Software Requirements Specification (SRS) is considered a highly critical artifact in the software development. All phases in software development are influenced by this artifact. Defects in software requirements may higher the risk of project overschedule that contributes to cost overrun of the project. Researchers have shown that finding defects in the initial software development phase is important because the cost of the bug is cheaper if it is fixed early. Hence, our main goal is to provide a platform for requirement engineers to produce better requirement specifications. We propose AmbiDetect, a (prototype) tool to automatically classify ambiguous software requirements. AmbiDetect combines text mining and machine learning for ambiguous requirement specification detection. The text mining technique is used to extract classification features as well as generating the training set. AmbiDetect uses a machine learning technique to perform the ambiguous requirement specification detection. From an initial user study to validate the tool, the results indicate that the accuracy of detection is reasonably acceptable. Although AmbiDetect is an early experimental tool, we optimist that this tool can be a platform to improve SRS quality.