Motifs often recur in musical works in altered forms, preserving aspects of their identity while undergoing local variation. This paper investigates how such motivic transformations occur within their musical context in symbolic music. To support this analysis, we develop a probabilistic framework for modeling motivic transformations and apply it to Beethoven's piano sonatas by integrating multiple datasets that provide melodic, rhythmic, harmonic, and motivic information within a unified analytical representation. Motif transformations are represented as multilabel variables by comparing each motif instance to a designated reference occurrence within its local context, ensuring consistent labeling across transformation families. We introduce a multilabel Conditional Random Field to model how motif-level musical features influence the occurrence of transformations and how different transformation families tend to co-occur. Our goal is to provide an interpretable, distributional analysis of motivic transformation patterns, enabling the study of their structural relationships and stylistic variation. By linking computational modeling with music-theoretical interpretation, the proposed framework supports quantitative investigation of musical structure and complexity in symbolic corpora and may facilitate the analysis of broader compositional patterns and writing practices.
Automatic Music Transcription (AMT) -- the task of converting music audio into note representations -- has seen rapid progress, driven largely by deep learning systems. Due to the limited availability of richly annotated music datasets, much of the progress in AMT has been concentrated on classical piano music, and even a few very specific datasets. Whether these systems can generalize effectively to other musical contexts remains an open question. Complementing recent studies on distribution shifts in sound (e.g., recording conditions), in this work we investigate the musical dimension -- specifically, variations in genre, dynamics, and polyphony levels. To this end, we introduce the MDS corpus, comprising three distinct subsets -- (1) Genre, (2) Random, and (3) MAEtest -- to emulate different axes of distribution shift. We evaluate the performance of several state-of-the-art AMT systems on the MDS corpus using both traditional information-retrieval and musically-informed performance metrics. Our extensive evaluation isolates and exposes varying degrees of performance degradation under specific distribution shifts. In particular, we measure a note-level F1 performance drop of 20 percentage points due to sound, and 14 due to genre. Generally, we find that dynamics estimation proves more vulnerable to musical variation than onset prediction. Musically informed evaluation metrics, particularly those capturing harmonic structure, help identify potential contributing factors. Furthermore, experiments with randomly generated, non-musical sequences reveal clear limitations in system performance under extreme musical distribution shifts. Altogether, these findings offer new evidence of the persistent impact of the Corpus Bias problem in deep AMT systems.
Recent advancements in diffusion models have significantly improved symbolic music generation. However, most approaches rely on transformer-based architectures with self-attention mechanisms, which are constrained by quadratic computational complexity, limiting scalability for long sequences. To address this, we propose Symbolic Music Diffusion with Mamba (SMDIM), a novel diffusion-based architecture integrating Structured State Space Models (SSMs) for efficient global context modeling and the Mamba-FeedForward-Attention Block (MFA) for precise local detail preservation. The MFA Block combines the linear complexity of Mamba layers, the non-linear refinement of FeedForward layers, and the fine-grained precision of self-attention mechanisms, achieving a balance between scalability and musical expressiveness. SMDIM achieves near-linear complexity, making it highly efficient for long-sequence tasks. Evaluated on diverse datasets, including FolkDB, a collection of traditional Chinese folk music that represents an underexplored domain in symbolic music generation, SMDIM outperforms state-of-the-art models in both generation quality and computational efficiency. Beyond symbolic music, SMDIM's architectural design demonstrates adaptability to a broad range of long-sequence generation tasks, offering a scalable and efficient solution for coherent sequence modeling.
Maral Ebrahimzadeh, Gilberto Bernardes, Sebastian Stober
State-of-the-art symbolic music generation models have recently achieved remarkable output quality, yet explicit control over compositional features, such as tonal tension, remains challenging. We propose a novel approach that integrates a computational tonal tension model, based on tonal interval vector analysis, into a Transformer framework. Our method employs a two-level beam search strategy during inference. At the token level, generated candidates are re-ranked using model probability and diversity metrics to maintain overall quality. At the bar level, a tension-based re-ranking is applied to ensure that the generated music aligns with a desired tension curve. Objective evaluations indicate that our approach effectively modulates tonal tension, and subjective listening tests confirm that the system produces outputs that align with the target tension. These results demonstrate that explicit tension conditioning through a dual-level beam search provides a powerful and intuitive tool to guide AI-generated music. Furthermore, our experiments demonstrate that our method can generate multiple distinct musical interpretations under the same tension condition.
