Application of sequential estimation to time-varying environment compensation [in speech recognition]
Nam Soo Kim, Dong Kook Kim, Sang Ryong Kim · 2002
Sequential approaches are proposed to compensate for the effects of a nonstationary environment. Unlike batch approaches, the proposed methods derive a different parameter estimate each time using the sequential expectation maximization (EM) algorithm. Moreover, we also propose a forward-backward estimation scheme as an improvement of the sequential parameter estimation.