We present a new automatic learning system for cognate identification. We design a linguistic-inspired substitution matrix to align sensibly our training dataset. We introduce a PAM-like technique, similar to the one successfully used in biological sequence analysis, in order to learn substitution parameters. We propose a novel family of parameterised string similarity measures and we apply them together with the PAM-like matrices to the task of cognate identification. We train and test our proposal on standard datasets of Indo-European languages in orthographic format based on the Latin alphabet, but it could easily be adapted to datasets using any other alphabet, including the phonetic alphabet if data was available. We compare our system with other models reported in the literature and the results show that our method outperforms both orthographic and phonetic approaches formerly presented, increasing the accuracy by approximately 5%