The invention provides a mispronounce correcting method and system through voice recognition. The method comprises the steps that a mapping table between a standard acoustic model and a wrong acousticmodel which correspond to characters easy to mispronounce is built; voice information of a user is acquired; the voice information of the user is recognized, and when the voice information comprisesthe characters easy to mispronounce, audio clips corresponding to terms comprising the characters easy to mispronounce in a voice message of the user are extracted; when the audio clips are in accordance with a voice audio matching result in the wrong acoustic model, the user is warned of mispronouncing of the characters easy to mispronounce, and a voice audio in the corresponding standard acoustic model is output according to the mapping table. By building the mapping table between the standard acoustic model and the wrong acoustic model, when it is recognized that the user mispronounces thecharacters easy to mispronounce, the user is warned, and the corresponding correct audio is output.