基于隐马尔可夫模型的单音及和弦钢琴指法自动标注（英文）

Automatic Marking of Single-tone and Chord Piano Fingering Based on Hidden Markov Model

提出了一种基于隐马尔可夫模型的用于双手的钢琴指法标注方法.在隐马尔可夫模型中,指法的形式是隐藏状态,乐谱的音符是输出状态.方法主要包含两个步骤:确定隐马尔可夫模型的转移概率矩阵和输出概率矩阵,以及使用维特比算法寻找对应于音符序列的概率最大的指法序列.所提方法中的隐马尔可夫模型可以同时处理单音以及和弦.同时方法的有效性也通过真实的钢琴乐谱得到了验证.

A method based on Hidden Markov Model（HMM）for automatic annotation of piano fingering for both hands is proposed.In HMM,the form of fingering is the hidden state and the output note is the observed state.The method mainly has two steps：determining all the transition and emission probability of the HMM and using Viterbi algorithm to search for the most likely sequence of the state of fingering given the sequence of notes.HMM in the method can process both the single note and the chord simultaneously.And the feasibility of the method was verified by the real piano pieces.