Results show that ARIMA is particularly efficient and effective on tasks involving harmonic, timing, and cross-performance retrieval, while remaining competitive with much larger baselines on other tasks.
Abstract
Self-supervised learning for symbolic music has advanced largely through token-level pretraining, but such representations remain tied to tokenizer-specific sequences and often provide time-span-level embeddings only indirectly. In this paper, we propose ARIMA, a reconstruction-grounded latent predictive framework for symbolic music that learns compact window-based representations directly from data. ARIMA encodes each fixed-duration window into a continuous latent representation, trains a causal predictor with contrastive next-latent prediction, and grounds the encoder through structured reconstruction of music elements. This design preserves local musical details while modeling temporal progression across windows. We evaluate ARIMA on downstream tasks spanning various levels of music understanding. Results show that ARIMA is particularly efficient and effective on tasks involving harmonic, timing, and cross-performance retrieval, while remaining competitive with much larger baselines on other tasks. Ablations further show that next-latent prediction is essential for temporally integrated representations, and that structured reconstruction stabilizes latent learning without requiring explicit variance regularization. The code is at https://github.com/AndyWeasley2004/symbolic_music_wm.
Rich internal representations of musical structure are essential for music understanding tasks such as machine-assisted music co-writing, yet self-supervised approaches for symbolic music representation remain underexplored, particularly those that encode the hierarchical multiscale nature of musical structures. We present MIDI-RAE-JEPA, combining a pitch- and time-shift equivariance objective with LeJEPA and a Swin Transformer V2 encoder to learn such hierarchical representations of symbolic music encoded as piano roll images. The time-shift equivariance objective encourages the model to internalize temporal musical relationships. The encoder is trained purely on self-supervised objectives -- including a masked embedding predictor (MEP) -- with collapse prevented via SIGReg. A separate decoder trained on the frozen encoder embeddings achieves reconstruction F1 of 0.995, and a flow matching generative model conditioned on those embeddings produces generations that closely match the pitch register and rhythmic density of the conditioning excerpt, while mismatched conditioning yields unrelated but musically plausible output. Learned representations outperform a Haar scattering transform baseline on a downstream emotion classification task, and embedding distances increase monotonically with pitch and time shift magnitude, confirming measurable equivariance. These results suggest that equivariance-based SSL objectives, combined with sufficient fine-level encoder capacity, provide a viable path toward semantically rich, generatively useful representations of symbolic music.
This study proposes a style-aware data augmentation framework that combines rule-based design with statistical constraints, applied to small-scale, highly constrained Jiangnan symbolic music generation tasks. By leveraging YNote representation, fixed rhythmic frameworks, and Markov-style local transition statistics, we systematically expand the training data while maintaining musical structural plausibility. Using the augmented data, we fine-tune a GPT-2 model to analyze how different training data scales affect generation behavior. Experimental results show that Bilingual Evaluation Understudy (BLEU) -based reference-overlap metrics exhibit only minor fluctuations across different training scales and are insufficient to directly reflect style improvement. In contrast, Kullback-Leibler (KL) divergence and bigram statistics effectively characterize the style consistency of the generated set in terms of overall distribution proximity and local transition plausibility. Further analysis indicates that a medium-scale training set (approximately 3,000–12,000 samples) achieves the best balance between distribution consistency and transition coverage, whereas excessive augmentation may lead to distribution calibration drift. Overall, the study demonstrates that data augmentation has a positive but non-monotonic effect on style consistency, highlighting the need for carefully designed augmentation strategies in highly constrained symbolic music generation tasks.
Yung-Ching Tseng, Yu-Chia Wang, Yung-An Chen et al.· International Conference on...· 0 citations
NAPE (Next-Audio-Patch-Embedding prediction), a self-supervised framework in which a causal Transformer predicts each next patch embedding of a log-mel spectrogram from the previous ones, using causal masking and stop-gradient as its sole training signal is introduced.
Umberto Cappellazzo, Xubo Liu, Stavros Petridis et al.· 0 citations
TAILS resolves cross-task ambiguity at the representation level, while leaving the original PTM, method-specific modules, and classifier unchanged, and can improve classification and task-inference performance with modest parameter overhead and negligible inference cost.
Zhiming Xu, Huiyu Yi, Zhenghe Xie et al.· 0 citations
Introduction The cognitive encoding of musical sequences is a complex process that involves capturing the intricate structure, temporal dynamics, and inherent uncertainties of musical data. Traditional methods often struggle to preserve the non-Euclidean geometric properties of musical sequences and fail to adequately model temporal dependencies and uncertainties. This paper introduces the Manifold Adaptive Sequence Encoder (MASE), a novel neural framework designed to address these challenges. Methods MASE integrates three key modules: the Riemannian Trajectory Mapper, which embeds musical sequences into a Riemannian manifold to maintain their geometric properties; the Agent-driven Temporal Planner, which effectively models the temporal dependencies and rhythmic patterns; and the Uncertainty-guided Sequence Filter, which quantifies and incorporates uncertainty to enhance robustness and generalization. The framework is optimized using manifold alignment optimization, ensuring the alignment of latent representations with the input data, and uncertainty-aware refinement, which iteratively refines predictions by leveraging uncertainty estimates. Results and discussion Experimental results demonstrate that MASE significantly improves the accuracy and robustness of musical sequence modeling, outperforming existing methods by a substantial margin. The proposed approach offers a principled methodology for modeling the cognitive encoding of musical sequences, with potential applications in music analysis, recommendation, and generation. This advancement in musical sequence encoding not only enhances the understanding of cognitive processes involved in music perception but also provides a robust tool for various practical applications in the field of music technology.
Shao-Jie Lin, Guang Zeng· Frontiers in Psychology· 0 citations
Joint Embedding Predictive Architectures (JEPA) have recently emerged as a paradigm for learning world models by predicting latent representations, offering a promising direction for self-supervised learning. While initial attempts have applied JEPA to the music domain, it remains unclear how such frameworks can naturally support the formation of a world model for music. In this work, we propose to learn a world model of piano sound using JEPA by framing music as an action-conditioned system: the audio is treated as the state, and the pianoroll as the instrument action. Given a current audio state and an action, the model predicts the resulting future audio state, mirroring how humans learn musical sound through interaction. The model is trained in a fully offline setting using paired audio-pianoroll data, without environment interaction. Experiments show that the learned model captures the relationships between musical actions and their resulting sound. The resulting representations support downstream tasks, including beat tracking, composer identification, and key estimation, and enable piano transcription via planning, by searching for actions that best explain a target sound.