Xhosa (Bantu) has an “unnatural” process of palatalization—contrary to typological expectations, it is triggered by [w], but not [i] or [j], and applies only to labials. For example, [m]→[ɲ] as in uku-lum-a to bite' ~ uku-luɲ-w-a ‘to be bitten', and [mb]→[ⁿdʒ] as in uku-ɬamb-a 'to wash' ~ uku-ɬaⁿdʒ-w-a ‘to be washed'. This paper compares underlying and derived palatals to determine whether the palatal/non-palatal contrast is neutralized (in)completely in the derivational context. 40 Xhosa nonce verbs, ending in segments which undergo palatalization, were created to be read by 6 native speakers. Speakers read these forms and were then asked to produce forms with the passive -w suffix, thus triggering palatalization. F2 was measured at boundaries and ten ms. into the vowels preceding and following the palatalized segment. F2 at ten ms into the following vowel differed on average by 167.99 Hz between underlying and derived palatals, trending towards, but not reaching significance (t = 1.94, p = 0.054), while F2 slope showed no clear trend. While Zsiga (1995) proposes that English palatalization can be complete or gradient, this is the first study of palatalization in the context of incomplete neutralization, and the first study to look at incomplete neutralization in Bantu.Xhosa (Bantu) has an “unnatural” process of palatalization—contrary to typological expectations, it is triggered by [w], but not [i] or [j], and applies only to labials. For example, [m]→[ɲ] as in uku-lum-a to bite' ~ uku-luɲ-w-a ‘to be bitten', and [mb]→[ⁿdʒ] as in uku-ɬamb-a 'to wash' ~ uku-ɬaⁿdʒ-w-a ‘to be washed'. This paper compares underlying and derived palatals to determine whether the palatal/non-palatal contrast is neutralized (in)completely in the derivational context. 40 Xhosa nonce verbs, ending in segments which undergo palatalization, were created to be read by 6 native speakers. Speakers read these forms and were then asked to produce forms with the passive -w suffix, thus triggering palatalization. F2 was measured at boundaries and ten ms. into the vowels preceding and following the palatalized segment. F2 at ten ms into the following vowel differed on average by 167.99 Hz between underlying and derived palatals, trending towards, but not reaching significance (t = 1.94, p = 0.054), whi...