"2007","unstructured":"S.H. Chen, H.T. Wu, Y.K. Chang, Teager energy based feature parameters for speech recognition in car noise. Pattern Recogn. Lett. 28, 1327\u20131332 (2007)","journal-title":"Pattern Recogn. Lett."},{"key":"9748_CR8","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1137\/S1064827596304010","volume":"20","author":"S Chen","year":"1999","unstructured":"S. Chen, D. Donoho, M. Saunders, Atomic decomposition by basis pursuit. SIAM J. Sci. Comput. 20, 33\u201361 (1999)","journal-title":"SIAM J. Sci. Comput."},{"issue":"10","key":"9748_CR9","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1109\/97.957270","volume":"8","author":"YD Cho","year":"2001","unstructured":"Y.D. Cho, A. Kondoz, Analysis and improvement of a statistical model-based voice activity detector. IEEE Signal Process. Lett. 8(10), 276\u2013278 (2001)","journal-title":"IEEE Signal Process. Lett."},{"key":"9748_CR10","doi-asserted-by":"crossref","unstructured":"Y.D. Cho, K.A. Naimi, A. Kondoz, Improved voice activity detection based on a smoothed statistical likelihood ratio, in IEEE International Conference Acoustics, Speech, and Signal Processing, vol. 2, 2001, pp. 7\u201311","DOI":"10.1109\/ICASSP.2001.941020"},{"key":"9748_CR11","doi-asserted-by":"crossref","unstructured":"D.S. Christian, D. Tomas, M.B. Joachim, Speech enhancement with sparse coding learned dictionaries, in IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 20, 2010, pp. 4758\u20134761","DOI":"10.1109\/ICASSP.2010.5495157"},{"key":"9748_CR12","doi-asserted-by":"crossref","unstructured":"A. Craciun, M. Gabrea, Correlation coefficient-based voice activity detector algorithm, in Proc. Can. Conf. Elect. Comput. Eng., vol 3, 2004, pp. 1789\u20131792","DOI":"10.1109\/CCECE.2004.1349763"},{"issue":"2","key":"9748_CR13","doi-asserted-by":"crossref","first-page":"412","DOI":"10.1109\/TSA.2005.855842","volume":"14","author":"A Davis","year":"2006","unstructured":"A. Davis, S. Nordholm, R. Togneri, Statistical voice activity detection using low-variance spectrum estimation and an adaptive threshold. IEEE Trans. Audio Speech Lang. Process. 14(2), 412\u2013424 (2006)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"4","key":"9748_CR14","doi-asserted-by":"crossref","first-page":"1289","DOI":"10.1109\/TIT.2006.871582","volume":"52","author":"D Donoho","year":"2006","unstructured":"D. Donoho, Compressed sensing. IEEE Trans. Inf. Theory 52(4), 1289\u20131306 (2006)","journal-title":"IEEE Trans. Inf. Theory"},{"issue":"2","key":"9748_CR15","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1214\/009053604000000067","volume":"32","author":"B Efron","year":"2004","unstructured":"B. Efron, T. Hastie, I. Johnstone, R. Tibshirani, Least angle regression. Ann. Stat. 32(2), 407\u2013499 (2004)","journal-title":"Ann. Stat."},{"key":"9748_CR16","first-page":"423","volume":"1","author":"D Enqing","year":"2002","unstructured":"D. Enqing, Z. Heming, L. Yongli, Lowbit and variable rate speech coding using local cosine transform. Proc. TENCON 1, 423\u2013426 (2002)","journal-title":"Proc. TENCON"},{"issue":"2","key":"9748_CR17","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1109\/MCAS.2011.941080","volume":"11","author":"A Fazel","year":"2011","unstructured":"A. Fazel, S. Chakrabartty, An overview of statistical pattern recognition techniques for speaker verification. IEEE Circuits Syst. Mag. 11(2), 62\u201381 (2011)","journal-title":"IEEE Circuits Syst. Mag."},{"key":"9748_CR18","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/TASL.2011.2179294","volume":"20","author":"A Fazel","year":"2012","unstructured":"A. Fazel, S. Chakrabartty, Sparse auditory reproducing kernel (SPARK) features for noise-robust speech recognition. IEEE Trans. Audio Speech Lang. Process. 