Irawan Sukma, Sri Rochana Widyastutieningrum, Aton Rustandi Mulyana
In the context of Anwar Beck, his lyrics reflect a sensitivity to cultural, social, and local identity issues in Palembang. However, in-depth studies on the influence of personal and social ideology in his works remain scarce. This study examines the ideology underlying the creative process of musician Anwar Beck and how this ideology is represented in the lyrics and themes of his songs. Using a qualitative approach and critical discourse analysis, this research explores Beck's ideological views through in-depth interviews, an analysis of the lyrics of five selected songs: Musimu Musiku, Raso-raso, Keladi Tumbuh di Lebak, Kemano Pegi, and Kembang Sriwijaya, as well as a literature review on the theory of ideology in art and music. The data analysis techniques used include thematic analysis to identify ideological patterns in the song lyrics and interviews, along with data validation through source and method triangulation. The study results show that Anwar Beck's songs embody a complex ideology, blending criticism of local culture's marginalization with efforts to preserve and empower Palembang's cultural identity. Bahasa Palembang Halus and Sari-sari serve as mediums for Beck's artistic ideology and strategies for preserving Palembang's cultural and linguistic values.
Patricia Hu, Lukáš Samuel Marták, Carlos Cancino-Chacón
et al.
Automatic piano transcription models are typically evaluated using simple frame- or note-wise information retrieval (IR) metrics. Such benchmark metrics do not provide insights into the transcription quality of specific musical aspects such as articulation, dynamics, or rhythmic precision of the output, which are essential in the context of expressive performance analysis. Furthermore, in recent years, MAESTRO has become the de-facto training and evaluation dataset for such models. However, inference performance has been observed to deteriorate substantially when applied on out-of-distribution data, thereby questioning the suitability and reliability of transcribed outputs from such models for specific MIR tasks. In this work, we investigate the performance of three state-of-the-art piano transcription models in two experiments. In the first one, we propose a variety of musically informed evaluation metrics which, in contrast to the IR metrics, offer more detailed insight into the musical quality of the transcriptions. In the second experiment, we compare inference performance on real-world and perturbed audio recordings, and highlight musical dimensions which our metrics can help explain. Our experimental results highlight the weaknesses of existing piano transcription metrics and contribute to a more musically sound error analysis of transcription outputs.
We present the IEEE-IS2 2024 Music Packet Loss Concealment Challenge. We begin by detailing the challenge rules, followed by an overview of the provided baseline system, the blind test set, and the evaluation methodology used to determine the final ranking. This inaugural edition aimed to foster collaboration between researchers and practitioners from the fields of signal processing, machine learning, and networked music performance, while also laying the groundwork for future advancements in packet loss concealment for music signals.
Previous studies on music style transfer have mainly focused on one-to-one style conversion, which is relatively limited. When considering the conversion between multiple styles, previous methods required designing multiple modes to disentangle the complex style of the music, resulting in large computational costs and slow audio generation. The existing music style transfer methods generate spectrograms with artifacts, leading to significant noise in the generated audio. To address these issues, this study proposes a music style transfer framework based on diffusion models (DM) and uses spectrogram-based methods to achieve multi-to-multi music style transfer. The GuideDiff method is used to restore spectrograms to high-fidelity audio, accelerating audio generation speed and reducing noise in the generated audio. Experimental results show that our model has good performance in multi-mode music style transfer compared to the baseline and can generate high-quality audio in real-time on consumer-grade GPUs.
This paper explores transformer-based models for music overpainting, focusing on jazz piano variations. Music overpainting generates new variations while preserving the melodic and harmonic structure of the input. Existing approaches are limited by small datasets, restricting scalability and diversity. We introduce VAR4000, a subset of a larger dataset for jazz piano performances, consisting of 4,352 training pairs. Using a semi-automatic pipeline, we evaluate two transformer configurations on VAR4000, comparing their performance with the smaller JAZZVAR dataset. Preliminary results show promising improvements in generalisation and performance with the larger dataset configuration, highlighting the potential of transformer models to scale effectively for music overpainting on larger and more diverse datasets.
Michał Wiszenko, Kacper Stefański, Piotr Malesa
et al.
Symbolic music research plays a crucial role in music-related machine learning, but MIDI data can be complex for those without musical expertise. To address this issue, we present MidiTok Visualizer, a web application designed to facilitate the exploration and visualization of various MIDI tokenization methods from the MidiTok Python package. MidiTok Visualizer offers numerous customizable parameters, enabling users to upload MIDI files to visualize tokenized data alongside an interactive piano roll.
