With the rapid development of computer technology, computer music has begun to appear in the laboratory. Many potential utility of computer music is gradually increasing. The purpose of this paper is attempted to analyze the possibility of integrating multimodal interaction such as vision-based hand gesture and speech interaction into musical conducting education. To achieve this purpose, this paper is focus on discuss some related research and the traditional musical conducting education. To do so, six musical conductors had been interviewed to share their musical conducting learning/ teaching experience. These interviews had been analyzed in this paper to show the syllabus and the focus of musical conducting education for beginners.