The problem of delay-dependent energy-to-peak filter design for a class of stochastic time-delay systems is investigated in this paper. Attention is focused on the design of full-order and reduced-order filters to guarantee a prescribed energy-to-peak performance for the filtering error system. The improvement lies in that the constructed Lyapunov-Krasovskii functional, based on the delay partitioning technique, can guarantee the obtained delay-dependent conditions to be less conservative than the existing results. The obtained results are formulated in the form of linear matrix inequalities (LMIs), which can be readily solved via standard numerical software. Finally, a numerical example is provided to illustrate the effectiveness and merit of the proposed filter design methods.