中文摘要：

目前对艺术嗓音进行评价存在耗时、费力且主观性强等缺陷。利用计算机提取和分析艺术嗓音信号的基频、第一共振峰及第三共振峰三个声学参数，构造BP神经网络，通过机器学习，实现了对艺术嗓音的客观评价。与主观评价比较，结果的一致性达到90％。

英文摘要：

At present, there are many defects in the evaluation of artistic voice, such as time -consuming, laborious and strong subjectivity. To overcome these defects, a new evaluating method is proposed in this paper. With the help of the com- puter and the way of voice analysis, three acoustic parameters are extracted, including fundamental frequency, the first for- mant and the third formant. Then the BP neural network is constructed, learning by the machine, an objective evaluation of the artistic voice is achieved. The result shows that the consistency of objective evaluation and subjective evaluation up to 90%.