{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T08:29:14Z","timestamp":1742632154836,"version":"3.30.1"},"reference-count":26,"publisher":"Elsevier BV","issue":"2-3","license":[{"start":{"date-parts":[[2000,6,1]],"date-time":"2000-06-01T00:00:00Z","timestamp":959817600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Speech Communication"],"published-print":{"date-parts":[[2000,6]]},"DOI":"10.1016\/s0167-6393(99)00077-1","type":"journal-article","created":{"date-parts":[[2003,4,5]],"date-time":"2003-04-05T03:57:58Z","timestamp":1049515078000},"page":"181-192","source":"Crossref","is-referenced-by-count":48,"title":["Robustness to telephone handset distortion in speaker recognition by discriminative feature design"],"prefix":"10.1016","volume":"31","author":[{"given":"Larry P.","family":"Heck","sequence":"first","affiliation":[]},{"given":"Yochai","family":"Konig","sequence":"additional","affiliation":[]},{"given":"M.Kemal","family":"S\u00f6nmez","sequence":"additional","affiliation":[]},{"given":"Mitch","family":"Weintraub","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/S0167-6393(99)00077-1_BIB1","unstructured":"Baum, E.B., Wilczek, F., 1988. Supervised learning of probability distributions by neural networks. In: D. Anderson, (Ed.), Neural Information Processing Systems. pp. 52\u201361"},{"key":"10.1016\/S0167-6393(99)00077-1_BIB2","doi-asserted-by":"crossref","unstructured":"Bengio, Y., De Mori, R., Flammia, G., Kompe, R., 1992. Global optmization of a neural network-hidden markov model hybrid. IEEE Trans. Neural Networks 3 (2)","DOI":"10.1109\/72.125866"},{"issue":"3","key":"10.1016\/S0167-6393(99)00077-1_BIB3","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1109\/89.568731","article-title":"HMM-based speech recognition using state-dependent, discriminatively derived transforms on mel-warped DFT features","volume":"5","author":"Chengalvarayan","year":"1997","journal-title":"IEEE Trans. Speech and Audio Process."},{"key":"10.1016\/S0167-6393(99)00077-1_BIB4","doi-asserted-by":"crossref","unstructured":"Euler, S., 1995. Integrated optimization of feature transformation for speech recognition. In: Proceedings European Conf. on Speech Communication and Technology. EUROSPEECH. pp. 109\u2013112","DOI":"10.21437\/Eurospeech.1995-31"},{"key":"10.1016\/S0167-6393(99)00077-1_BIB5","doi-asserted-by":"crossref","first-page":"254","DOI":"10.1109\/TASSP.1981.1163530","article-title":"Cepstral analysis technique for automatic speaker verification","volume":"29","author":"Furui","year":"1981","journal-title":"IEEE Trans. Acoust. Speech Signal Process. ASSP-"},{"key":"10.1016\/S0167-6393(99)00077-1_BIB6","doi-asserted-by":"crossref","unstructured":"Heck, L.P., Weintraub, M., 1997. Handset dependent background models for robust text-independent speaker recognition. In: Proceedings Internat. Conf. on Acoust. Speech and Signal Process","DOI":"10.1109\/ICASSP.1997.596126"},{"key":"10.1016\/S0167-6393(99)00077-1_BIB7","doi-asserted-by":"crossref","unstructured":"Hermansky, H., Morgan, N., Bayya, A., Kohn, P., 1991. Compensation for the effect of the communication channel in auditory-like analysis of speech (RASTA-PLP). In: Proceedings European Conf. on Speech Communication and Technology. EUROSPEECH. pp. 1367\u20131370","DOI":"10.1109\/ACSSC.1991.186557"},{"key":"10.1016\/S0167-6393(99)00077-1_BIB8","unstructured":"Lehr, M., 1996. Scaled stochastic methods for training neural networks, Ph.D. Dissertation, Information Systems Laboratory, Dept. of Electrical Engineering, Stanford University"},{"key":"10.1016\/S0167-6393(99)00077-1_BIB9","unstructured":"Liu, F.-H., Stern, R.M., Acero, A., Moreno, P.J., 1994. Environment normalization for robust speech recognition using direct cepstral comparison. In: Proceedings Internat. Conf. on Acoust. Speech Signal Process., Vol. 2, pp. 19\u201322"},{"key":"10.1016\/S0167-6393(99)00077-1_BIB10","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1109\/79.536825","article-title":"Robust speaker recognition","volume":"13","author":"Mammone","year":"1996","journal-title":"IEEE Signal Process. Magazine"},{"key":"10.1016\/S0167-6393(99)00077-1_BIB11","doi-asserted-by":"crossref","first-page":"554","DOI":"10.1109\/89.784108","article-title":"Robust text-independent speaker identification over telephone channels","volume":"7","author":"Murthy","year":"1999","journal-title":"IEEE Trans. Speech and Audio Process."