In this paper, we consider the generalized semiparametric model (GSPM) y i = h(x T i β) + f (t i) + e i , 1≤ i ≤ n, where h(•) is a known function, e i are dependent errors. We obtain an estimator of the parametric component β for the model by a difference-based M-estimator. In addition, we prove the asymptotic normality of the proposed estimator and investigate the weak convergence rate of the wavelet estimator of f (•). Furthermore, we apply these results to a partially linear model with dependent errors.