| 融合声源分离及反复结构模型的音乐分离方法 |
| |
| 引用本文： | 张天, 张天骐, 葛宛营, 喻盛琪. 融合声源分离及反复结构模型的音乐分离方法[J]. 声学学报, 2020, 45(5): 707-715. DOI: 10.15949/j.cnki.0371-0025.2020.05.010 |
| |
| 作者姓名： | 张天 张天骐 葛宛营 喻盛琪 |
| |
| 作者单位： | 1.重庆邮电大学 通信与信息工程学院 重庆 400065 |
| |
| 基金项目： | 国家自然科学基金项目(61671095,61702065,61701067,61771085)、信号与信息处理重庆市市级重点实验室建设项目(CSTC2009CA2003)、重庆市研究生科研创新项目(CYS17219)和重庆市教育委员会科研项目(KJ1600427,KJ1600429)资助 |
| |
| 摘 要： | 针对现有的单一音乐分离算法难以分离背景音乐和歌声的问题,提出一种融合声源分离及反复结构模型的音乐分离方法。该方法首先通过迭代的方式分离出音乐的谐波声源和冲击声源,再引入节奏谱分析不同声源的能量谱矩阵,对其建立反复周期结构模型,最后保留谐波源的反复周期成分,去除冲击源的反复周期成分,得到分离后的背景音乐和歌声。针对MIR-1K数据库,对1000首音乐片段的分离实验表明,与现有分离方法对比,本文方法在分离背景音乐和歌声时均表现出优异的性能。
|
| 收稿时间： | 2018-12-10 |
| 修稿时间： | 2019-05-05 |
Music separation method based on repeating structural model and sound source separation |
| |
| ZHANG Tian, ZHANG Tianqi, GE Wanying, YU Shengqi. Music separation method based on repeating structural model and sound source separation[J]. ACTA ACUSTICA, 2020, 45(5): 707-715. DOI: 10.15949/j.cnki.0371-0025.2020.05.010 |
| |
| Authors: | ZHANG Tian ZHANG Tianqi GE Wanying YU Shengqi |
| |
| Affiliation: | 1.School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications Chongqing 400065 |
| |
| Abstract: | In order to solve the problem of separation between singing and accompaniment in the musical signals,a music separation method based on repeating structural model and Sound Source Separation is proposed.Firstly,the harmonic source and the percussive source of the music are separated by iterative method.Then the beat spectrum was introduced to analysis the energy spectrum matrix of the different sound sources.And the repeated periodic components of the harmonic source are retained to obtain background music while the repeated periodic components of the percussive source are removed to separate the singing voice.For the MIR-1 K database,the separation experimental results of 1000 music fragments show that the proposed method has an advantage over other existing music separation methods. |
| |
| Keywords: | |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《声学学报》浏览原始摘要信息 |
|
点击此处可从《声学学报》下载免费的PDF全文 |
|
