{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T13:59:08Z","timestamp":1762351148392},"reference-count":54,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2010,6,3]],"date-time":"2010-06-03T00:00:00Z","timestamp":1275523200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2010,9]]},"DOI":"10.1007\/s10772-010-9075-z","type":"journal-article","created":{"date-parts":[[2010,6,2]],"date-time":"2010-06-02T15:04:20Z","timestamp":1275491060000},"page":"141-161","source":"Crossref","is-referenced-by-count":24,"title":["Speaker recognition under stressed condition"],"prefix":"10.1007","volume":"13","author":[{"given":"G.","family":"Senthil\u00a0Raja","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S.","family":"Dandapat","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2010,6,3]]},"reference":[{"issue":"4","key":"9075_CR1","doi-asserted-by":"crossref","first-page":"460","DOI":"10.1109\/PROC.1976.10155","volume":"64","author":"B. S. Atal","year":"1976","unstructured":"Atal, B. S. (1976). Automatic recognition of speakers from their voices. Proceedings of the IEEE, 64(4), 460\u2013476.","journal-title":"Proceedings of the IEEE"},{"key":"9075_CR2","first-page":"1","volume":"83","author":"S. Behera","year":"2002","unstructured":"Behera, S., & Dandapat, S. (2002). Speech features for speaker identification. Journal of Institution of Engineers (Electronics and Telecommunications section) India, 83, 1\u20136.","journal-title":"Journal of Institution of Engineers (Electronics and Telecommunications section) India"},{"key":"9075_CR3","first-page":"430","volume":"4","author":"F. Bimbot","year":"2004","unstructured":"Bimbot, F., Bonastre, J., Fredouille, C., Gravier, G., Magrin-Chagnolleau, I., Meignier, S., Merlin, T., Ortega-Garcia, J., Petrovska-Delacretaz, D., & Reynolds, D. (2004). A tutorial on text-independent speaker verification. EURASIP Journal of Applied Signal Processing, 4, 430\u2013451.","journal-title":"EURASIP Journal of Applied Signal Processing"},{"key":"9075_CR4","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1109\/89.668815","volume":"6","author":"S. E. Bou-Ghazale","year":"1998","unstructured":"Bou-Ghazale, S. E., & Hansen, J. H. L. (1998). Stress perturbation of neutral speech for synthesis based on hidden Markov models. IEEE Transactions on Speech and Audio Processing, 6, 201\u2013216.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"issue":"6","key":"9075_CR5","doi-asserted-by":"crossref","first-page":"3392","DOI":"10.1121\/1.410601","volume":"96","author":"D. A. Cairns","year":"1994","unstructured":"Cairns, D. A., & Hansen, J. H. L. (1994). Nonlinear analysis and classification of speech under stressed conditions. The Journal of the Acoustical Society of America, 96(6), 3392\u20133400.","journal-title":"The Journal of the Acoustical Society of America"},{"issue":"9","key":"9075_CR6","doi-asserted-by":"crossref","first-page":"1437","DOI":"10.1109\/5.628714","volume":"85","author":"J. Campbell","year":"1997","unstructured":"Campbell, J. (1997). Speaker recognition: A tutorial. Proceedings of the IEEE, 85(9), 1437\u20131462.","journal-title":"Proceedings of the IEEE"},{"issue":"6","key":"9075_CR7","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1109\/TSA.2002.800557","volume":"10","author":"I. M. Chagnolleau","year":"2002","unstructured":"Chagnolleau, I. M., & Durou, G. (2002). Application of time-frequency principal component analysis to text-independent speaker identification. IEEE Transactions on Speech and Audio Processing, 10(6), 371\u2013378.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"9075_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Y. (1987). Cepstral domain stress compensation for robust speech recognition. In IEEE international conference on acoustics, speech, and signal processing, ICASSP\u201987 (Vol.\u00a012, pp.