20, 4 (2012)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"9748_CR19","doi-asserted-by":"crossref","unstructured":"D.K. Freeman, C.B. Southcott, I. Boyd, and G. Cosier, A voice activity detector for pan-European digital cellular mobile telephone service, in IEEE International Conference on Acoustics, Speech, and Signal Processing, Glasgow, U.K., vol. 1, 1989, pp. 369\u2013372","DOI":"10.1109\/ICASSP.1989.266442"},{"key":"9748_CR20","doi-asserted-by":"crossref","unstructured":"M. Fujimoto, K. Ishizuka, T. Nakatani, A voice activity detection based on the adaptive integration of multiple speech features and a signal decision scheme, in IEEE International Conference on Acoustics, Speech, and Signal Processing, 2008, pp. 4441\u20134444","DOI":"10.1109\/ICASSP.2008.4518641"},{"key":"9748_CR21","doi-asserted-by":"crossref","unstructured":"R. Fulchiero, A. Spanias, Speech enhancement using the bispectrum, in IEEE International Conference on Acoustics, Speech, and Signal Processing, 1993, pp. 488\u2013491","DOI":"10.1109\/ICASSP.1993.319701"},{"issue":"3","key":"9748_CR22","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TASL.2010.2052803","volume":"19","author":"PK Ghosh","year":"2011","unstructured":"P.K. Ghosh, A. Tsiartas, S. Narayanan, Robust voice activity detection using long-term signal variability. IEEE Trans. Audio Speech Lang. Process. 19(3), 600\u2013613 (2011)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"9748_CR23","doi-asserted-by":"crossref","unstructured":"J.A. Haigh, and J.S. Mason, Robust voice activity detection using cepstral feature, in IEEE TELCON, 1993, pp. 321\u2013324","DOI":"10.1109\/TENCON.1993.327987"},{"key":"9748_CR24","doi-asserted-by":"crossref","first-page":"588","DOI":"10.1016\/j.specom.2006.12.006","volume":"49","author":"Y Hu","year":"2007","unstructured":"Y. Hu, P. Loizou, Subjective comparison and evaluation of speech enhancement algorithms. Speech Commun. 49, 588\u2013601 (2007)","journal-title":"Speech Commun."},{"key":"9748_CR25","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1109\/TSA.2003.814458","volume":"11","author":"Y Hu","year":"2003","unstructured":"Y. Hu, P. Loizou, A generalized subspace approach for enhancing speech corrupted by colored noise. IEEE Trans. Speech Audio Process. 11, 334\u2013341 (2003)","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"9748_CR26","doi-asserted-by":"crossref","unstructured":"K. Itoh, M. Mizushima, Environmental noise reduction based on speech\/non-speech identification for hearing aids, in Proc. Int. Conf. Acoust., Speech. Signal Process., vol. 1, 1997, pp. 419\u2013422","DOI":"10.1109\/ICASSP.1997.599662"},{"key":"9748_CR27","unstructured":"F.G. Jort, H. Antti, V. Tuomas, and S. Yang, Toward a practical implementation of exemplar-based noise robust ASR, in 19th European Signal Processing Conference, 2011, pp. 1490\u20131494"},{"key":"9748_CR28","unstructured":"M. Julien, P. Jean, and S. Guillermo, Online dictionary learning for sparse coding, in Proc. 26th ICML, 2009"},{"key":"9748_CR29","doi-asserted-by":"crossref","unstructured":"B. Kotnik, Z. Kacic, and B. Horvat, A multiconditional robust front-end feature extraction with a noise reduction procedure based on improved spectral subtraction algorithm, in Proc. 7th Eurospeech, Aalborg, Denmark, 2001, pp. 197\u2013200","DOI":"10.21437\/Eurospeech.2001-72"},{"key":"9748_CR30","doi-asserted-by":"crossref","unstructured":"T. Kristjansson, S. Deligne, P. Olsen, Voicing features for robust speech detec-tion, in Proc. Interspeech, 2005, pp. 369\u2013372","DOI":"10.21437\/Interspeech.2005-186"},{"issue":"5","key":"9748_CR31","doi-asserted-by":"crossref","first-page":"956","DOI":"10.1109\/TSA.2005.851952","volume":"13","author":"K Li","year":"2005","unstructured":"K. Li, M.N.S. Swamy, M.O. Ahmad, An improved voice activity detection using higher order statistics. IEEE Trans. Speech Audio Process. 