

Author: Wang Qi Zhou Ruohua Yan Yonghong
Publisher: MDPI
E-ISSN: 2076-3417|8|3|470-470
ISSN: 2076-3417
Source: Applied Sciences, Vol.8, Iss.3, 2018-03, pp. : 470-470
Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.
Abstract
This paper proposes a note-based music language model (MLM) for improving note-level polyphonic piano transcription. The MLM is based on the recurrent structure, which could model the temporal correlations between notes in music sequences. To combine the outputs of the note-based MLM and acoustic model directly, an integrated architecture is adopted in this paper. We also propose an inference algorithm, in which the note-based MLM is used to predict notes at the blank onsets in the thresholding transcription results. The experimental results show that the proposed inference algorithm improves the performance of note-level transcription. We also observe that the combination of the restricted Boltzmann machine (RBM) and recurrent structure outperforms a single recurrent neural network (RNN) or long short-term memory network (LSTM) in modeling the high-dimensional note sequences. Among all the MLMs, LSTM-RBM helps the system yield the best results on all evaluation metrics regardless of the performance of acoustic models.
Related content




Identification of polyphonic piano signals
By Rossi L. Girolami G. Leca M.
Acta Acustica united with Acustica, Vol. 83, Iss. 6, 1997-11 ,pp. :


A Note on Distance-based Graph Entropies
By Chen Zengqiang Dehmer Matthias Shi Yongtang
Entropy, Vol. 16, Iss. 10, 2014-10 ,pp. :


Metrics for Polyphonic Sound Event Detection
By Mesaros Annamaria Heittola Toni Virtanen Tuomas
Applied Sciences, Vol. 6, Iss. 6, 2016-05 ,pp. :