MODEL-BASED EVENT LABELING IN THE TRANSCRIPTION OF PERCUSSIVE AUDIO SIGNALS

MODEL-BASED EVENT LABELING IN THE TRANSCRIPTION OF PERCUSSIVE AUDIO SIGNALS
复制标题

敲击声音频信号转录中基于模型的事件标记

DOI:
--
复制
发表时间:
2003
期刊:
--
影响因子:
--
通讯作者:
Anssi Klapuri
Anssi Klapuri
中科院分区:
--
文献类型:
--
作者:
Jouni Paulus;Anssi Klapuri

文献摘要

被引文献

相似文献

本文描述了一种转录任意非鼓声的连续音频信号的方法,该系统使用起始检测器从输入信号中定位声音。然后从这些声音的起始时间中提取一组特征,对这些特征向量进行聚类,并对聚类中的每一个向量进行标记,以描述每一个声音的节奏作用。该系统使用由非鼓声组成的多声道声音轨迹进行评估,在模拟中,该系统的总错误率为33.7%。演示信号可在URL:<http://www.cs.tut.fi/~paulus/demo/>上获得。
In thispaperwedescribeamethodfor thetranscriptionof percussive audiosignalswhich have beenperformedwith arbitrarynondrumsounds.Thesystemlocatessoundeventsfrom theinputsignal using an onsetdetector . Then a set of featuresis extracted from the onsettimes.Featurevectorsareclusteredandthe clustersareassignedwith labelswhich describethe rhythmic role of eachevent.For thelabeling,a novel methodis proposedwhich is basedon metrical(temporal)positionsof thesoundeventswithin themeasures. Thesystemis evaluatedusingmonophonicpercussive tracks consistingof non-drumsounds.In simulations,the systemachieved a total error rate of 33.7%. Demo signalsare available at URL:<http://www.cs.tut.fi/~paulus/demo/>.