一个快速自动音乐记谱方法  

An approach to fast automatic polyphonic music transcription

作　　者：周若华[1] 颜永红[1] 

机构地区：[1]中国科学院声学研究所,中科信利语音实验室,北京100190

出　　处：《声学学报》2010年第2期282-287,共6页Acta Acustica

基　　金：国家高技术研究发展计划(863计划,2006AA010102);国家科技支撑计划(2008BAI50B00);国家重点基础研究发展规划项目计划(973计划,2004CB318106);国家自然科学基金(10574140,60535030)

摘　　要：自动音乐记谱是音乐信号处理中的关键技术。本文描述了一个快速的自动复音音乐记谱方法。该方法采用回声器时频分析(RTFI)作为时频分析工具,主要由两个阶段组成,能量基的音符切分和多基频估计。本文所采用的多基频估计方法首先将RTFI能量谱按照谐音组合原理转换为基频能量谱,并基于基频能量谱采用简单的峰拾起方法对基频做初步估计;然后根据频谱不规律性和乐音谐音结构的基本假定,消除初步估计中的错误预测。Automatic music transcription plays an important role in music signal processing. This paper presents a computationally efficient approach to automatic polyphonic music transcription. The approach employs the Resonator Time-Frequency Image （RTFI） as a basic time-frequency analysis tool. The approach is mainly composed of two stages： energy-based onset detection and multiple pitch estimation. The proposed method makes preliminary pitch estimations by a simple peak-picking in the pitch energy spectrum, which is produced from original energy spectrum according to harmonic grouping principle; and then the incorrect estimations are cancelled according to spectral irregularity or some assumptions about harmonic structures of music notes.

关 键 词：自动音乐记谱 音乐信号处理 关键技术 回声器时频分析 

分 类 号：TN912.3[电子电信—通信与信息系统]