Search Results (40)

Controllable symbolic music generation must preserve a reference melody while remaining responsive to style prompts. Existing hierarchical diffusion systems typically reuse a shared condition vector across harmony, rhythm, and timbre stages, which can entangle stylistic factors and weaken melody preservation. We present HCDMG++, a hierarchical diffusion framework that addresses these two limitations through stage-aware style routing and differentiable melody regularization. The routing module uses a residual multi-layer perceptron (MLP) with zero-initialized scalar gates to project text-derived style embeddings into harmony-, rhythm-, and timbre-specific subspaces, whereas the regularization branch aligns soft pitch histograms and contour trajectories with the conditioning melody during training without breaking the differentiable computation graph. We evaluate the integrated system on a 384-sample benchmark covering four melodies, eight styles, four random seeds, and three denoising budgets, supplemented by a matched legacy-compatible reference and inference-time component ablation that contrasts legacy behavior, silenced gates, an automated uniform gamma routing sweep, and the full forward pass. HCDMG++ produces valid four-track outputs in all 384 runs, reaches a peak pitch histogram similarity score of 0.508 under a 64-step budget, and improves pitch histogram alignment over Legacy-HCDMG by roughly two orders of magnitude on the matched slice, while attaining a positive Fisher-style style separability score where the legacy benchmark is too sparse to support one. These results indicate that stage-specific conditioning and differentiable structural guidance jointly improve controllability in symbolic music diffusion, while also exposing the remaining limitations in long-form generalization and perceptual validation, which motivate the future work outlined at the end of this paper. Full article

Large-scale symbolic melody datasets are essential for data-driven music information retrieval and generation, yet traditional-style Chinese melodies remain scattered across heterogeneous score formats and image sources. Existing extraction pipelines typically focus on single modalities—either MIDI archives or standard staff notation—and lack unified handling for numbered musical notation (Jianpu) and automated quality assurance. We propose the Multi-Source Melody Pipeline (MSMP), a systems-integration prototype whose front-end admits MIDI, MusicXML, Jianpu images, and staff images, and whose back-end converges on a standardized event-level representation; the present case study exercises the image branch—in particular the Jianpu branch, through a Gemini-2.5-flash vision language model—and treats the MIDI/MusicXML ingestion paths as architectural slots that are wired in but not experimentally validated in this submission. The system employs notation-aware routing to direct score images to appropriate backends (a VLM for Jianpu and rule-based OMR for staff) and enforces a structural validity gate (schema conformance plus at least one melodic track with at least one musical event) on every candidate segment. Validation on a 292-page representative prototype cohort yielded an 80.1% structural-acceptance rate—explicitly not a transcription accuracy number—and a newly added ground-truth benchmark on 50 manually annotated Jianpu pages reports 95.8% time-signature exact accuracy, 77.1% tonal-pitch-class key accuracy, 100% tempo agreement within $\pm 5$ BPM, and, on a 10-page note-level subset, a mean first-16-note pitch F1 of 0.898 (octave-sensitive) with a Symbol Error Rate of 0.150. A companion 10-page K = 3 self-consistency audit indicates that metadata errors are systematic rather than stochastic. This work, therefore, contributes a reproducible integration architecture and a quantitative baseline on the Jianpu branch, rather than a new OMR algorithm, a new dataset release, or a fully benchmarked multi-format corpus; ongoing work addresses out-of-distribution classifier evaluation, comparison against dedicated Jianpu OMR baselines, and release of a copyright-cleared corpus. Full article

Irish traditional music is typically characterised as an ‘oral tradition’ which has been handed down from one generation to the next. Though the process of reworking has been considered central to its transmission, little consideration has thus far been given to the ways in which the music develops diachronically and what factors influence these performance decisions. Cottrell considers the act of performance as a palimpsest where traces of earlier renditions can still be identified in any given performance. Taking the example of ‘The Japanese Hornpipe’, this article will consider the ways in which individual actors and regional styles can reshape fundamental melodic characteristics through creative alteration in successive performances as the melody passed from circus performance act through the Donegal fiddle tradition and the whistling competition at Fleadh Cheoil na hÉireann. Full article