13(5), 956\u2013974 (2005)","journal-title":"IEEE Trans. Speech Audio Process."},{"issue":"5","key":"9748_CR32","doi-asserted-by":"crossref","first-page":"3387","DOI":"10.1121\/1.3097493","volume":"125","author":"J Ma","year":"2009","unstructured":"J. Ma, Y. Hu, P. Loizou, Objective measures for predicting speech intelligibility in noisy conditions based on new band-importance functions. J. Acoust. Soc. Am. 125(5), 3387\u20133405 (2009)","journal-title":"J. Acoust. Soc. Am."},{"key":"9748_CR33","volume-title":"A Wavelet Tour of Signal Processing, the Sparse Way","author":"S Mallat","year":"2009","unstructured":"S. Mallat, A Wavelet Tour of Signal Processing, the Sparse Way (Academic Press, Burlington, 2009)"},{"issue":"3","key":"9748_CR34","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1109\/89.905996","volume":"9","author":"E Nemer","year":"2001","unstructured":"E. Nemer, R. Goubran, S. Mahmoud, Robust voice activity detection using higher-order statistics in the LPC residual domain. IEEE Trans. Speech Audio Process. 9(3), 217\u2013231 (2001)","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"9748_CR35","unstructured":"R. Padmanabhan, P.S.H. Krishnan, and H.A. Murthy, A pattern recognition approach to VAD using modified group delay, in Proc. 14th National Conf. Commun., IIT Bombay, 2008, pp. 432\u2013437"},{"key":"9748_CR36","doi-asserted-by":"crossref","unstructured":"R. Prasad, H. Saruwatari, K. Shikano, Noise estimation using negentropy based voice-activity detector, in Proc. 47th Midwest Symp. Circuits Syst., vol. 2, 2004, pp. 149\u2013152","DOI":"10.1109\/MWSCAS.2004.1354113"},{"issue":"6","key":"9748_CR37","doi-asserted-by":"crossref","first-page":"1119","DOI":"10.1109\/TSA.2005.853212","volume":"13","author":"J Ramirez","year":"2005","unstructured":"J. Ramirez, J.C. Segura, C. Benitez, An effective subband OSF-based vad with noise reduction for robust speech recognition. IEEE Trans. Speech Audio Process. 13(6), 1119\u20131129 (2005)","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"9748_CR38","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1016\/j.specom.2003.10.002","volume":"42","author":"J Ramirez","year":"2004","unstructured":"J. Ramirez, J.C. Segura, C. Benitez, A. Torre, A. Rubio, Efficient voice activity detection algorithms using long-term speech information. Speech Commun. 42, 271\u2013287 (2004)","journal-title":"Speech Commun."},{"key":"9748_CR39","doi-asserted-by":"crossref","unstructured":"J. Ramirez, J.C. Segura, C. Benitez, L. Garcia, and A. Rubio, Statistical voice detection using a multiple observation likelihood ratio test, in IEEE Signal Processing Letters, vol. 12, no. 10, 2005.","DOI":"10.1109\/LSP.2005.855551"},{"key":"9748_CR40","unstructured":"A. Sangwan, M.C. Chiranth, H.S. Jamadagni, R. Sah, R.V. Prasad, and V. Gaurav, VAD techniques for real-time speech transmission on the Internet, in Proc. IEEE Int. Conf. High-Speech Netw. Multimedia Commun., 2002, pp. 365\u2013368"},{"key":"9748_CR41","doi-asserted-by":"crossref","unstructured":"J.W. Shin, H.J. Kwon, S.H. Jin and N.S. Kim, Voice activity detection based on conditional MAP criterion, in IEEE Signal Processing Letters, vol. 15, 2008","DOI":"10.1109\/LSP.2008.917027"},{"key":"9748_CR42","doi-asserted-by":"crossref","first-page":"978","DOI":"10.1038\/nature04485","volume":"439","author":"EC Smith","year":"2006","unstructured":"E.C. Smith, M.S. Lewicki, Efficient auditory coding. Nature 439, 978\u2013982 (2006)","journal-title":"Nature"},{"issue":"1","key":"9748_CR43","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/97.736233","volume":"6","author":"J Sohn","year":"1999","unstructured":"J. Sohn, N.S. Kim, W.A. Sung, A statistical model-based voice activity detection. IEEE Signal Process. Lett. 6(1), 1\u20133 (1999)","journal-title":"IEEE Signal Process. Lett."