On the Use of Memory for Detecting Musical Notes in Polyphonic Piano Music

被引：1
|
作者：
Costantini, Giovanni [1 ,2 ]
Todisco, Massimiliano [1 ,2 ]
Perfetti, Renzo [3 ]
机构：
[1] Univ Roma Tor Vergata, Dept Elect Engn, Rome, Italy
[2] Inst Acoust OM Corbino, Rome, Italy
[3] Univ Perugia, Elect & Informat Engn Dept, Perugia, Italy
来源：
2009 EUROPEAN CONFERENCE ON CIRCUIT THEORY AND DESIGN, VOLS 1 AND 2 | 2009年
关键词：
D O I：
10.1109/ECCTD.2009.5275106
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
Music transcription consists in transforming the musical content of audio data into a symbolic representation. The objective of this study is to investigate a transcription system for polyphonic piano. The proposed method focuses on temporal musical structures, note events and their main characteristics: the attack instant and the pitch. Onset detection exploits a time-frequency representation of the audio signal. Note classification is based on constant Q transform (CQT) and support vector machines (SVMs). Finally, to validate our method, we present a collection of experiments using a wide number of musical pieces of heterogeneous style.
引用
收藏
页码：806 / +
页数：2
相关论文
共 50 条
12345