Recognition and identification of unknown targets is a crucial task in surveillance and security systems. Electronic Support Measures (ESM) are one of the most effective sensors for identification, especially for maritime and air-to-ground applications. In typical surveillance systems multiple ESM sensors are usually deployed along with kinematic sensors like radar. Different ESM sensors may produce different types of reports ready to be sent to the fusion center. The focus of this paper is to develop a new architecture for target recognition and identification when non-homogeneous ESM and possibly kinematic reports are received at the fusion center. A Bayesian version of the new fusion architecture is evaluated using simulations to show the benefit of utilizing different ESM reports such as attribute and signal level ESM data.