Existing Real-Time Translation Interfaces (RTTI) do not provide experience as natural and efficient as monolingual communication. Also, such systems do not provide functions supporting language learning. This results in the waste of both time and potential language context. In order to overcome the above limitations, we propose a solution named "Talk&Learn". Its core idea is to rearrange ("Delay-Match") the real-time videos and translated texts or speeches, so as to gain better naturalness and efficiency. At the same time, this will create extra free time for users. So we further propose to utilize the free time for contextual language learning.