\u00a0717\u2013720).","DOI":"10.1109\/ICASSP.1987.1169559"},{"issue":"7","key":"9075_CR9","doi-asserted-by":"crossref","first-page":"663","DOI":"10.1109\/10.301733","volume":"41","author":"D. G. Childers","year":"1994","unstructured":"Childers, D. G., & Wong, C. F. (1994). Measuring and modeling vocal source-tract interaction. IEEE Transactions on Biomedical Engineering, 41(7), 663\u2013671.","journal-title":"IEEE Transactions on Biomedical Engineering"},{"issue":"2\u20133","key":"9075_CR10","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1016\/S0167-6393(99)00080-1","volume":"31","author":"G. R. Doddington","year":"2000","unstructured":"Doddington, G. R., Martin, A., Przybockin, M. A., & Reynolds, D. (2000). The NIST speaker recognition evaluation\u2014overview, methodology, systems, results, perspective. Speech Communication, 31(2\u20133), 225\u2013254.","journal-title":"Speech Communication"},{"key":"9075_CR11","doi-asserted-by":"crossref","unstructured":"Etemoglu, C. O., Cuperman, V., & Gersho, A. (2000). Speech coding with an analysis-by-synthesis sinusoidal model. In ICASSP (Vol.3, pp.\u00a01371\u20131374).","DOI":"10.1109\/ICASSP.2000.861834"},{"issue":"4","key":"9075_CR12","doi-asserted-by":"crossref","first-page":"917","DOI":"10.1109\/78.376844","volume":"43","author":"B. Friedlander","year":"1995","unstructured":"Friedlander, B., & Francos, J. (1995). Estimation of amplitude and phase parameters of multicomponent signals. IEEE Transactions on Signal Processing, 43(4), 917\u2013926.","journal-title":"IEEE Transactions on Signal Processing"},{"issue":"3","key":"9075_CR13","doi-asserted-by":"crossref","first-page":"342","DOI":"10.1109\/TASSP.1981.1163605","volume":"29","author":"S. Furui","year":"1981","unstructured":"Furui, S. (1981). Comparison of speaker recognition methods using statistical features and dynamic features. IEEE Transactions on Acoustics, Speech, and Signal Processing, 29(3), 342\u2013350.","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"issue":"5","key":"9075_CR14","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1109\/89.622558","volume":"5","author":"E. George","year":"1997","unstructured":"George, E., & Smith, M. (1997). Speech analysis\/synthesis and modification using an analysis-by-synthesis\/overlap-add sinusoidal model. IEEE Transactions on Speech and Audio Processing, 5(5), 389\u2013406.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"issue":"4","key":"9075_CR15","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1109\/89.848224","volume":"8","author":"S. Ghazale","year":"2000","unstructured":"Ghazale, S., & Hansen, J. H. L. (2000). A comparative study of traditional and newly proposed features for recognition of speech under stress. IEEE Transactions on Speech and Audio Processing, 8(4), 429\u2013442.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"9075_CR16","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1016\/S0167-6393(96)00050-7","volume":"20","author":"J. H. L. Hansen","year":"1996","unstructured":"Hansen, J. H. L. (1996). Analysis and compensation of speech under stress and noise for environmental robustness in speech recognition. Speech Communication, 20, 151\u2013173.","journal-title":"Speech Communication"},{"issue":"4","key":"9075_CR17","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1016\/0167-6393(95)00007-B","volume":"16","author":"J. H. L. Hansen","year":"1995","unstructured":"Hansen, J. H. L., & Cairns, D. A. (1995). ICARUS: Source generator based real-time recognition of speech in noisy stressful and Lombard effect environments. Speech Communication, 16(4), 391\u2013422.","journal-title":"Speech Communication"},{"key":"9075_CR18","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1109\/89.506935","volume":"4","author":"J. H. L. Hansen","year":"1996","unstructured":"Hansen, J. H. L., & Womack, B. D. (1996). Feature analysis and neural network-based classification of speech under stress. IEEE Transactions on Speech and Audio Processing, 4, 307\u2013313.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"9075_CR19","doi-asserted-by":"crossref","unstructured":"Hansen, J. H. L., Womack, B., & Arsian, L. M. (1994). A source generator based production model for environmental robustness in speech recognition. In International conference on spoken language processing (ICSLP) (pp.