一个快速自动音乐记谱方法

An approach to fast automatic polyphonic music transcription

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.