The purpose of this research was to investigate whether music empirically associated with therapeutic effects contains intrinsic informational structures that differentiate it from other sound sequences. Drawing on ontology, phenomenology, nonlinear dynamics, and complex systems theory, we hypothesize that therapeutic relevance may be linked to persistent structural patterns embedded in musical signals rather than to stylistic or genre-related attributes. This paper introduces the Discriminating Music Sequences (DiMuSes) method, an unsupervised, structure-oriented analytical framework designed to detect such patterns. The method applies 24 scalar evaluators derived from statistics, fractal geometry, nonlinear physics, and complex systems, transforming sound sequences into multidimensional vectors that characterize their global temporal organization. Principal Component Analysis (PCA) reduces this feature space to three dominant components (PC1–PC3), enabling visualization and comparison in a reduced informational space. Unsupervised k-Means clustering is subsequently applied in the PCA space to identify groups of structurally similar sound sequences, with cluster quality evaluated using Silhouette and Davies–Bouldin indices. Beyond clustering, DiMuSe implements ranking procedures based on relative positions in the PCA space, including distance to cluster centroids, inter-item proximity, and stability across clustering configurations, allowing melodies to be ordered according to their structural proximity to the therapeutic cluster. The method was first validated using synthetically generated nonlinear signals with known properties, confirming its capacity to discriminate structured time series. It was then applied to a dataset of 39 music and sound sequences spanning therapeutic, classical, folk, religious, vocal, natural, and noise categories. The results show that therapeutic music consistently forms a compact and well-separated cluster and ranks highly in structural proximity measures, suggesting shared informational characteristics. Notably, pink noise and ocean sounds also cluster near therapeutic music, aligning with independent evidence of their regulatory and relaxation effects. DiMuSe-derived rankings were consistent with two independent studies that identified the same musical pieces as highly therapeutic.The present research remains at a theoretical stage. Our method has not yet been tested in clinical or experimental therapeutic settings and does not account for individual preference, cultural background, or personal music history, all of which strongly influence therapeutic outcomes. Consequently, DiMuSe does not claim to predict individual efficacy but rather to identify structural potential at the signal level. Future work will focus on clinical validation, integration of biometric feedback, and the development of personalized extensions that combine intrinsic informational structure with listener-specific response data. Full article

This study introduces a novel generative approach for crafting phrase-oriented rhythmic patterns in jazz solos, leveraging statistical analyses of a comprehensive corpus, the Weimar Jazz Database. Jazz solos, celebrated for their improvisational complexity, require a delicate interplay between rhythm and melody, making the generation of authentic rhythmic patterns a challenging task. This work systematically explores the relationships among rhythmic elements, including phrases, beats, divisions, and patterns. The generative method employs a Markov chain framework to synthesize rhythmic divisions and patterns, ensuring stylistic coherence and diversity. An extensive evaluation compares original and generated datasets through statistical and machine learning metrics, validating the generative model’s ability to replicate key rhythmic characteristics while fostering innovation. The findings underscore the potential of this approach to contribute significantly to the fields of computational creativity and algorithmic music composition, providing a robust tool for generating compelling jazz solos. Full article

This paper explores different approaches to harmony tokenization in symbolic music for transformer-based models, focusing on two tasks: masked language modeling (MLM) and melodic harmonization generation. Four tokenization strategies are compared, each varying in how chord information is encoded: (1) as full chord symbols, (2) separated into root and quality, (3) as sets of pitch classes, and (4) as sets of pitch classes where one is designated as a root. A dataset of over 17,000 lead sheet charts is used to train and evaluate RoBERTa for MLM and GPT-2/BART for harmonization. The results show that chord spelling methods—those breaking chords into pitch-class tokens—achieve higher accuracy and lower perplexity, indicating more confident predictions. These methods also produce fewer token-level errors. In harmonization tasks, chunkier tokenizations (with more information per token) generate chords more similar to the original data, while spelling-based methods better preserve structural aspects such as harmonic rhythm and melody–harmony alignment. Audio evaluations reveal that spelling-based models tend toward more generic pop-like harmonizations, while chunkier tokenizations more faithfully reflect the dataset’s style. Overall, while no single tokenization method dominates across all tasks, different strategies may be preferable for specific applications, such as classification or generative style transfer. Full article

We present a novel encoder-only Transformer model for symbolic music harmony generation, based on a fixed time-grid representation of melody and harmony. Inspired by denoising diffusion processes, our model progressively unmasks harmony tokens over a sequence of discrete stages, learning to reconstruct the full harmonic structure from partial context. Unlike autoregressive models, this formulation enables flexible, non-sequential generation and supports explicit control over harmony placement. The model is stage-aware, receiving timestep embeddings analogous to diffusion timesteps, and is conditioned on both a binary piano roll and a pitch class roll to capture melodic context. We explore two unmasking schedules—random token revealing and midpoint doubling—both requiring a fixed and significantly reduced number of model calls at inference time. While our approach achieves competitive performance with strong autoregressive baselines (GPT-2 and BART) across several harmonic metrics, its key advantages lie in controllability, structured decoding with fixed inference steps, and alignment with musical structure. Ablation studies further highlight the role of stage awareness and pitch class conditioning. Our results position this method as a viable and interpretable alternative for symbolic harmony generation and a foundation for future work on structured, controllable musical modeling. Full article

