Aiming for autonomous living for the people after a stroke is the challenge these days especially for swallowing disorders or dysphagia. It is in this context that the e-swallhome project proposes to develop tools, from hospital care until the patient returns home, which are able to monitor in real time the process of swallowing. This paper proposes a non-invasive acoustic based method to differentiate between swallowing sounds and other sounds in normal ambient environment during food intake. Gaussian Mixture Models (GMM) adapted through the Expectation Maximization (EM) algorithm was employed for classification and test combination using the leave-one-out approach according to the small amount of data in our database. Results provide a good recognition rate of 100 %