Voice command system in multi-room smart homes for assisting people in loss of autonomy in their daily activities faces several challenges, one of which being the distant condition which impacts the ASR system performance. This paper presents an approach to improve voice command recognition at the decoding level by using multiple sources and model adaptation. The method has been tested on data recorded with 11 elderly and visually impaired participants in a real smart home. The results show an error rate of 3.2% in off-line condition and of 13.2% in on-line condition.