The Mysteries of Udolpho was published at a time when poetry and music were being redefined, along with the notions of imitation and expression. From a precedence of word over music, theorists, musicians and composers started reconsidering the hierarchy of arts, which led to a new appreciation of both sung music and instrumental music. Ann Radcliffe’s novel is replete with pleasing sounds and mysterious melodies, working both as part of her décor and general soundscape and as a key element of the narrative. Given the novel’s musical profusion and versatility, one may wonder how to adapt its musicality into actual music. This paper, therefore, endeavors to define the balance of imitation and expression in The Mysteries of Udolpho and questions the ability of other media, especially those relying on sounds, to adapt its musical richness. It first focuses on the novel’s inscription in the larger context of musical theory, before delving into the limits of language’s sound mimesis and its counteracting expressivity. The final part is a case study of three artworks inspired by Radcliffe’s novel: John Bray’s song “Soft as yon’s silver ray that sleeps”, Catherine Czerkawska’s radio dramatization The Mysteries of Udolpho, and Marc Morvan and Benjamin Jarry’s album Udolpho. Full article

Text-to-music generation integrates natural language processing and music generation, enabling artificial intelligence (AI) to compose music from textual descriptions. While AI-enabled music generation has advanced, challenges in aligning text with musical structures remain underexplored. This paper systematically reviews text-to-music generation across symbolic and audio domains, covering melody composition, polyphony, instrumental synthesis, and singing voice generation. It categorizes existing methods into traditional, hybrid, and end-to-end LLM-centric frameworks according to the usage of large language models (LLMs), highlighting the growing role of LLMs in improving controllability and expressiveness. Despite progress, challenges such as data scarcity, representation limitations, and long-term coherence persist. Future work should enhance multi-modal integration, improve model generalization, and develop more user-controllable frameworks to advance AI-enabled music composition. Full article

Advancements in music emotion prediction are driving AI-driven algorithmic composition, enabling the generation of complex melodies. However, bridging neural and auditory domains remains challenging due to the semantic gap between brain-derived low-level features and high-level musical concepts, making alignment computationally demanding. This study proposes a deep learning framework for generating MIDI sequences aligned with labeled emotion predictions through supervised feature extraction from neural and auditory domains. EEGNet is employed to process neural data, while an autoencoder-based piano algorithm handles auditory data. To address modality heterogeneity, Centered Kernel Alignment is incorporated to enhance the separation of emotional states. Furthermore, regression between feature domains is applied to reduce intra-subject variability in extracted Electroencephalography (EEG) patterns, followed by the clustering of latent auditory representations into denser partitions to improve MIDI reconstruction quality. Using musical metrics, evaluation on real-world data shows that the proposed approach improves emotion classification (namely, between arousal and valence) and the system’s ability to produce MIDI sequences that better preserve temporal alignment, tonal consistency, and structural integrity. Subject-specific analysis reveals that subjects with stronger imagery paradigms produced higher-quality MIDI outputs, as their neural patterns aligned more closely with the training data. In contrast, subjects with weaker performance exhibited auditory data that were less consistent. Full article

Music generation by AI algorithms like Transformer is currently a research hotspot. Existing methods often suffer from issues related to coherence and high computational costs. To address these problems, we propose a novel Transformer-based model that incorporates a gate recurrent unit with root mean square norm restriction (TARREAN). This model improves the temporal coherence of music by utilizing the gate recurrent unit (GRU), which enhances the model’s ability to capture the dependencies between sequential elements. Additionally, we apply masked multi-head attention to prevent the model from accessing future information during training, preserving the causal structure of music sequences. To reduce computational overhead, we introduce root mean square layer normalization (RMS Norm), which smooths gradients and simplifies the calculations, thereby improving training efficiency. The music sequences are encoded using a compound word method, converting them into discrete symbol-event combinations for input into the TARREAN model. The proposed method effectively mitigates discontinuity issues in generated music and enhances generation quality. We evaluated the model using the Essen Associative Code and Folk Song Database, which contains 20,000 folk melodies from Germany, Poland, and China. The results show that our model produces music that is more aligned with human preferences, as indicated by subjective evaluation scores. The TARREAN model achieved a satisfaction score of 4.34, significantly higher than the 3.79 score of the Transformer-XL + REMI model. Objective evaluation also demonstrated a 15% improvement in temporal coherence compared to traditional methods. Both objective and subjective experimental results demonstrate that TARREAN can significantly improve generation coherence and reduce computational costs. Full article

