{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T22:09:54Z","timestamp":1772489394031,"version":"3.50.1"},"publisher-location":"Berlin, Heidelberg","reference-count":28,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642388460","type":"print"},{"value":"9783642388477","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-38847-7_22","type":"book-chapter","created":{"date-parts":[[2013,6,11]],"date-time":"2013-06-11T02:38:00Z","timestamp":1370918280000},"page":"168-175","source":"Crossref","is-referenced-by-count":4,"title":["Smoothed Nonlinear Energy Operator-Based Amplitude Modulation Features for Robust Speech Recognition"],"prefix":"10.1007","author":[{"given":"Md. Jahangir","family":"Alam","sequence":"first","affiliation":[]},{"given":"Patrick","family":"Kenny","sequence":"additional","affiliation":[]},{"given":"Douglas","family":"O\u2019Shaughnessy","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"issue":"4","key":"22_CR1","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","volume":"28","author":"S. Davis","year":"1980","unstructured":"Davis, S., Mermelstein, P.: Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Trans. Acoustics, Speech, and Signal Processing\u00a028(4), 357\u2013366 (1980)","journal-title":"IEEE Trans. Acoustics, Speech, and Signal Processing"},{"issue":"4","key":"22_CR2","doi-asserted-by":"publisher","first-page":"1738","DOI":"10.1121\/1.399423","volume":"87","author":"H. Hermansky","year":"1990","unstructured":"Hermansky, H.: Perceptual linear prediction analysis of speech, J. Acoust. Soc. Am.\u00a087(4), 1738\u20131752 (1990)","journal-title":"Acoust. Soc. Am."},{"key":"22_CR3","unstructured":"Terasawa, H.: A Hybrid Model for Timbre Perception: Quantitative Representations of Sound Color and Density. Ph.D. Thesis, Stanford University, Stanford, CA (2009)"},{"key":"22_CR4","unstructured":"ETSI ES 202 050, Speech Processing, Transmission and Quality aspects (STQ); Distributed speech recognition; advanced front-end feature extraction algorithm; Compression algorithms (2003)"},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Kim, C., Stern, R.M.: Feature extraction for robust speech recognition based on maximizing the sharpness of the power distribution and on power flooring. In: IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, pp. 4574\u20134577 (March 2010)","DOI":"10.1109\/ICASSP.2010.5495570"},{"key":"22_CR6","doi-asserted-by":"crossref","unstructured":"Alam, M.J., Kenny, P., O\u2019Shaughnessy, D.: Robust Feature Extraction for Speech Recognition by Enhancing Auditory Spectrum. In: Proc. INTERSPEECH, Portland Oregon (September 2012)","DOI":"10.21437\/Interspeech.2012-392"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"van Hout, J., Alwan, A.: A novel approach to soft-mask estimation and log-spectral enhancement for robust speech recognition. In: Proc. of ICASSP, pp. 4105\u20134108 (2012)","DOI":"10.1109\/ICASSP.2012.6288821"},{"key":"22_CR8","doi-asserted-by":"crossref","unstructured":"Vikramjit Mitra, H., Franco, M., Graciarena, A.: Mandal, Normalized Amplitude modulation features for large vocabulary noise-robust speech recognition. In: Proc. of ICASSP, pp. 4117\u20134120 (2012)","DOI":"10.1109\/ICASSP.2012.6288824"},{"issue":"4","key":"22_CR9","doi-asserted-by":"publisher","first-page":"1532","DOI":"10.1109\/78.212729","volume":"41","author":"Maragos","year":"1993","unstructured":"Maragos, Kaiser, J.F., Quatieri, T.F.: On amplitude and frequency demodulation using energy operators. IEEE Trans. Signal Processing\u00a041(4), 1532\u20131550 (1993)","journal-title":"IEEE Trans. Signal Processing"},{"key":"22_CR10","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1016\/S0167-6393(99)00012-6","volume":"28","author":"A. Potamianos","year":"1999","unstructured":"Potamianos, A., Maragos, P.: Speech analysis and synthesis using an AM\u2013FM modulation model. Speech Communication\u00a028, 195\u2013209 (1999)","journal-title":"Speech Communication"},{"issue":"7","key":"22_CR11","doi-asserted-by":"publisher","first-page":"819","DOI":"10.1016\/j.specom.2005.08.007","volume":"48","author":"D. Dimitriadis","year":"2006","unstructured":"Dimitriadis, D., Maragos, P.: Continuous energy demodulation methods and application to speech analysis. Speech Communication\u00a048(7), 819\u2013837 (2006)","journal-title":"Speech Communication"},{"key":"22_CR12","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1109\/89.905995","volume":"9","author":"G. Zhou","year":"2001","unstructured":"Zhou, G., Hansen, J.H.L., Kaiser, J.F.: Nonlinear feature based classification of speech under stress. IEEE Transactions on Speech and Audio Processing\u00a09, 201\u2013216 (2001)","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"22_CR13","unstructured":"Gao, H., Chen, S.G.: Emotion classification of mandarin speech based on TEO nonlinear features. Software Engineering, Artificial Intelligence, Networking and Parallel\/Distributed Computing, 394\u2013398 (2007)"},{"issue":"10","key":"22_CR14","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1109\/97.789604","volume":"6","author":"F. Jabloun","year":"1999","unstructured":"Jabloun, F., Cetin, A.E., Erzin, E.: