Instrogram: Probabilistic Representation of Instrument Existence for Polyphonic Music
Instrogram: Probabilistic Representation of Instrument Existence for Polyphonic Music
复制标题
DOI：
10.2197/ipsjdc.3.1
复制
发表时间：
2007-01
期刊：
影响因子：
--
通讯作者：
Tetsuro Kitahara;Masataka Goto;Kazunori Komatani;T. Ogata;HIroshi G. Okuno
中科院分区：
文献类型：
--
作者：
Tetsuro Kitahara;Masataka Goto;Kazunori Komatani;T. Ogata;HIroshi G. Okuno
本文提出了一种新的复调音乐乐器识别技术。由于复调音乐中的传统乐器识别是按音符执行的，即对于每个音符，需要准确地估计每个音符的开始时间和基频(F0)。然而，在复调音乐中，这些估计通常并不容易，因此估计误差严重恶化了识别性能。在没有这些估计的情况下，我们的技术计算每个可能的F0的仪器存在概率的时间轨迹。仪器存在概率被定义为使用PreFEst计算的非特定仪器存在概率和使用隐马尔可夫模型计算的条件仪器存在概率的乘积。乐器存在概率被可视化为被称为Instrogram的类似谱图的图形表示，并被应用于基于MPEG7注释和基于乐器相似性的音乐信息检索。对合成音乐和实际演奏录音的实验结果表明，Instrogram对合成音乐的平均准确率为87.5%，对真实演奏的准确率为69.4%，并且比基于MFCC的度量更好地反映了实际乐器的情况。
This paper presents a new technique for recognizing musical instruments in polyphonic music. Since conventional musical instrument recognition in polyphonic music is performed notewise, i.e., for each note, accurate estimation of the onset time and fundamental frequency (F0) of each note is required. However, these estimations are generally not easy in polyphonic music, and thus estimation errors severely deteriorated the recognition performance. Without these estimations, our technique calculates the temporal trajectory of instrument existence probabilities for every possible F0. The instrument existence probability is defined as the product of a nonspecific instrument existence probability calculated using the PreFEst and a conditional instrument existence probability calculated using hidden Markov models. The instrument existence probability is visualized as a spectrogram-like graphical representation called the instrogram and is applied to MPEG-7 annotation and instrumentation-similaritybased music information retrieval. Experimental results from both synthesized music and real performance recordings have shown that instrograms achieved MPEG-7 annotation (instrument identification) with a precision rate of 87.5% for synthesized music and 69.4% for real performances on average and that the instrumentation similarity measure reflected the actual instrumentation better than an MFCC-based measure.