The DIRHA project addresses the challenge of natural spontaneous speech interaction with distant microphones in a home environment. The main fields on which research will be conducted, and for which suitable solutions will be identified and embedded in real-time prototypes, are: multichannel acoustic processing, distant speech recognition and understanding, speaker identification/verification, and spoken dialogue management. The project also aims to investigate the use of a new type of acquisition device consisting of MEMS (Micro Electrical-Mechanical System) digital microphone arrays.