\u00a0 1003\u20131006).","DOI":"10.21437\/ICSLP.1994-265"},{"key":"9075_CR20","volume-title":"Statistical digital signal processing and modeling","author":"M. H. Hayes","year":"1996","unstructured":"Hayes, M. H. (1996). Statistical digital signal processing and modeling. New York: Wiley."},{"key":"9075_CR21","doi-asserted-by":"crossref","unstructured":"Hunt, M. (1983). Further experiments in text-independent speaker recognition over communications channels. In Proc. IEEE intern. conf. ASSP (pp.\u00a0563\u2013566).","DOI":"10.1109\/ICASSP.1983.1172259"},{"issue":"4","key":"9075_CR22","doi-asserted-by":"crossref","first-page":"385","DOI":"10.1016\/S0167-6393(97)00053-8","volume":"22","author":"B. Imperl","year":"1997","unstructured":"Imperl, B., Ka\u010di\u010d, Z., & Horvat, B. (1997). A study of harmonic features for the speaker recognition. Speech Communication, 22(4), 385\u2013402.","journal-title":"Speech Communication"},{"key":"9075_CR23","doi-asserted-by":"crossref","unstructured":"Inal, M., Erkan, K., Yildirum, M., Butun, E., & Ceken, C. (2000). Comparison of linear predictive analysis methods for ANN-based speaker identification. In Proc. IEEE 5th seminar on neural network applications in electrical engineering (pp.\u00a0109\u2013112).","DOI":"10.1109\/NEUREL.2000.902395"},{"issue":"7","key":"9075_CR24","doi-asserted-by":"crossref","first-page":"731","DOI":"10.1109\/89.952491","volume":"9","author":"J. Jensen","year":"2001","unstructured":"Jensen, J., & Hansen, J. H. L. (2001). Speech enhancement using a constrained iterative sinusoidal model. IEEE Transactions on Speech and Audio Processing, 9(7), 731\u2013740.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"issue":"8","key":"9075_CR25","first-page":"883","volume":"9","author":"H. Jiang","year":"2001","unstructured":"Jiang, H., & Deng, L. (2001). A Bayesian approach to the verification problem: Applications to speaker verification. IEEE Transactions on Speech Audio Process, 9(8), 883\u2013884.","journal-title":"IEEE Transactions on Speech Audio Process"},{"issue":"5","key":"9075_CR26","doi-asserted-by":"crossref","first-page":"763","DOI":"10.1109\/29.17571","volume":"37","author":"L. S. Marques","year":"1989","unstructured":"Marques, L. S., & Almeida, L. (1989). Frequency-varying sinusoidal modeling of speech. IEEE Transactions on Acoustics, Speech, and Signal Processing, 37(5), 763\u2013765.","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"key":"9075_CR27","unstructured":"Mathur, S., & Story, B. H. (2003). Vocal tract modeling: implementation of continuous length variations in a half-sample delay Kelly-Lochbaum model. In Proceedings of the 3rd IEEE international symposium on signal processing and information technology, Germany (pp.\u00a0753\u2013756)."},{"issue":"4","key":"9075_CR28","doi-asserted-by":"crossref","first-page":"744","DOI":"10.1109\/TASSP.1986.1164910","volume":"34","author":"R. McAulay","year":"1986","unstructured":"McAulay, R., & Quatieri, T. (1986). Speech analysis\/synthesis based on a sinusoidal representation. IEEE Transactions on Acoustics, Speech, and Signal Processing, 34(4), 744\u2013754.","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"key":"9075_CR29","first-page":"193","volume":"24","author":"H. Misra","year":"2003","unstructured":"Misra, H., Ikbal, S., & Yegnanarayana, B. (2003). Speaker-specific mapping for text-independent speaker recognition. Speech Communication, 24, 193\u2013209.","journal-title":"Speech Communication"},{"issue":"1","key":"9075_CR30","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1109\/LSP.2005.860538","volume":"13","author":"K. S. R. Murty","year":"2006","unstructured":"Murty, K. S. R., & Yegnanarayana, B. (2006). Combining evidence from residual phase and MFCC features for speaker recognition. IEEE Signal Processing Letters, 13(1), 52\u201355.","journal-title":"IEEE Signal Processing Letters"},{"issue":"11","key":"9075_CR31","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1109\/97.728467","volume":"5","author":"B. L. Pellom","year":"1998","unstructured":"Pellom, B. L., & Hansen, J. (1998). An efficient scoring algorithm for gaussian mixture model based speaker identification. IEEE Signal Processing Letters, 5(11), 281\u2013284.","journal-title":"IEEE Signal Processing Letters"},{"issue":"9","key":"9075_CR32","doi-asserted-by":"crossref","first-page":"1215","DOI":"10.1109\/5.237532","volume":"81","author":"J. Picone","year":"1993","unstructured":"Picone, J. (1993). Signal modeling techniques in speech recognition. Proceedings of the IEEE, 81(9), 1215\u20131247.","journal-title":"Proceedings of the IEEE"},{"key":"9075_CR33","volume-title":"Discrete-time speech signal processing","author":"T. Quatieri","year":"2004","unstructured":"Quatieri, T. (2004). Discrete-time speech signal processing. Upper Saddle River: Pearson Education."