REFERENCES
［1］X.D.Huang，Y.Anki，and M.A.Jack.Hidden Markov models For Speech RecogniEion［M］.Edinburgh University Press，1990.
［2］Duda，R.O.and Harc.P.E.Pattem classification and scene analysis［M］.John Wiley ＆ Sons，1973.
［3］L.R.Rabiner and B.H.Juang.Fundamentals of speech recognition.Prentice Hall PTR，1993.
［4］Y Linde，A.Buzo，＆ R M.Gray.An algorithm for vector quantisation［J］.IEEE Trans.Comm.，1980，no.28，pp.84-95.
［5］D.A.Reynolds.A Gaussian Mixture Modeling Approach to Text-Independent Speaker Identificalion［D］.PhD thesis，1993.
［6］L.R.Rabiner，and B.H.Juang.An introduaion to hidden Markov models［J］.IEEE Acoustic，Speech，and Signal Processing Society Mag.，1986 vol.3，no.1，pp.4-16.
［7］A.P.Dempster，N.M.Laird，and D.B.Rubin.Maximum Likelmood from Incomplete Data via the EM algorithm［J］.Journal of the Royal Statistical Society，Ser.B，1977 vol.39，pp.1-38.
［8］C.F.J.Wu.On the convergence properties of the EM algorirhm［J］.Arm.Statist.1983 vol.11.pp.5-103.
［9］J.Dunn.A fuzzy rejative of the ISODATA process and its use in detecting compact well-separated cluster［J］.J.Cybenzetics，vol.3，pp.32-57，1974.
［10］James C.Bezdek.Pattern Recognition with Fuzzy Objecrive Function Algorithms［M］.Plenum Press，New York and London，1987.
［11］D.E.Gustafson，and W.Kessel.Fuzzy clustering with a fuuy covariance matrix［J］.in Proc.IEEE-CDC，v01.2（K.S.Fu，ed.），pp.761-766.
［12］I.Gath and A.B.Geva.Unsupervised optimal fuzzy clustering.IEEE Trans.on Patt.Anal.＆ Mac.Intel.，vol.11，no.7，pp.773-781，1989.
［13］R.Hathaway.Another interpretation of the EM ajgorithm for mixture dislribution［J］.Journal of Statistics ＆ Probability letters，vol.4，pp.53-56.
［14］C.Ambroise，M.Dang and G.Govaert.Clustering of spatial data by the EM algorithm［J］.In A.Soares，J.Gomez-Hernandez and R.Froidevaux，eds，geoENV I-Geostatistics for Enviromnemal Applications，Quantitative Geology and Geostatistics，Kluwer Academic Publisher.vol.9，pp.493-504，1997.
［15］Dat Tran and Michael Wagner.Fuzzy Expecration-Maximisation Algorithms for Speech and Speaker Recognition［C］.The International Conference of the North American Fuzzy Information Processing Society（NAFIPS），USA.1999（to appear）.
［16］Dat Tran and Michael Wagner.Fuzzy Hidden Markov Models For Speech and Speaker Recognition［C］.The International Conference of the North American Fuzzy Information Processing Society（NAFIPS）.USA，1999.（to appear）.
［17］Dat Tran，T.Van Le and Michael Wagner.Fuzzy Gaussian mixture models for speaker recognition［C］.In Proc.Int.Conf.Spoken Language Processing（ICSLP），1998 vol.2，pp.759-762.
［18］Dat Tran and Michael Wagner.Fuzzy Approach to Gaussian Mixture Models and Generalised Gaussian Mixtvre Models.International Computer Science Conventions（ICSC）USA，1999（to appear）.
［19］Dat Tran and Michael Wagner.Fuzzy Gaussian Mixture Models for Speaker Recognition［J］.In a special issue of the Australian Journal of Intelligent Information Processing Systems（AJIIPS）.1999，Australia（to appear）.
［20］R.N.Dave.Characterizatlon and detection of noise in clustering［J］.Pattern Recognition Letters，1991 vol.12，no.1 1，pp.657-664.
［21］Dat Tran and Michael Wagner.Hidden Markov Modelsusing Fuzzy Estimation［C］.EUROSPEECH'99 Conference，Hungary，1999（to appear）.
［22］Dat Tran and Michael Wagner.Speaker recognition using fuzzy Gaussian mixture models in noisy data［C］.The Third International Conference on Knowledge-Based Intelligent Information Engineering Systems（KES'99）-Adelaide，Auslralia，1999（submitted）.
［23］R.N.Dave and R.Krishnaputam.Robust clustering methods：a unified view［J］.IEEE Trans.Fuzzy Systems.1997 vol.5，no.2，May.
［24］T.Matsui and S.Furui.Concatenated Phoneme models for text-variable speaker recognition［J］.Proc.IEEE Int.Conf.Acoust.Speech，Signal Processing，1993 pp.IJ-391-394.
（In Proceedings of the FUZZY-IEEE 1999 Conference，vol.3，PP.1275-1280，1999，with Dat Tran，Michael Wagner）