Although most hospitals in the United States provide medical services in English, a significant percentage of the U.S. population uses languages other than English. Mostly the interpreting department in a hospital finds interpreters for limited English proficiency (LEP) patients. This includes inpatients, outpatients, and emergency patients. The department employs full-time and part-time interpreters to cover the demand of LEP patients. Two main challenges are facing an interpreting department: 1) there are many interpreting agencies in the market, in which part-time interpreters can be chosen from. Selecting a part-time interpreter with the best service quality and lowest hourly rate makes the scheduling process difficult. 2) the arrival of LEP emergency patients must be predicted to make sure that LEP emergency patients are covered and to avoid any service delay. This paper proposes a framework for scheduling full-time and part-time interpreters for medical centers. Firstly, we develop a prediction model to forecast LEP patient demand at the emergency department (ED). Secondly, we develop a mixed integer programming (MIP) model to assign interpreters to inpatient, outpatient and emergency LEP patients. The goal is to minimize the total interpreting cost, maximize the quality of the interpreting service, and maximize the utilization of full-time interpreters. Various experiments are conducted to show the robustness and practicality of the proposed framework. The schedules generated by our model are compared with the schedules generated by the interpreting department of the hospital. The results show that our model produces better schedules with regard to all the three objectives.