Teager energy based feature parameters for speech recognition in car noise. IEEE Signal Processing Letters\u00a06(10), 259\u2013261 (1999)","journal-title":"IEEE Signal Processing Letters"},{"issue":"9","key":"22_CR15","doi-asserted-by":"publisher","first-page":"621","DOI":"10.1109\/LSP.2005.853050","volume":"12","author":"D. Dimitriadis","year":"2005","unstructured":"Dimitriadis, D., Maragos, P., Potamianos, A.: Robust AM\u2013FM features for speech recognition. IEEE Signal Processing Letters\u00a012(9), 621\u2013624 (2005)","journal-title":"IEEE Signal Processing Letters"},{"key":"22_CR16","unstructured":"Jankowski Jr., C.R., Quatieri, T.F., Reynolds, D.A.: Measuring fine structure in speech: Application to speaker identification. In: ICASSP 1995, Detroit, USA (May 1995)"},{"issue":"5","key":"22_CR17","doi-asserted-by":"publisher","first-page":"569","DOI":"10.1109\/89.784109","volume":"7","author":"M.D. Plumpe","year":"1999","unstructured":"Plumpe, M.D., Quatieri, T.F., Reynolds, D.A.: Modeling of the glottal flow derivative waveform with application to speaker identification. IEEE Trans. Speech and Audio Processing\u00a07(5), 569\u2013586 (1999)","journal-title":"IEEE Trans. Speech and Audio Processing"},{"issue":"6","key":"22_CR18","doi-asserted-by":"publisher","first-page":"1097","DOI":"10.1109\/TASL.2008.2001109","volume":"16","author":"M. Grimaldi","year":"2008","unstructured":"Grimaldi, M., Cummins, F.: Speaker identification using instantaneous frequencies. IEEE Trans. Audio, Speech and Language Processing\u00a016(6), 1097\u20131111 (2008)","journal-title":"IEEE Trans. Audio, Speech and Language Processing"},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"Tsiakoulis, P., Potamianos, A.: Statistical Analysis of Amplitude Modulation in Speech Signals using an AM-FM Model. In: Proc. Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP 2009), Taipei, Taiwan (April 2009)","DOI":"10.1109\/ICASSP.2009.4960500"},{"issue":"1","key":"22_CR20","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1016\/0165-1684(94)90169-4","volume":"37","author":"A. Potamianos","year":"1994","unstructured":"Potamianos, A., Maragos, P.: A comparison of energy operator and Hilbert transform approach to signal and speech demodulation. Signal Process\u00a037(1), 95\u2013120 (1994)","journal-title":"Signal Process"},{"issue":"2","key":"22_CR21","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1109\/10.661266","volume":"45","author":"S. Mukhopadhyay","year":"1998","unstructured":"Mukhopadhyay, S., Ray, G.C.: A new interpretation of nonlinear energy operator and its efficacy in spike detection. IEEE Tans. on Biomedical Engg.\u00a045(2), 180\u2013187 (1998)","journal-title":"IEEE Tans. on Biomedical Engg."},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Parihar, N., Picone, J., Pearce, D., Hirsch, H.G.: Performance analysis of the Aurora large vocabulary baseline system. In: Proceedings of the European Signal Processing Conference, Vienna, Austria (2004)","DOI":"10.21437\/Eurospeech.2003-139"},{"key":"22_CR23","unstructured":"Kaiser, J.F.: On a Simple Algorithm to Calculate the \u2018Energy\u2019 of a Signal,\u201d. In: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, Albuquerque, NM, pp. 381\u2013384 (April 1990)"},{"key":"22_CR24","doi-asserted-by":"crossref","unstructured":"Li, Q(P.), Huang, Y.: Robust speaker identification using an auditory-based feature. In: Proc. ICASSP, pp. 4514\u20134517 (2010)","DOI":"10.1109\/ICASSP.2010.5495589"},{"key":"22_CR25","unstructured":"Kvedalen, E.: Signal processing using the Teager energy operator and other nonlinear operators, Cand. Scient Thesis, University of Oslo (May 2003)"},{"key":"22_CR26","doi-asserted-by":"crossref","unstructured":"Au Yeung, S.-K., Siu, M.-H.: Improved performance of Aurora-4 using HTK and unsupervised MLLR adaptation. In: Proceedings of the Int. Conference on Spoken Language Processing, Jeju, Korea (2004)","DOI":"10.21437\/Interspeech.2004-108"},{"key":"22_CR27","unstructured":"Young, S.J., et al.: HTK Book, Entropic Cambridge Research Laboratory Ltd., 3.4 edition (2006), http:\/\/htk.eng.cam.ac.uk\/"},{"key":"22_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1007\/978-3-642-25020-0_32","volume-title":"Advances in Nonlinear Speech Processing","author":"M.J. Alam","year":"2011","unstructured":"Alam, M.J., Ouellet, P., Kenny, P., O\u2019Shaughnessy, D.: Comparative Evaluation of Feature Normalization Techniques for Speaker Verification. In: Travieso-Gonz\u00e1lez, C.M., Alonso-Hern\u00e1ndez, J.B. (eds.) NOLISP 2011. LNCS, vol.\u00a07015, pp. 246\u2013253. Springer, Heidelberg (2011)"}],"container-title":["Lecture Notes in Computer Science","Advances in Nonlinear Speech Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-38847-7_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,2]],"date-time":"2023-07-02T09:16:58Z","timestamp":1688289418000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-38847-7_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642388460","9783642388477"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-38847-7_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013]]}}}