Several diversity techniques have been proposed to counteract the effect of fading on the error performance of wireless networks. A recent and promising technique, which achieves spatial diversity without increased hardware demands, is cooperative communication, involving other terminals in the network that relay the information broadcasted by the source terminal to the destination terminal. In literature several cooperative protocols have been studied under the simplifying assumption that all channel state information is available at the destination. In this paper, we use the space-alternating generalized expectation-maximization (SAGE) algorithm to perform codeaided iterative channel estimation from the broadcasted signals in an Amplify-and-Forward protocol, and investigate the resulting error performance.