Abstract-This paper proposes an implementation of calibrated acoustic emission (AE) and vibration techniques to monitor progressive stages of flank wear on carbide tool tips. Three cutting conditions were used on workpiece material, type EN24T, in turning operation. The root-mean-square value of AE (AErms) and the coherence function between the acceleration signals at the tool tip in the tangential and feed directions was studied. Three features were identified to be sensitive to tool wear: AErms, coherence function in the frequency ranges 2.5-5.5 kHz and 18-25 kHz. Belief network based on Bayes' rule was used to integrate information in order to recognise the occurrence of worn tool. The three features obtained from the three cutting conditions and machine time were used to train the network. The set of feature vectors for worn tools was divided into two equal sub-sets: one to train the network and the other to test it. The AErms in term of AE pressure equivalent was used to train and test the net work to validate the calibrated acoustic. The overall success rate of the network in detecting a worn tool was high with low error rate.