Noise reduction methods have been proposed for various loud noises. However, in a quiet indoor environment, even small noises often cause discomfort. One of the small noises that causes discomfort is noise with resonant frequencies. Since resonant frequencies are often high frequencies, it is difficult to apply conventional active noise control methods to them. To solve this problem, we focused on auditory masking, a phenomenon in which synthesized sounds increase the audible threshold. We have performed several studies on reducing discomfort based on auditory masking. However, it was difficult for comfortable sound design to be achieved using the previously proposed methods, even though they were able to reduce feelings of discomfort. Here, we focus on a pleasant sound: music. Comfortable sound design is made possible by introducing music theory into the design of masker signals. In this paper, we therefore propose comfortable sound design based on auditory masking with chord progression and melody generation to match the peak frequencies of dental treatment noises. Full article

Background/Objectives: Musical pleasure is considered to be induced by prediction errors (surprise), as suggested in neuroimaging studies. However, the role of temporal changes in musical features in reward processing remains unclear. Utilizing the Information Dynamics of Music (IDyOM) model, a statistical model that calculates musical surprise based on prediction errors in melody and harmony, we investigated whether brain activities associated with musical pleasure, particularly in the θ, β, and γ bands, are induced by prediction errors, similar to those observed during monetary rewards. Methods: We used the IDyOM model to calculate the information content (IC) of surprise for melody and harmony in 70 musical pieces across six genres; eight pieces with varying IC values were selected. Electroencephalographic data were recorded during listening to the pieces, continuously evaluating the participants’ subjective pleasure on a 1–4 scale. Time–frequency analysis of electroencephalographic data was conducted, followed by general linear model analysis to fit the power-value time course in each frequency band to the time courses of subjective pleasure and IC for melody and harmony. Results: Significant positive fits were observed in the β and γ bands in the frontal region with both subjective pleasure and IC for melody and harmony. No significant fit was observed in the θ band. Both subjective pleasure and IC are associated with increased β and γ band power in the frontal regions. Conclusions: β and γ oscillatory activities in the frontal regions are strongly associated with musical rewards induced by prediction errors, similar to brain activity observed during monetary rewards. Full article

Composing coherent and structured music is one of the main challenges in symbolic music generation. Our research aims to propose a user-centric framework design that promotes a collaborative environment between users and knowledge agents. The primary objective is to improve the music creation process by actively involving users who provide qualitative feedback and emotional assessments. The proposed framework design constructs an abstract format in which a musical piece is represented as a sequence of musical samples. It consists of multiple agents that embody the dynamics of musical creation, emphasizing user-driven creativity and control. This user-centric approach can benefit individuals with different musical backgrounds, encouraging creative exploration and autonomy in personalized, adaptive environments. To guide the design of this framework, we investigate several key research questions, including the optimal balance between system autonomy and user involvement, the extraction of rhythmic and melodic features through musical sampling, and the effectiveness of topological and hierarchical data representations. Our discussion will highlight the different aspects of the framework in relation to the research questions, expected outcomes, and its potential effectiveness in achieving objectives. Through establishing a theoretical foundation and addressing the research questions, this work has laid the groundwork for future empirical studies to validate the framework and its potential in symbolic music generation. Full article

Loving-kindness meditation (LKM) has been widely used in promoting mental health, with positive emotions as an important mechanism. The current study explored the impact of background music on the effects and difficulties of LKM practice. Two hundred participants were randomly divided into six groups, wherein LKM plus music with harmony only, LKM plus music with harmony and melody, and LKM without music were presented in a different order during the intermediate three days of a five-day LKM intervention. Participants reported three types of positive emotions (pro-social, low-arousal, and medium-arousal positive emotions) and the difficulties during meditation (lack of concentration and lack of pro-social attitudes) after each of three sessions. The results of MANOVA indicated that compared to the session without music, incorporating music could evoke more low-arousal positive emotions and pro-social positive emotions without altering the difficulties. However, the results did not reveal significant differences in the effects of music with harmony and music with harmony and melody on both emotions and difficulties. Additionally, practice effects may have influenced the generation of medium-arousal positive emotions and the difficulty of concentration, but the results were inconsistent across groups. Our findings suggest potential benefits for practitioners of LKM in incorporating music during the meditation process, and the directions for future research were further discussed. Full article