},{"issue":"1","key":"9075_CR34","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1109\/29.45618","volume":"38","author":"T. Quatieri","year":"1990","unstructured":"Quatieri, T., & Danisewicz, R. (1990). An approach to co-channel talker interference suppression using a sinusoidal model for speech. IEEE Transaction on Acoustics, Speech, and Signal Processing, 38(1), 56\u201369.","journal-title":"IEEE Transaction on Acoustics, Speech, and Signal Processing"},{"key":"9075_CR35","volume-title":"Fundamentals of speech recognition","author":"L. Rabiner","year":"1993","unstructured":"Rabiner, L., & Juang, B. H. (1993). Fundamentals of speech recognition. Englewood Cliffs: Prentice Hall Inc., 07632."},{"key":"9075_CR36","unstructured":"Raja, G. S., & Dandapat, S. (2004a). Sinusoidal model based speaker identification. In Proc. NCC-2004 conference, IIsc, Bangalore (Vol.\u00a01(1), pp.\u00a0523\u2013527)."},{"key":"9075_CR37","doi-asserted-by":"crossref","unstructured":"Raja, G. S., & Dandapat, S. (2004b). Sinusoidal model based speaker identification using VQ and DHMM. In Proc. IEEE, INDICON-2004 conference, IIT, Kharagpur (pp.\u00a0338\u2013343).","DOI":"10.1109\/INDICO.2004.1497767"},{"key":"9075_CR38","unstructured":"Raja, G. S., & Dandapat, S. (2008). Performance of selective speech features for speaker identification. IE(I) Journal-CP (pp.\u00a038\u201346)."},{"issue":"3","key":"9075_CR39","doi-asserted-by":"crossref","first-page":"737","DOI":"10.1109\/TSA.2005.858071","volume":"14","author":"S. Ramamohan","year":"2006","unstructured":"Ramamohan, S., & Dandapat, S. (2006). Sinusoidal model-based analysis and classification of stressed speech. IEEE Transactions on Audio Speech and Language Processing, 14(3), 737\u2013746.","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"issue":"3","key":"9075_CR40","doi-asserted-by":"crossref","first-page":"972","DOI":"10.1109\/TSA.2005.858051","volume":"14","author":"K. Rao","year":"2006","unstructured":"Rao, K., & Yegnanarayana, B. (2006). Prosody modification using instants of significant excitation. IEEE Transactions on Audio Speech and Language Processing, 14(3), 972\u2013980.","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"issue":"1\u20132","key":"9075_CR41","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/0167-6393(95)00009-D","volume":"17","author":"D. Reynolds","year":"1995","unstructured":"Reynolds, D. (1995). Speaker identification and verification using gaussian mixture speaker models. Speech Communication, 17(1\u20132), 91\u2013108.","journal-title":"Speech Communication"},{"key":"9075_CR42","doi-asserted-by":"crossref","unstructured":"Reynolds, D. (1997). Comparison of background normalization methods for text-independent speaker verification. In European conference on speech processing, Rhodes, Greece (pp.\u00a0963,\u00a0966).","DOI":"10.21437\/Eurospeech.1997-337"},{"key":"9075_CR43","doi-asserted-by":"crossref","unstructured":"Roe, D. (1987). Speech recognition with a noise-adapting codebook. In IEEE international conference on acoustics, speech, and signal processing, ICASSP\u201987 (Vol.\u00a012, pp.