In his commentary on our recent evaluation [L. W. Lee and L. E. Humes, J. Acoust. Soc. Am.93, 2879–2885 (1993)] of Plomp’s speech‐reception threshold (SRT) model, Plomp [J. Acoust. Soc. Am.96, 586–587 (1994)] attempts to make three points: (1) that our results were invalid due to the use of a restricted set of spondaic words as stimuli; (2) that our results, as well as those of Smoorenburg [J. Acoust. Soc. Am.91, 421–437 (1992)] which we cited as supporting our results, were entirely consistent with his SRT model; and (3) that the articulation index (AI) model provided a poorer explanation of these data than his model. Each of these points are discussed in this letter.