In this paper the authors proposed an intuitive speech interface with which a user can retrieve information through the speech dialogue. If the user says a keyword that the system has already read aloud, this interface returns information corresponding to the keyword. The authors system including this interface contains a dynamic dictionary and response control. From the dialogue, the system analyzes retrieved information using morphological analysis, and dynamically generates a recognition dictionary based on the morpheme and pronunciation of the words. The dynamic dictionary realizes the recognition of words that the system reads aloud. Also, response control obtains information from speech recognition results and previously spoken topics even if a part of the user’s spoken word is unclear. Because the user only repeats words that are heard, this interface can be used in eyes-free or hands-free situations. The proposed method was implemented on the system and the authors found that the task accomplishment rate was 96.1% for the condition where the SNR was 6.6 dB, which is the assumed noise in the car.