},{"key":"10.1016\/S0167-6393(99)00077-1_BIB12","doi-asserted-by":"crossref","unstructured":"Neumeyer, L., Weintraub, M., 1994. Probabilistic optimum filtering for robust speech recognition. In: Proceedings Internat. Conf. on Acoust. Speech Signal Process., pp. 417\u2013420","DOI":"10.1109\/ICASSP.1994.389267"},{"key":"10.1016\/S0167-6393(99)00077-1_BIB13","unstructured":"NIST, 1996. Speaker recognition workshop. In: NIST Workshop Notebook, Linthicum Heights, Maryland"},{"key":"10.1016\/S0167-6393(99)00077-1_BIB14","unstructured":"NIST, 1997. Speaker recognition workshop. In: NIST Workshop Notebook, Linthicum Heights, Maryland"},{"key":"10.1016\/S0167-6393(99)00077-1_BIB15","unstructured":"NIST, 1998. Speaker recognition workshop. In: NIST Workshop Notebook, Linthicum Heights, Maryland"},{"key":"10.1016\/S0167-6393(99)00077-1_BIB16","doi-asserted-by":"crossref","unstructured":"Paliwal, K.K., Bacchiani, M., Sagisaka, Y., 1995. Minimum classification error training algorithm for feature extractor and pattern classifier in speech recognition. In: Proceedings European Conf. on Speech Communication and Technology. EUROSPEECH. pp. 541\u2013544","DOI":"10.21437\/Eurospeech.1995-30"},{"key":"10.1016\/S0167-6393(99)00077-1_BIB17","unstructured":"Przybocki M.A., Martin, A.F., 1998. NIST speaker recognition evaluations. In: LREC, Granada, Spain, pp. 331\u2013335"},{"key":"10.1016\/S0167-6393(99)00077-1_BIB18","doi-asserted-by":"crossref","unstructured":"Quatieri, T.F., Reynolds, D.A., O'Leary, G.C., 1998. Magnitude-only estimation of handset nonlinearity with application to speaker recognition. In: Proceedings Internat. Conf. on Acoust. Speech Signal Process., Vol. 2, pp. 745\u2013748","DOI":"10.1109\/ICASSP.1998.675372"},{"key":"10.1016\/S0167-6393(99)00077-1_BIB19","doi-asserted-by":"crossref","unstructured":"Rahim, M., Bengio, Y., Lecun, Y., 1997. Discriminative feature and model design for automatic speech recognition. In: Proceedings European Conf. on Speech Communication and Technology. EUROSPEECH. Rhodes, Greece","DOI":"10.21437\/Eurospeech.1997-46"},{"key":"10.1016\/S0167-6393(99)00077-1_BIB20","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/0167-6393(95)00009-D","article-title":"Speaker identification and verification using Gaussian mixture speaker models","volume":"17","author":"Reynolds","year":"1995","journal-title":"Speech Communication"},{"key":"10.1016\/S0167-6393(99)00077-1_BIB21","doi-asserted-by":"crossref","unstructured":"Reynolds, D.A., 1997a. Htimit and llhdb: Speech corpora for the study of handset transducer effect. In: Proceedings Internat. Conf. on Acoust. Speech Signal Process., Vol. 2, pp. 1535\u20131538","DOI":"10.1109\/ICASSP.1997.596243"},{"key":"10.1016\/S0167-6393(99)00077-1_BIB22","doi-asserted-by":"crossref","unstructured":"Reynolds, D.A., 1997b. Comparison of background normalization methods for text-independent speaker verification. In: Proceedings European Conf. on Speech Communication and Technology. EUROSPEECH","DOI":"10.21437\/Eurospeech.1997-337"},{"issue":"4","key":"10.1016\/S0167-6393(99)00077-1_BIB23","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1162\/neco.1991.3.4.461","article-title":"Neural network classifiers estimate bayesian a posteriori probabilities","volume":"3","author":"Richard","year":"1991","journal-title":"Neural Computation"},{"key":"10.1016\/S0167-6393(99)00077-1_BIB24","doi-asserted-by":"crossref","unstructured":"Rumelhart, D.E., Hinton, G.E., Williams, R.J., 1986. Learning internal representations by error propagation. In: Parallel Distributed Processing. MIT Press, Cambridge, pp. 318\u2013364","DOI":"10.21236\/ADA164453"},{"key":"10.1016\/S0167-6393(99)00077-1_BIB25","doi-asserted-by":"crossref","unstructured":"Stern, R.M., Liu, F.-H., Moreno, P.J., Acero, A., 1994. Signal processing for robust speech recognition. In: Proceedings Internat. Conf. on Spoken Language Process., Vol. 3, pp. 1027\u20131030","DOI":"10.21437\/ICSLP.1994-271"},{"key":"10.1016\/S0167-6393(99)00077-1_BIB26","unstructured":"Weintraub, M., 1985. A theory and computational model of auditory monaural sound separation, Ph.D. Dissertation, Stanford University"}],"container-title":["Speech Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639399000771?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639399000771?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T17:06:26Z","timestamp":1733504786000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167639399000771"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2000,6]]},"references-count":26,"journal-issue":{"issue":"2-3","published-print":{"date-parts":[[2000,6]]}},"alternative-id":["S0167639399000771"],"URL":"https:\/\/doi.org\/10.1016\/s0167-6393(99)00077-1","relation":{},"ISSN":["0167-6393"],"issn-type":[{"type":"print","value":"0167-6393"}],"subject":[],"published":{"date-parts":[[2000,6]]}}}