• Generative model for piano sight-reading exercises controlled by difficulty level. • Scores are generated in MusicXML, ensuring readability and playability. • An auxiliary loss improves difficulty control and prevents conditioning collapse. • Expert pianists rated the pieces as clear, natural, and suitable for teaching. • The approach advances towards personalized music learning. Sight-reading is a core skill in music education. It refers to the ability to play a written piece of music correctly the first time it is seen. Developing this skill requires frequent practice with completely new musical excerpts that match the difficulty level of the student. However, creating new sight-reading exercises at a specific difficulty level requires significant time and expert knowledge. As a result, students and teachers often rely on pieces from the existing piano literature, even though sight-reading exams typically use compositions written specifically for the exam. Generative music systems provide a promising approach for creating new sight-reading material with explicit control over performance difficulty. In this work, we frame the creation of sight-reading exercises as a symbolic music generation task that produces piano scores with controllable difficulty. Existing approaches typically rely on control tokens to guide generation, but we show that this strategy does not result in piano scores with reliably controlled difficulty. To address this issue, we introduce an auxiliary difficulty prediction objective using synthetic difficulty labels produced by an expert-based system, enabling scalable training. Our method improves difficulty conditioning accuracy from 69.3% to 92.9% compared to a baseline that conditions generation solely on difficulty control tokens, and reduces mean squared error from 0.30 to 0.09. A user study with expert pianists shows that the generated scores are rated comparable or superior to human-written material in readability and naturalness, while maintaining appropriate playability across difficulty levels. These results represent a step toward the generation of music exercises for a variety of educational applications.

Predicting the difficulty of playing a musical score is essential for structuring and exploring score collections. Despite its importance for music education, the automatic difficulty classification of piano scores is not yet solved, mainly due to the lack of annotated data and the subjectiveness of the annotations. This paper aims to advance the state-of-the-art in score difficulty classification with two major contributions. To address the lack of data, we present Can I Play It? (CIPI) dataset, a machine-readable piano score dataset with difficulty annotations obtained from the renowned classical music publisher Henle Verlag. The dataset is created by matching public domain scores with difficulty labels from Henle Verlag, then reviewed and corrected by an expert pianist. As a second contribution, we explore various input representations from score information to pre-trained ML models for piano fingering and expressiveness inspired by the musicology definition of performance. We show that combining the outputs of multiple classifiers performs better than the classifiers on their own, pointing to the fact that the representations capture different aspects of difficulty. In addition, we conduct numerous experiments that lay a foundation for score difficulty classification and create a basis for future research. Our best-performing model reports a 39.5% balanced accuracy and 1.1 median square error across the nine difficulty levels proposed in this study. Code, dataset, and models are made available for reproducibility.

Comunicació presentada a la 14th International Conference on Computer Supported Education, celebrada del 22 a 24 d'abril de 2021 de manera virtual.

In this paper, we introduce score difficulty classification as a sub-task of music information retrieval (MIR), which may be used in music education technologies, for personalised curriculum generation, and score retrieval. We introduce a novel dataset for our task, Mikrokosmos-difficulty, containing 147 piano pieces in symbolic representation and the corresponding difficulty labels derived by its composer Béla Bartók and the publishers. As part of our methodology, we propose piano technique feature representations based on different piano fingering algorithms. We use these features as input for two classifiers: a Gated Recurrent Unit neural network (GRU) with attention mechanism and gradient-boosted trees trained on score segments. We show that for our dataset fingering based features perform better than a simple baseline considering solely the notes in the score. Furthermore, the GRU with attention mechanism classifier surpasses the gradient-boosted trees. Our proposed models are interpretable and are capable of generating difficulty feedback both locally, on short term segments, and globally, for whole pieces. Code, datasets, models, and an online demo are made available for reproducibility.

Piano fingering is a creative and highly individualised task acquired by musicians progressively in their first music education years. Pianists must learn to choose the order of fingers to play the piano keys because scores do not have engraved finger and hand movements as other technique elements. Numerous research efforts have been conducted for automatic piano fingering based on a previous dataset composed of 150 score excerpts fully annotated by multiple expert annotators. However, most piano sheets include partial annotations for problematic finger and hand movements. We introduce a novel dataset for the task, the ThumbSet dataset, containing 2523 pieces with partial and noisy annotations of piano fingering crowdsourced from non-expert annotators. As part of our methodology, we propose two autoregressive neural networks with beam search decoding for modelling automatic piano fingering as a sequence-to-sequence learning problem, considering the correlation between output finger labels. We design the first model with the exact pitch representation of previous proposals. The second model uses graph neural networks to more effectively represent polyphony, whose treatment has been a common issue across previous studies. Finally, we finetune the models on the existing expert annotations dataset. The evaluation shows that (1) we are able to achieve high performance when training on the ThumbSet dataset and that (2) the proposed models outperform the state-of-the-art hidden Markov models and recurrent neural network baselines. Code, dataset, models, and results are made available to enhance the task reproducibility, including a new framework for evaluation.