This paper reports on experiments performed in the develop- ment of the QALL-ME system, a multilingual QA infrastructure capable of handling input requests both in written and spoken form. Our objec- tive is to estimate the impact of dealing with automatically transcribed (i.e. noisy) requests on a specific question interpretation task, namely extraction of relations from natural language questions. A number of experiments are presented, featuring different combinations of manu-ally and automatically transcribed questions datasets to train and eval-uate the system. Results (ranging from 0.624 to 0.634 F-measure in the recogniton of the relations expressed by a question) demonstrate that the impact of noisy data on question interpretation is negligible with all the combinations of training/test data. This shows that the benefits of enabling speech access capabilities, allowing for a more natural human- machine interaction, outweight the minimal loss in terms of performance.