论文信息 - Speech parameter estimation by time-weighted-error Kalman filtering

Speech parameter estimation by time-weighted-error Kalman filtering

In this paper, we discuss a method of improving the parameter-tracking performance of the Kalman filter for modeling time-varying signals. The Kalman filter is an effective means of recursively estimating the coefficients of an AR (or ARMA) model; however, its effectiveness is diminished by the weight which the filter gives to the history of the signal. With a view toward improved modeling of speech signals, we examine the use of a time-weighted error criterion to remedy this situation.

V. Jain | G. Mack

[1] A.V. Oppenheim,et al. Enhancement and bandwidth compression of noisy speech , 1979, Proceedings of the IEEE.

[2] J. Gibson,et al. Analyses and experiments on the DM into LPC tandem , 1982 .

[3] R. W. Miller,et al. Asymptotic behavior of the Kalman filter with exponential aging , 1971 .

[4] Arthur Gelb,et al. Applied Optimal Estimation , 1974 .

[5] H. W. Sorenson,et al. Comment on "A Practical Nondiverging Filter" , 1971 .

[6] Jerry D. Gibson,et al. Optimal estimation and speech analysis , 1979, ICASSP.

[7] Alan V. Oppenheim,et al. All-pole modeling of degraded speech , 1978 .

[8] T. Anderson. Statistical analysis of time series , 1974 .

[9] T. J. Tarn,et al. A practical nondiverging filter , 1970 .

[10] A. Jazwinski. Stochastic Processes and Filtering Theory , 1970 .

[11] Lawrence R. Rabiner,et al. Speech synthesis by rule: An acoustic domain approach , 1968 .

[12] Jerry D. Gibson,et al. Unified development of algorithms used for linear predictive coding of speech signals , 1976 .

[13] J.D. Gibson,et al. Adaptive prediction in speech differential encoding systems , 1980, Proceedings of the IEEE.