\u00a01139\u20131142).","DOI":"10.1109\/ICASSP.1987.1169793"},{"issue":"4","key":"9075_CR44","doi-asserted-by":"crossref","first-page":"475","DOI":"10.1109\/PROC.1976.10156","volume":"64","author":"A. E. Rosenberg","year":"1976","unstructured":"Rosenberg, A. E. (1976). Automatic speaker verification: A review. IEEE Proceedings of the IEEE, 64(4), 475\u2013487.","journal-title":"IEEE Proceedings of the IEEE"},{"issue":"3\u20134","key":"9075_CR45","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1016\/0885-2308(87)90005-2","volume":"2","author":"A. E. Rosenberg","year":"1987","unstructured":"Rosenberg, A. E., & Soong, F. K. (1987). Evaluation of a vector quantization talker recognition system in text independent and text dependent modes. Computer Speech and Language, 2(3\u20134), 143\u2013157.","journal-title":"Computer Speech and Language"},{"issue":"7","key":"9075_CR46","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1109\/97.847363","volume":"7","author":"R. Sarikaya","year":"2000","unstructured":"Sarikaya, R., & Hansen, J. H. L. (2000). High resolution speech feature parametrization for monophone-based stressed speech recognition. IEEE Signal Processing Letters, 7(7), 182\u2013185.","journal-title":"IEEE Signal Processing Letters"},{"issue":"8","key":"9075_CR47","doi-asserted-by":"crossref","first-page":"1047","DOI":"10.1016\/j.specom.2006.01.005","volume":"48","author":"I. Shahin","year":"2006","unstructured":"Shahin, I. (2006). Enhancing speaker identification performance under the shouted talking condition using second-order circular hidden Markov models. Speech Communication, 48(8), 1047\u20131055.","journal-title":"Speech Communication"},{"issue":"4","key":"9075_CR48","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/MASSP.1986.1165388","volume":"3","author":"D. O. Shaughnessy","year":"1986","unstructured":"Shaughnessy, D. O. (1986). Speaker recognition. IEEE ASSP Magazine, 3(4), 4\u201317.","journal-title":"IEEE ASSP Magazine"},{"key":"9075_CR49","volume-title":"Speech communication: human and machine","author":"D. O. Shaughnessy","year":"1987","unstructured":"Shaughnessy, D. O. (1987). Speech communication: human and machine. Reading: Addison-Wesley."},{"issue":"5","key":"9075_CR50","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1109\/97.841155","volume":"7","author":"Y. Stylianou","year":"2000","unstructured":"Stylianou, Y. (2000). A simple and fast way of generating a harmonic signal. IEEE Signal Processing Letters, 7(5), 111\u2013113.","journal-title":"IEEE Signal Processing Letters"},{"key":"9075_CR51","doi-asserted-by":"crossref","first-page":"1145","DOI":"10.1109\/TASL.2006.876113","volume":"14","author":"J. Tao","year":"2006","unstructured":"Tao, J., Kang, Y., & Li, A. (2006). Prosody conversion from neutral speech to emotional speech. IEEE Transactions on Audio, Speech and Language Processing, 14, 1145\u20131154.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"key":"9075_CR52","doi-asserted-by":"crossref","unstructured":"Umesh, S., Cohen, L., & Nelson, D. (1999). Fitting the mel scale. In IEEE international conference on acoustics, speech, and signal processing (Vol.\u00a01, pp.\u00a0217\u2013220).","DOI":"10.1109\/ICASSP.1999.758101"},{"issue":"4","key":"9075_CR53","doi-asserted-by":"crossref","first-page":"575","DOI":"10.1109\/TSA.2005.848892","volume":"13","author":"B. Yegnanarayana","year":"2005","unstructured":"Yegnanarayana, B., Zachariah, J., Prasanna, S. R. M., & Gupta, C. (2005). Combining evidence from source, suprasegmental and spectral features for a fixed-text speaker verification system. IEEE Transactions on Speech and Audio Processing, 13(4), 575\u2013582.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"9075_CR54","unstructured":"Zhang, Y., Loke, C., Togneri, R., & Alder, M. (1994). A comparison of PBDHMM and CHMM for isolated word recognition. In Proc. fifth Australian international conference on speech science and technology, Perth, Australia (pp.\u00a0564\u2013569)."}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-010-9075-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-010-9075-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-010-9075-z","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T11:31:24Z","timestamp":1685619084000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-010-9075-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,6,3]]},"references-count":54,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2010,9]]}},"alternative-id":["9075"],"URL":"https:\/\/doi.org\/10.1007\/s10772-010-9075-z","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010,6,3]]}}}