5th International Conference on Spoken Language Processing

Sydney, Australia
November 30 - December 4, 1998

On Robust Sequential Estimator Based on T-Distribution with Forgetting Factor for Speech Analysis

Joohun Lee (1), Ki Yong Lee (2)

(1) Dong-Ah Broadcasting College, Korea
(2) Soongsil University, Korea

In this paper, to estimate the time-varying speech parameters having non-Gaussian excitation source, we use the robust sequential estimator(RSE) based on t-distribution and introduce the forgetting factor. By using the RSE based on t-distribution with small degree of freedom, we can alleviate efficiently the effects of outliers to obtain the better performance of parameter estimation. Moreover, by the forgetting factor, the proposed algorithm can estimate the accurate parameters under the rapid variation of speech signal.

Full Paper

Bibliographic reference.  Lee, Joohun / Lee, Ki Yong (1998): "On robust sequential estimator based on t-distribution with forgetting factor for speech analysis", In ICSLP-1998, paper 0296.