},{"key":"9748_CR44","doi-asserted-by":"crossref","unstructured":"S.A. Soleimani and S.M. Ahadi, Voice activity detection based on combination of multiple features using linear\/kernel discriminant analyses, in Proc. 3rd Int. Conf. Inf. Commun. Technol.: from theory to applicat., 2008, pp. 1\u20135","DOI":"10.1109\/ICTTA.2008.4530028"},{"key":"9748_CR45","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","volume":"67","author":"R Tibshirani","year":"1996","unstructured":"R. Tibshirani, Regression shrinkage and selection via the Lasso. J. R. Stat. Soc. Series B 67, 267\u2013288 (1996)","journal-title":"J. R. Stat. Soc. Series B"},{"issue":"3","key":"9748_CR46","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1016\/0167-6393(93)90095-3","volume":"12","author":"A Varga","year":"1993","unstructured":"A. Varga, H.J.M. Steenken, Assessment for automatic speech recognition II: NOISEX-92: a database and an experiment to study the effect of additive noise on speech recognition systems. Speech Commun. 12(3), 247\u2013251 (1993)","journal-title":"Speech Commun."},{"key":"9748_CR47","doi-asserted-by":"crossref","unstructured":"R. Vipperla, J.T. Geiger, S. Bozonnet, D. Wang, Nicholas Evans, Bjorn Schuller, Gerhard Rigoll, Speech overlap detection and attribution using convolutive non-negative sparse coding, in IEEE International Conference on Acoustics, Speech, and Signal Processing, 2012, pp. 4181\u20134184","DOI":"10.1109\/ICASSP.2012.6288840"},{"key":"9748_CR48","doi-asserted-by":"crossref","first-page":"487","DOI":"10.1155\/ASP.2005.487","volume":"4","author":"D Vlaj","year":"2005","unstructured":"D. Vlaj, B. Kotnik, B. Horvat, Z. Kacic, A computationally efficient mel-flter bank VAD algorithm for distributed speech recognition systems. EURASIP J. Appl. Signal Process. 4, 487\u2013497 (2005)","journal-title":"EURASIP J. Appl. Signal Process."},{"issue":"1","key":"9748_CR49","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/89.650304","volume":"6","author":"B Yegnanarayana","year":"1998","unstructured":"B. Yegnanarayana, C. Alessandro, V. Darsinos, An iterative algorithm for decompo-sition of speech signals into periodic and aperiodic components. IEEE Trans. Speech Audio Process. 6(1), 1\u201311 (1998)","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"9748_CR50","doi-asserted-by":"crossref","unstructured":"D.T. You, J.Q. Han, G.B. Zheng, and T.R. Zheng, Sparse power spectrum based robust voice activity detector, in IEEE International Conference on Acoustics, Speech, and Signal Processing, 2012, pp. 289\u2013292","DOI":"10.1109\/ICASSP.2012.6287874"}],"container-title":["Circuits, Systems, and Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-014-9748-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00034-014-9748-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-014-9748-y","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T21:35:39Z","timestamp":1746135339000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00034-014-9748-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,2,18]]},"references-count":50,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2014,7]]}},"alternative-id":["9748"],"URL":"https:\/\/doi.org\/10.1007\/s00034-014-9748-y","relation":{},"ISSN":["0278-081X","1531-5878"],"issn-type":[{"type":"print","value":"0278-081X"},{"type":"electronic","value":"1531-5878"}],"subject":[],"published":{"date-parts":[[2014,2,18]]}}}