Musical Sound Source Identi(cid:12)cation Based on Frequency Component Adaptation
Musical Sound Source Identi(cid:12)cation Based on Frequency Component Adaptation
复制标题
基于频率分量自适应的音乐声源识别(cid:12)
DOI：
--
复制
发表时间：
2003
期刊：
影响因子：
--
通讯作者：
H. Tanaka
中科院分区：
文献类型：
--
作者：
Toichiro Kinoshita;S. Sakai;H. Tanaka
在听觉场景分析中，声源识别（cid:12）是从多个声源组成的声信号中提取音符的必要操作。我们提出了一种用于音乐场景分析的处理模型OPTIMA，并实现了它的实验系统。然而，该系统对频率成分重叠的信号不具有鲁棒性。本文提出了一种利用频率分量的重叠模式来改善这一问题的新方法，并在OP-TIMA中作为处理模块实现。采用加权模板匹配法对每个频率分量簇重复识别声源。根据信号的每个特征的signi（cid:12）百分比来评估权重。当多个组件重叠时，我们的系统自适应地将输入信号的特征修改为重叠组件的组合。实验结果表明，该系统可以识别66% ~ 75%的音源。与没有提出机制的结果相比，它还显示出大约10%的准确性提高。
In auditory scene analysis, sound source identi-(cid:12)cation is an essential operation when extracting musical notes from acoustical signals composed of multiple sound sources. We have previously proposed a processing model OPTIMA for music scene analysis and implemented its experimental system. However, the system was not robust to signals with overlapped frequency components. In this paper, we present a new method that improves this problem by using overlap pattern of frequency components, and implemented as a processing module in OP-TIMA. Weighted template-matching method is applied to identify sound sources repeatedly to each frequency component cluster. The weight is evaluated according to the signi(cid:12)cance of each feature of the signal. When multiple components are overlapped, our system adaptively modi(cid:12)es features of an input signal to a combination of overlapped components. Experimental results show that the system can identify sound sources of 66% to 75% of musical notes. It also showed about 10% improvement in accuracy, compared to the result without the proposed mechanism.