Joint Multi-Pitch Detection and Score Transcription for Polyphonic Piano Music

Liu, Lele; Morfi, Veronica; Benetos, Emmanouil

doi:10.1109/icassp39728.2021.9413601

Cited by 9 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…6 Table I also shows the tempo stability rate for the datasets, calculated according to the approach of Schreiber [23]. Specifically, we first convert all IBIs of a dataset into tempo values, and divide these tempo values by the average tempo of the corresponding 6 During the execution of this project, a dataset called ACPAS [49] that combines ASAP and another 59 real recordings of classical piano performances was released. We have the analysis and evaluation for those relatively small number of recordings not included in this work.…”

Section: A Statistics Of Datasetsmentioning

confidence: 99%

Local Periodicity-Based Beat Tracking for Expressive Classical Piano Music

Chiu

Müller

Davies

et al. 2023

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

To model the periodicity of beats, state-of-the-art beat tracking systems use "post-processing trackers" (PPTs) that rely on several empirically determined global assumptions for tempo transition, which work well for music with a steady tempo. For expressive classical music, however, these assumptions can be too rigid. With two large datasets of Western classical piano music, namely the Aligned Scores and Performances (ASAP) dataset and a dataset of Chopin's Mazurkas (Maz-5), we report on experiments showing the failure of existing PPTs to cope with local tempo changes, thus calling for new methods. In this paper, we propose a new local periodicity-based PPT, called predominant local pulse-based dynamic programming (PLPDP) tracking, that allows for more flexible tempo transitions. Specifically, the new PPT incorporates a method called "predominant local pulses" (PLP) in combination with a dynamic programming (DP) component to jointly consider the locally detected periodicity and beat activation strength at each time instant. Accordingly, PLPDP accounts for the local periodicity, rather than relying on a global tempo assumption. Compared to existing PPTs, PLPDP particularly enhances the recall values at the cost of a lower precision, resulting in an overall improvement of F1-score for beat tracking in ASAP (from 0.473 to 0.493) and Maz-5 (from 0.595 to 0.838).

show abstract

Section: A Statistics Of Datasetsmentioning

confidence: 99%

Local Periodicity-Based Beat Tracking for Expressive Classical Piano Music

Chiu

Müller

Davies

et al. 2023

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

show abstract

“…However, some recent proposals in MIR literature frame transcription problems in a sequence labeling formulation that approaches the task in a holistic or end-to-end manner [5], [6]: the input data-either scores or acoustic pieces-are directly decoded into a sequence of music-notation symbols. This makes it possible to address OMR and AMT tasks with similar recognition models that differ only as regards the input data used to train the system.…”

Section: Introductionmentioning

confidence: 99%

Late multimodal fusion for image and audio music transcription

Alfaro-Contreras¹,

Valero-Mas²,

Iñesta³

et al. 2022

Preprint

View full text Add to dashboard Cite

Music transcription, which deals with the conversion of music sources into a structured digital format, is a key problem for Music Information Retrieval (MIR). When addressing this challenge in computational terms, the MIR community follows two lines of research: music documents, which is the case of Optical Music Recognition (OMR), or audio recordings, which is the case of Automatic Music Transcription (AMT). The different nature of the aforementioned input data has conditioned these fields to develop modality-specific frameworks. However, their recent definition in terms of sequence labeling tasks leads to a common output representation, which enables research on a combined paradigm. In this respect, multimodal image and audio music transcription comprises the challenge of effectively combining the information conveyed by image and audio modalities. In this work, we explore this question at a late-fusion level: we study four combination approaches in order to merge, for the first time, the hypotheses regarding end-to-end OMR and AMT systems in a lattice-based search space. The results obtained for a series of performance scenarios-in which the corresponding singlemodality models yield different error rates-showed interesting benefits of these approaches. In addition, two of the four strategies considered significantly improve the corresponding unimodal standard recognition frameworks.

show abstract

“…With the rapid growth of the number of digital music, the piano playing pitch recognition algorithm performs personalized identification by analyzing the historical behavior of pitch-on-demand music [ 1 ]. As a hotspot of development in the new century, the neural network has gained more and more attention and application depending on its advantages in nonlinearity, self-learning, robustness, and self-adaptation [ 2 – 4 ]. As one of the most successful models of neural networks, the BP network has been able to simulate complex nonlinear models by virtue of its powerful nonlinear mapping capability, parallel distributed processing capability, adaptive capability, fault tolerance capability, and generalization capability [ 5 ].…”

Section: Introductionmentioning

confidence: 99%

Construction and Application of a Piano Playing Pitch Recognition Model Based on Neural Network

Chen

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

The intonation recognition of piano scores is an important problem in the field of music information retrieval. Based on the neural network theory, this study constructs a piano playing intonation recognition model and uses the optimized result as the feature of piano music to realize the prediction of the music recognition of the intonation preference. The model combines the behavioral preference relationship between intonation and musical notation to measure the similarity between intonations, which is used to calculate the similarity between intonation preference and music, and solves the quantification problem of intonation recognition. In the simulation process, the pitch preference feature of piano playing is used as the identification basis, and the effectiveness of the algorithm is verified through four sets of experiments. The experimental results show that the average symbol error rate of the improved network model is reduced to 0.3234%, and the model training time is about 33.3% of the traditional convolutional recurrent neural network, which is optimized in terms of recognition accuracy and training time in single-class pitch feature. In the recommended method of multi-category evaluation of pitch features, the recognition accuracy of multi-category pitch features is 42.89%, which effectively improves the musical tone recognition rate.

show abstract

Joint Multi-Pitch Detection and Score Transcription for Polyphonic Piano Music

Cited by 9 publications

References 8 publications

Local Periodicity-Based Beat Tracking for Expressive Classical Piano Music

Local Periodicity-Based Beat Tracking for Expressive Classical Piano Music

Late multimodal fusion for image and audio music transcription

Construction and Application of a Piano Playing Pitch Recognition Model Based on Neural Network

Contact Info

Product

Resources

About