Abstract: A feature extraction algorithm based on the music melody outline is proposed.The algorithm picks up the music pitch sequence，and then converts to melody outline sequence.Finally the sequence is converted to melody outline characteristics based on the table of standard tone differences value.The results show that the system are very robust against surroundings noise，and the top-5 success rate is over 90% in a music database comprised 405 songs.

摘要： 提出了一种基于音乐旋律轮廓的特征提取算法。该算法从哼唱片断中提取出歌曲基音序列，经规整、合并、分段后转化为旋律轮廓序列，然后使用标准音调生成的标准音调差值表将此序列转化为旋律轮廓特征。结果表明，该系统对环境噪声有较好的鲁棒性；在含有405首歌曲的搜索空间中，检索前5位成功率超过90%。