This article tryes to initiate the concept of Minangkabau rhythm syllables, which is a method in music learning related to audiation in rhythm learning, the urgency in this study explores the basic elements of the audiation system that can be applied to music learning related to rhythm syllables based on local approaches, taking into account previous concepts that have been popular in recent schools. In West Sumatra, the concepts of syllable rhythm such as Zoltan Kodaly, Kannokol, American Style Syllables, and Edwin Gordon are not so popular, but environments such as schools and art studios have their own ways of approaching learning music related to pronouncing sounds, so that in this study it is addressed as an interesting and crucial thing to study and formulate further into formulations. The method used in this research uses a qualitative paradigm with a literature review approach. Where the concept of previous rhythmic syllables is used as a reference in analyzing, bringing up findings, and juxtaposing the findings with the initiated Minangkabau rhythmic syllable formula, so that the Minangkabau rhythmic syllables can be generalized and adapted, but still referring to the habits of the local community material. Based on the results of the analysis, like Gordon’s concept, it is found that syllables or audiation appear after the formation of rhythms, patterns and sound colors from an instrument, which can then strengthen the form of audiation into verbal form.
Ethnology. Social and cultural anthropology, Philosophy. Psychology. Religion
The Journal of Linguistic and Rhetorical Studies is one of the core journals in its Journal of Linguistic and Rhetorical Studies, having reached the first quarter and received the A rank, is one of the core humanities journals of Semnan University. Due to its significant status, the present research was conducted with the aim of analyzing the content of the articles of published in this Journal spanning the years 2010/1389 to 2023/1402. This research was done using the content analysis method for the statistical population of the 370 scientific articles published by Journal of Linguistic and Rhetorical Studies of Semnan University from 2010 to 2023. Sampling was not used in this research and the research population was investigated by census. By examining each article, necessary data were collected and analyzed using Excel software. The findings of the research showed that from 2010 to 2023, 370 articles were published in Journal of Language and Rhetoric Studies of Semnan University. Most of the articles were written by male authors (65% of the articles), with the scientific rank of assistant professor (30% of the articles), and the organizational affiliation of most of the articles belonged to Semnan University (10% of the articles). Concerning the variety of the disciplines, the fields of Persian language and literature (75 percent), general linguistics (7 percent), and Arabic language and literature (5 percent) showed the highest rate of publication. In the review and analysis of the journal articles, 1600 topics were identified with open code, out of which about 500 more frequent topics were selected in about 20 main topics. The first to third ranks of the main topics were dedicated to poetry and poets (9 percent), rhetoric (7.9 percent), and style and stylistics (6.3 percent). These were followed by metaphor, language and linguistics, sonnets and sonnets sequences, analysis, image and visualization. The remaining ten topics of the 370 articles were related to literary devices, literary elements, language structure, literature, story, simile, music, aesthetics, literary layers, grammar, and other fields. In the process of internationalization of publications, geographical distribution of authors is an important indicator. Since the review and analysis of the articles of Journal of Linguistic and Rhetorical Studies showed that the pattern of publishing articles was based on domestic authors, planning is deemed necessary to elevate the geographical distribution of authors at the international level.
Tablature notation is widely used in popular music to transcribe and share guitar musical content. As a complement to standard score notation, tablatures transcribe performance gesture information including finger positions and a variety of guitar-specific playing techniques such as slides, hammer-on/pull-off or bends.This paper focuses on bends, which enable to progressively shift the pitch of a note, therefore circumventing physical limitations of the discrete fretted fingerboard. In this paper, we propose a set of 25 high-level features, computed for each note of the tablature, to study how bend occurrences can be predicted from their past and future short-term context. Experiments are performed on a corpus of 932 lead guitar tablatures of popular music and show that a decision tree successfully predicts bend occurrences with an F1 score of 0.71 anda limited amount of false positive predictions, demonstrating promising applications to assist the arrangement of non-guitar music into guitar tablatures.
Alessandro Guglielmo, Anja Plonka, Csenge Kolozsvari
et al.
Csenge Kolozsvari, "Bodylandscapes I." (10:58). A proposition for remembering the ecological ways of belonging, a feeling into other ways of knowing, connecting into the vastness that surrounds us and moves across us, becoming-environment once again. // Anja Plonka, Marko Stefanovic, and Rasmus Nordholt-Frieling, "Breathing Gaia: Searching for Kinship Around Walensee" (8:28). The video essay creates a speculative-utopian body and existence of human and non-human. The body as an archive of traumatic inscriptions practices transformation as a being in resonance with Gaia. // Jessica Marion Barr, Jenn Cole, and LA Alfonso, "Our Bodies, These Lands: Practising Reciprocity" (6:03). As artist-researchers with embodied practices and relationships with lands and waters, we explore a unique part of Michi Saagig Nishnaabeg territory wherein “rockmills” or “kettles” offer spaces for our human selves to be held and surrounded by massive ancient rock beings. // Alessandro Guglielmo, "Wisdom and Trouble: Notes on Blood, Care, and Death in Multispecies Settings" (9:30). In this video essay, I employ my emplacement as a vegetarian anthropologist witnessing the killing of a non-human being to produce an understanding of more-than-human ecologies. I reflect on narratives of death, and the trouble of care and killing in multispecies settings.