In recognition-based user interface,users'satisfaction is determined not only by recognition accuracy but also by effort to correct recognition errors.In this paper,an error correction technique based on multimodal fusion is introduced.It allows a user to correct errors of Chinese handwriting recognition by repeating the handwriting in speech.A multimodal fusion algorithm is the key of the technique.By constraining the search for the best handwriting recognition result by speech input,the algorithm can correct errors in both character extraction and recognition of handwriting.The experimental result indicates that the algorithm is effective and efficient in computation.Moreover,evaluation also shows the correction technique can help users to correct errors in handwriting recognition more efficiently than the other two error correction techniques.