The Intelligent audio analytics module, allows the detection of abnormal behavior regardless of the field of view, while also allowing the triggering of the system with the occurrence of pre-defined keywords. The solution implements well established methods from the fields of audio coding, machine learning and speech recognition and allows efficient operation on low cost power limited devices (or embedded systems) for the detection of screaming, glass breaking and gunshots within the environment. The flexible parametrization of the system allows the detection module to adopt to the auditory characteristics of the environment of deployment for uncompromised performance. Moreover, the speaker independent speech recognition module allows the detection of pre-specified key words through the decomposition of the audio scene; critical for the seamless triggering of a surveillance system.