Correction method and system for voice conversation

The embodiment of the invention provides a correction method for voice conversation. The method comprises the steps of: recognizing first text information of dialogue voice input by a user, wherein the first text information comprises a first semantic keyword determined by a plurality of candidate words; feeding back a first result with the first semantic keyword to the user based on the first text information; responding to the selection of the user on the first semantic keyword in the first result, and feeding back the plurality of candidate words to the user; and receiving a second semantickeyword input by the user, correcting the first text information based on the second semantic keyword, determining corrected second text information, and feeding back a second result with the secondsemantic keyword to the user based on the second text information. The embodiment of the invention further provides a correction system for the voice conversation. According to the embodiment of the invention, the objective tr