In the pursuit of developing expressive music performance models using artificial intelligence, this paper introduces DExter, a new approach leveraging diffusion probabilistic models to render Western classical piano performances. The main challenge faced in performance rendering tasks is the continuous and sequential modeling of expressive timing and dynamics over time, which is critical for capturing the evolving nuances that characterize live musical performances. In this approach, performance parameters are represented in a continuous expression space, and a diffusion model is trained to predict these continuous parameters while being conditioned on a musical score. Furthermore, DExter also enables the generation of interpretations (expressive variations of a performance) guided by perceptually meaningful features by being jointly conditioned on score and perceptual-feature representations. Consequently, we find that our model is useful for learning expressive performance, generating perceptually steered performances, and transferring performance styles. We assess the model through quantitative and qualitative analyses, focusing on specific performance metrics regarding dimensions like asynchrony and articulation, as well as through listening tests that compare generated performances with different human interpretations. The results show that DExter is able to capture the time-varying correlation of the expressive parameters, and it compares well to existing rendering models in subjectively evaluated ratings. The perceptual-feature-conditioned generation and transferring capabilities of DExter are verified via a proxy model predicting perceptual characteristics of differently steered performances.

Rapid advancements in artificial intelligence have significantly enhanced generative tasks involving music and images, employing both unimodal and multimodal approaches. This research develops a model capable of generating music that resonates with the emotions depicted in visual arts, integrating emotion labeling, image captioning, and language models to transform visual inputs into musical compositions. Addressing the scarcity of aligned art and music data, we curated the Emotion Painting Music Dataset, pairing paintings with corresponding music for effective training and evaluation. Our dual-stage framework converts images to text descriptions of emotional content and then transforms these descriptions into music, facilitating efficient learning with minimal data. Performance is evaluated using metrics such as Fréchet Audio Distance (FAD), Total Harmonic Distortion (THD), Inception Score (IS), and KL divergence, with audio-emotion text similarity confirmed by the pre-trained CLAP model to demonstrate high alignment between generated music and text. This synthesis tool bridges visual art and music, enhancing accessibility for the visually impaired and opening avenues in educational and therapeutic applications by providing enriched multi-sensory experiences.

Empirical expressive performance studies are typically performed on small, curated datasets. In this study, we present a large‑scale analysis of expressive timing in classical piano performance using a ‘distant listening’ approach across six MIDI datasets totaling over 600 hours of music. We revisit three core aspects of expressive timing drawn from empirical performance research: (1) the relational invariance of timing patterns with respect to tempo; (2) the influence of score markings, register, and interval consonance on articulation; and (3) the role of asynchrony as a means of expressive accentuation. Our findings indicate that timing patterns do not scale proportionally with tempo; however, weak interactions between tempo and metrical position suggest that both factors jointly contribute to shaping timing patterns. Articulation analysis confirms associations with score markings and register, although the relationship with interval consonance is less consistent. Melody lead tendencies are consistently observed across datasets, though our findings indicate that those occurring on the beat level may primarily reflect dynamic accentuation. Overall, our results provide empirical validation for certain established theories of expressive performance while challenging others, illustrating how large‑scale computational analysis can complement traditional controlled studies by offering broader insights into performance timing.

Research in music understanding has extensively explored composition-level attributes such as key, genre, and instrumentation through advanced representations, leading to cross-modal applications using large language models. However, aspects of musical performance such as stylistic expression and technique remain underexplored, along with the potential of using large language models to enhance educational outcomes with customized feedback. To bridge this gap, we introduce LLaQo, a Large Language Query-based music coach that leverages audio language modeling to provide detailed and formative assessments of music performances. We also introduce instruction-tuned query-response datasets that cover a variety of performance dimensions from pitch accuracy to articulation, as well as contextual performance understanding (such as difficulty and performance techniques). Utilizing AudioMAE encoder and Vicuna-7b LLM backend, our model achieved state-of-the-art (SOTA) results in predicting teachers' performance ratings, as well as in identifying piece difficulty and playing techniques. Textual responses from LLaQo was moreover rated significantly higher compared to other baseline models in a user study using audio-text matching. Our proposed model can thus provide informative answers to open-ended questions related to musical performance from audio data.

Music is inherently made up of complex structures, and representing them as graphs helps to capture multiple levels of relationships. While music generation has been explored using various deep generation techniques, research on graph-related music generation is sparse. Earlier graph-based music generation worked only on generating melodies, and recent works to generate polyphonic music do not account for longer-term structure. In this paper, we explore a multi-graph approach to represent both the rhythmic patterns and phrase structure of Chinese pop music. Consequently, we propose a two-step approach that aims to generate polyphonic music with coherent rhythm and long-term structure. We train two Variational Auto-Encoder networks - one on a MIDI dataset to generate 4-bar phrases, and another on song structure labels to generate full song structure. Our work shows that the models are able to learn most of the structural nuances in the training dataset, including chord and pitch frequency distributions, and phrase attributes.